JP6582876B2 - Video storage system, video storage device, and program - Google Patents

Description

  The present invention relates to a video storage system, a video storage device, and a program.

  In recent years, with the heightened social security awareness and the progress of surveillance cameras, the number of surveillance cameras installed in public spaces such as station premises and shopping malls is increasing. In addition, a network camera connected to a network is spreading as a monitoring camera, and remote video monitoring using an existing network is possible. In addition, the resolution of captured images taken by the surveillance camera is also increasing, and it is becoming possible to monitor the situation in more detail than before.

  On the other hand, as the number of cameras increases and the image quality increases, the amount of captured video data increases significantly. For example, the amount of video data stored in the data storage server via the network is reduced. Is required. As a technique for reducing the amount of video data, for example, a technique for efficiently recording video by changing the compression rate for each frame in video compression has been developed.

  For example, in Patent Document 1, it is determined on the basis of voice whether or not active discussion is being performed in the application of conference recording or coverage recording, and the compression rate is varied for each frame based on the determination result. A technique for performing recompression is disclosed. Further, in Patent Document 2, when an object to be monitored is detected and the detected object area is similar to the object area in the transmitted image, the image of the detected object area is not transmitted, A technique for notifying identification information of the object is disclosed.

Japanese Patent No. 3960646 JP 2012-209831 A

  However, in Patent Document 1, although the compression rate is determined by making a determination for each frame, there is no distinction for each region in the image (frame), and there is room for further efficiency. In addition, in the technique described in Patent Document 2, images of similar object regions are not transmitted. For example, it is impossible to grasp the detailed behavior or detailed situation of a person, and a sufficient amount of information can be obtained even in an important region. Sometimes it was not recorded.

  Accordingly, the present invention has been made in view of the above problems, and an object of the present invention is to reduce the amount of accumulated video data while recording important areas with high definition. Another object of the present invention is to provide a new and improved video storage system, video storage device, and program.

In order to solve the above-described problem, according to an aspect of the present invention, a video analysis unit that detects a monitoring target event to be monitored from a captured video and analyzes a situation related to the monitoring target event, and the video analysis unit Based on the analysis result of the first, the importance level identifying unit for identifying the importance level for each area of the captured video and generating the importance level information, the importance level information, and the captured video are associated with each other. When the video recording unit for recording the video recording information and the video recording status of the video recording unit satisfy a predetermined condition, the importance information is included in the importance information for each of the areas of the captured video included in the first video recording information. a video compression unit for performing video compression at a compression rate based, a second video recording information based on the image compression, and recording the image updating unit for the to be recorded in the video recording unit in place of the first video recording information, the Before corresponding to one time Based on the importance information, recorded on the video recording unit, provides the video storage system and an importance updating unit for updating the importance information corresponding to the second time before the first time Is done.

  The video compression unit may perform the video compression such that a region having a higher importance is compressed at a lower compression rate in the importance information.

  The video storage system may further include a recording status determination unit that determines whether the video recording status satisfies the predetermined condition.

  The importance information may be included in the second video recording information.

  The recording status determination unit performs the determination for a plurality of the predetermined conditions, and the video compression unit compresses the captured video recorded in the video recording unit based on the determination by the recording status determination unit. May be.

  The importance level update unit may update the importance level information corresponding to the second time for a region having an importance level equal to or higher than a predetermined value in the importance level information corresponding to the first time. .

  The video analysis unit tracks the monitoring target event, and the importance level update unit includes the monitoring target included in a region having an importance level equal to or higher than a predetermined value in the importance level information corresponding to the first time. For the region based on the event, the importance level information corresponding to the second time may be updated.

In order to solve the above problem, according to another aspect of the present invention, based on an analysis result obtained by analyzing a situation related to a monitoring target event that is detected from a captured video and is a monitoring target, An importance level specifying unit that specifies importance level for each area of a captured video and generates importance level information, and video recording that records first video recording information in which the importance level information and the captured video are associated with each other And when the video recording status of the video recording unit satisfies a predetermined condition, video compression is performed at a compression rate based on the importance information for each area of the captured video included in the first video recording information A video compression unit, a recorded video update unit for recording the second video recording information based on the video compression in the video recording unit instead of the first video recording information, and the important corresponding to the first time Based on the degree information. Recorded in the recording unit, and the importance updating unit for updating the importance information corresponding to the second time before the first time, the image storage apparatus comprising a are provided.

In order to solve the above problems, according to another aspect of the present invention, based on an analysis result obtained by analyzing a situation related to a monitoring target event to be monitored and detected from a captured video on a computer. The importance specifying function for specifying the importance for each area of the captured video and generating the importance information, and the first video recording information in which the importance information and the captured video are associated with each other are recorded. A video compression function for performing video compression at a compression rate based on the importance information for each area of the captured video included in the first video recording information when the video recording status of the recording device that satisfies the condition satisfies The second video recording information based on the video compression is recorded on the recording device instead of the first video recording information, and the importance level information corresponding to the first time is recorded on the recording device. , The above Is recorded in the device, for realizing the importance of update function for updating the importance information corresponding to the second time before the first time, the program is provided.

  As described above, according to the present invention, it is possible to reduce the amount of stored video data while recording an important area with high definition.

It is explanatory drawing which shows the outline | summary of the video storage system 1 which concerns on 1st embodiment of this invention. It is explanatory drawing which shows the structural example of the monitoring camera 10 by the embodiment. It is explanatory drawing which shows typically the example of importance specification based on the person's face detection by the detection part 132 concerning the embodiment. It is explanatory drawing which shows typically the example of importance specification based on the person's abnormal action recognition by the situation recognition part 134 which concerns on the embodiment. It is explanatory drawing which shows the structural example of the video storage apparatus 20 by the same embodiment. It is explanatory drawing which shows the operation example of the surveillance camera 10 which concerns on the embodiment. FIG. 7 is an explanatory diagram illustrating an operation example of the video storage device 20 according to the embodiment. It is explanatory drawing for demonstrating the specific example of the recompression process of the image | video by the video storage apparatus 20 which concerns on the embodiment. It is explanatory drawing which shows the structural example of the video storage apparatus which concerns on the 1st modification of the embodiment. It is explanatory drawing which shows the structural example of the surveillance camera 50 which concerns on 2nd embodiment of this invention. It is explanatory drawing which shows the structural example of the video storage apparatus 60 by the same embodiment. It is explanatory drawing which shows the operation example of the surveillance camera 50 by the embodiment. FIG. 7 is an explanatory diagram illustrating an operation example of the video storage device 60 according to the same embodiment. It is explanatory drawing which shows the hardware structural example.

  Exemplary embodiments of the present invention will be described below in detail with reference to the accompanying drawings. In addition, in this specification and drawing, about the component which has the substantially same function structure, duplication description is abbreviate | omitted by attaching | subjecting the same code | symbol.

  In the present specification and drawings, a plurality of components having substantially the same functional configuration may be distinguished by adding different alphabets after the same reference numeral. However, when it is not necessary to particularly distinguish each of a plurality of constituent elements having substantially the same functional configuration, only the same reference numerals are given.

<< 1. First embodiment >>
<1-1. Overview>
First, the outline of the information processing system according to the first embodiment of the present invention will be described with reference to FIG. FIG. 1 is an explanatory diagram showing an overview of a video storage system 1 according to the first embodiment of the present invention.

  As shown in FIG. 1, the video storage system 1 includes monitoring cameras 10 </ b> A and 10 </ b> B, a video storage device 20, and a communication network 30.

  Monitoring camera 10A, 10B is an apparatus which images and acquires a picked-up image. The acquired captured video is transmitted from the monitoring cameras 10A and 10B to the video storage device 20 via the communication network 30. The monitoring cameras 10A and 10B may be information processing apparatuses having an information processing function such as compression processing of captured video and detection processing of an object included in the captured video. In this specification, a video is data (information) including at least a plurality of frames of images. Further, in this specification, the captured video is a video obtained based on the imaging of the monitoring cameras 10A and 10B. For example, the video obtained by the imaging of the monitoring cameras 10A and 10B is also obtained by compressing the video. Video may also be included in the captured video. Hereinafter, the captured video may be simply referred to as video.

  The video storage device 20 is a data storage server (information processing device) that records (stores) the captured video received from the monitoring cameras 10 </ b> A and 10 </ b> B in the video recording unit 230 included in the video storage device 20. The video storage device 20 may record the captured video in the video recording unit 230 after compressing or recompressing the captured video.

  The communication network 30 is a wired or wireless transmission path for information transmitted from a device connected to the communication network 30. For example, the communication network 30 may include a public line network such as the Internet, a telephone line network, a satellite communication network, various local area networks (LANs) including the Ethernet (registered trademark), a wide area network (WAN), and the like. . The communication network 30 may include a dedicated line network such as an IP-VPN (Internet Protocol-Virtual Private Network).

  1 illustrates an example in which the video storage system 1 according to the present embodiment includes two monitoring cameras 10A and 10B. However, the video storage system 1 may include one monitoring camera or three or more monitoring cameras. There may be.

<1-2. Background>
The outline of the video storage system 1 according to the first embodiment of the present invention has been described above. Next, the background that led to the creation of the video storage system according to the present embodiment will be described.

  In recent years, with the heightened social security awareness and the progress of surveillance cameras, the number of surveillance cameras installed in public spaces such as station premises and shopping malls is increasing. In addition, the resolution of captured images taken by the surveillance camera is also increasing, and it is becoming possible to monitor the situation in more detail than before.

  With the increase in the number of cameras and the increase in image quality as described above, the amount of captured video data stored in a data storage server such as the video storage device 20 described above has increased significantly, making it difficult to record video for a long time. It becomes. For this reason, it is required to reduce the amount of captured video data stored in the data storage server.

  In order to reduce the amount of video data, it is conceivable to change the compression rate for each frame in video compression and record video efficiently. For example, by setting the compression rate of frames that are determined to be important low and the compression rate of frames that are not determined to be high to perform video compression, only important frames are recorded in high definition while reducing the amount of data. Is possible.

  It is also conceivable to determine the degree of similarity with a transmitted image by image analysis and reduce the amount of data based on the result of the determination. For example, when an object to be monitored is detected from a captured video and the detected object area is similar to the object area in the transmitted image, the image of the detected object area is not transmitted and the object By notifying the identification information, the amount of data to be transmitted can be reduced.

  However, when the compression rate is changed for each frame as in the former case, the difference in importance depending on the area in the image is not considered, but the importance may differ depending on the area in the image. For example, the area of the face or the peripheral area of the abnormally behaving person is considered important in the monitoring video. Therefore, there is room for further efficiency by considering the difference in importance depending on the region in the image.

  In addition, when the object area already transmitted and the object area of the current frame are similar as in the latter case, the method of not transmitting the object area of the current frame cannot visually recognize the latest accurate situation. was there. For example, for a person area that is considered to be an important area in the surveillance video, if the current area of the current frame is not transmitted, the detailed behavior of the fallen person or the detailed status of the staggered person may not be confirmed. .

  Therefore, the present inventor has come up with an embodiment of the present invention by focusing on the above circumstances. The video storage system according to the embodiment of the present invention can reduce the amount of stored video data while recording an important area with high definition. Hereinafter, configurations of the monitoring camera 10 and the video storage device 20 for realizing the above-described effects in the video storage system according to the embodiment of the present invention will be sequentially described in detail.

  In the following, an example in which there is one monitoring camera 10 and the monitoring camera 10 and the video storage device 20 perform one-to-one communication will be described. However, the present embodiment is not limited to this example, and FIG. As described above, the present invention can be similarly applied to the case where there are a plurality of surveillance cameras 10.

<1-3. Configuration of surveillance camera>
FIG. 2 is an explanatory diagram showing a configuration example of the monitoring camera 10 according to the first embodiment of the present invention. As shown in FIG. 2, the monitoring camera 10 is an information processing apparatus including an imaging unit 110, a video analysis unit 130, an importance level specification unit 150, a video compression unit 170, and a transmission unit 190.

(Imaging part)
The imaging unit 110 is a camera module that acquires captured video. The imaging unit 110 acquires a captured video by imaging a real space using an imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). The captured video acquired by the imaging unit 110 is provided to the video analysis unit 130 and the video compression unit 170.

  The imaging unit 110 may include a visible light camera that can acquire a visible light image, an infrared camera that can acquire a near-infrared light image and a thermal image, a depth camera that can acquire a depth image, and the like. . For example, when the imaging unit 110 can acquire a thermal image, the video analysis unit 130 (to be described later) can detect a monitoring target event (for example, a person or a fire) with higher accuracy.

(Video Analysis Department)
The video analysis unit 130 has a video analysis function that detects a monitoring target event to be monitored from the captured video acquired by the imaging unit 110 and analyzes a situation related to the monitoring target event. The video analysis unit 130 according to the present embodiment includes a detection unit 132 and a situation recognition unit 134 as illustrated in FIG.

  The detection unit 132 detects one or a plurality of monitoring target events from the captured video. The monitoring target event according to the present embodiment may include, for example, an object existing in a video such as a human face, a person, a vehicle, or an event such as a disaster such as a fire, an earthquake, or an accident. In order for the detection unit 132 to detect the monitoring target event from the captured video, various image analysis methods can be applied, and a method corresponding to the type of the monitoring target event may be used. For example, when detecting a human face from an image, it is possible to use an object detection method based on statistical learning of image feature amounts, such as the technique described in Non-Patent Document 1 below.

  Non-Patent Document 1: P.I. Viola and M.M. Jones, “Rapid object Detection using a Boosted Cascade of Simple Features,” Proc. of IEEE Conf. Computer Vision and Pattern Recognition 2001 (USA), IEEE Computer Society Conference, 2001, vol. 1, pp. 511-518

  When the monitoring target event is a moving object, the detection unit 132 may track the monitoring target event on a plurality of frames of time-series images included in the captured video. Various object tracking methods such as a method using a particle filter or a Kalman filter and a method based on matching of image feature amounts used for object detection may be used for tracking the monitoring target event. According to such a configuration, it is possible to detect the monitoring target event once detected more stably. In addition, the video storage system 1 can acquire correspondence information between frames in the monitored event area.

  When the detection unit 132 detects a monitoring target event from the captured video, the monitoring target event identification information (ID information), the position of the monitoring target event in the captured video, and the monitoring target event area (area occupied by the monitoring target event) And the like are provided to the situation recognition unit 134 and the importance level identification unit 150. For example, the detection unit 132 may detect a person and the person's face as the monitoring target event, and provide information that associates the person and the person's face to the situation recognition unit 134 and the importance level specification unit 150.

  The situation recognition unit 134 recognizes (analyzes) a situation related to the monitored event detected by the detection unit 132. For example, the situation recognition unit 134 may perform situation recognition using time-series image information of a plurality of frames included in the captured video. In the present embodiment, the situation to be recognized may include, for example, an abnormal behavior of a person such as a fall or a staggered foot, an abnormal operation of a vehicle such as reverse running or a sudden stop, or occurrence of a disaster (fire, earthquake, accident, etc.). Good.

  In order for the situation recognizing unit 134 to recognize the situation related to the monitoring target event, various video analysis methods can be applied, and a technique corresponding to the type of the monitoring target event and the type of the situation may be used. For example, when recognizing an abnormal behavior of a person from a captured video, a technique based on an image feature amount called CHLAC (stereoscopic higher-order local autocorrelation), such as a technique described in Non-Patent Document 2 below, is used. Also good. In such a case, for example, the situation recognition unit 134 identifies normal operation or abnormal operation based on the subspace method using the subspace learned using the image feature amount extracted from the normal operation video. May be.

  Non-Patent Document 2: Takuya Nanzato, Nobuyuki Otsu, “Detection of abnormal motion from multiple human moving images,” Information Processing Society of Japan Journal of Computer Vision and Image Media, Information Processing Society of Japan, October 15, 2005, Vol. 45, no. SIG_15, pp. 43-50

(Importance level identification part)
The importance level identifying unit 150 has an importance level identifying function that identifies (assigns) an importance level for each region of a captured video and generates importance level information based on the analysis result of the video analysis unit 130. The importance level information generated by the importance level specifying unit 150 is provided to the transmission unit 190.

The importance may be expressed by a numerical value, for example. In the following, an example will be described in which the greater the importance value is, the more important it is, and the importance may take the following three values.
2: Indicates that importance is high. Sometimes expressed as “high”.
1: Indicates that the importance is medium. Sometimes referred to as “medium”.
0: Indicates that the importance is low. Sometimes expressed as “low”.

  The importance level information may be, for example, map-like information indicating the importance level for every position in each frame of a captured video, or information specifying an area having a medium or higher level (1 or higher level). Also good. In the following, the importance level information according to the present embodiment is assumed to be information specifying an area having a medium importance level or higher (1 or higher), and areas other than the area are regarded as low in importance level (importance level). “Low” is assigned).

  The importance level specifying unit 150 may specify the importance level based on the position or region of the monitoring target event detected by the detection unit 132. Further, the importance level identifying unit 150 may identify the importance level based on the status of the monitoring target event recognized by the status recognition unit 134.

  For example, the importance level specifying unit 150 may assign a predetermined importance level (for example, an importance level “medium”) to an area where the detection unit 132 has detected a human face. Further, when the situation recognition unit 134 recognizes the abnormal behavior of the person detected by the detection unit 132, the importance level identification unit 150 assigns a higher importance level (for example, importance level “high”) to the peripheral area of the person. It may be assigned. Hereinafter, with reference to FIGS. 3 and 4, an example of importance level identification by the importance level identifying unit 150 will be described.

  FIG. 3 is an explanatory diagram schematically showing an example of specifying the importance level based on the human face detection by the detection unit 132. An image R1 illustrated in FIG. 3 is a schematic diagram in which a human face detection result by the detection unit 132 that receives the image is superimposed on an image of the tth frame of the captured video, and Table J1 is an image of the tth frame. Is an example of the importance level information generated by the importance level specifying unit 150.

  FIG. 3 shows a face rectangle F1 (xs1, ys1, xe1, ye1) including the face area of the person H1 and a face rectangle F2 (xs2, ys2, xe2, ye2) including the face area of the person H2 in the image R1. Is shown as a face detection result by the detection unit 132. Each area may be specified by upper left coordinates and lower right coordinates as shown in FIG. 3. For example, the face rectangle F1 has upper left coordinates (xs1, ys1) and lower right coordinates (xe1, ye1) shown in FIG. ) Can be expressed as a rectangular area (xs1, ys1, xe1, ye1) specified by

  Note that face rectangle information is provided from the detection unit 132 to the importance level identification unit 150 as a face detection result. The importance level identifying unit 150 that has received the face detection result assigns importance level information “medium” to each rectangular area (face rectangle) of the detected person's face as shown in Table J1 of FIG. Is generated.

  FIG. 4 is an explanatory diagram schematically showing an example of specifying the importance level based on the recognition of the abnormal behavior of the person by the situation recognition unit 134. An image R2 illustrated in FIG. 4 is a schematic diagram in which a human face detection result by the detection unit 132 using the image as an input and a human abnormal behavior recognition result by the situation recognition unit 134 are superimposed on an image of the t-th frame of the captured video. FIG. Table J2 illustrated in FIG. 4 is an example of importance information generated by the importance specifying unit 150 for the image of the t-th frame.

  As shown in the image R2 of FIG. 4 and the table J2, a face rectangle F1 indicating the face area of the person H1 in the image R2 is obtained as a face detection result by the detection unit 132, and similarly to the example shown in FIG. The importance “medium” is assigned to the face rectangle F1 (xs1, ys1, xe1, ye1). Further, when the situation recognition unit 134 recognizes the abnormal behavior of the person H2 shown in FIG. 4, the importance “high” is assigned to the surrounding rectangle M2 (xs2 ′, ys2 ′, xe2 ′, ye2 ′) of the person H2. .

  The peripheral rectangle M2 is set based on the person area detected by the detection unit 132, and may be a rectangle including the person area and a peripheral area of a predetermined size, or a rectangle indicating the entire image. Good. In addition, the setting method of the surrounding rectangle M2 by the importance specifying unit 150 may be different depending on the situation recognized by the situation recognition unit 134.

  For example, when a situation related to the entire image (for example, occurrence of an earthquake) is recognized, a peripheral rectangle M2 indicating the entire screen may be set. Further, when an abnormal behavior (for example, burglary) of a person affecting a relatively large range is recognized, a peripheral rectangle M2 including a sufficiently large range in the vicinity of the person and the person may be set. In addition, when an abnormal behavior (for example, staggered feet) of a person that affects a relatively small range is recognized, a peripheral rectangle M2 including the person and a small range near the person may be set.

  When the face rectangle area detected by the detection unit 132 and the surrounding rectangle area related to the situation recognized by the situation recognition unit 134 overlap, the higher importance (example shown in FIG. 4). Then, the degree of importance “high”) may be assigned to overlapping areas.

(Video compression part)
The video compression unit 170 illustrated in FIG. 2 has a video compression function that performs video compression processing using the captured video acquired by the imaging unit 110 as an input. The compressed captured video is provided to the transmission unit 190. Various methods may be used for video compression by the video compression unit 170, and for example, a moving image encoding method such as MPEG-1 may be used. For example, the video compression unit 170 may perform video compression processing that generates a high-definition video with a relatively low compression rate for the entire image of each frame of the captured video.

(Transmitter)
The transmission unit 190 is connected to the communication network 30 described with reference to FIG. 1 and performs communication processing with other devices. For example, the transmission unit 190 transmits the compressed captured video provided from the video compression unit 170 and the importance level information provided from the importance level identification unit 150 to the video storage device 20 via the communication network 30.

<1-4. Configuration of video storage device>
The configuration example of the monitoring camera 10 according to the first embodiment of the present invention has been described above. Next, a configuration example of the video storage device 20 according to the present embodiment will be described. FIG. 5 is an explanatory diagram showing a configuration example of the video storage device 20 according to the first embodiment of the present invention. As shown in FIG. 5, the video storage device 20 is an information processing device including a reception unit 210, a video recording unit 230, a recording status determination unit 250, a recorded video update unit 270, and a video compression unit 290.

(Receiver)
The receiving unit 210 is connected to the communication network 30 described with reference to FIG. 1 and performs communication processing with other devices. For example, the receiving unit 210 receives captured video and importance information from the monitoring camera 10 via the communication network 30. Here, the captured video and the importance information received by the receiving unit 210 may be associated with each frame, and the receiving unit 210 captures the captured video and the importance information in units of one block in which a predetermined number of frames are collected. May be received. The captured video and importance information received by the receiving unit 210 are provided to the video recording unit 230 in a state of being associated with each frame.

(Video recording part)
The video recording unit 230 is a recording for recording (storing) various programs and programs for executing processing described below by the recording status determination unit 250, the recorded video update unit 270, and the video compression unit 290, which will be described later. Device. For example, the video recording unit 230 records video recording information in which importance information is associated with a captured video.

  The video recording unit 230 may record the video recording information in which the importance level information received from the monitoring camera 10 by the receiving unit 210 is associated with the captured video as the first video recording information. The video recording unit 230 also stores second video recording information in which importance information is associated with a captured video compressed by a video compression unit 290 described later, based on an update process performed by a recorded video update unit 270 described later. It may be recorded instead of the first video recording information.

  Note that the video recording unit 230 is realized as an HDD (Hard Disc Drive), for example. Of course, various recording media such as a solid-state memory such as a flash memory, a memory card with a built-in fixed memory, an optical disc, a magneto-optical disc, and a hologram memory are conceivable. The video recording unit 230 records and reproduces according to the recording medium employed. Any configuration can be used.

(Recording status judgment unit)
The recording status determination unit 250 has a recording status determination function that determines whether or not it is necessary to recompress the captured video recorded in the video recording unit 230. For example, the recording status determination unit 250 determines whether or not the recompression needs to be performed by determining whether or not the video recording status of the video recording unit 230 satisfies a predetermined condition, and the result of the determination To the recorded video update unit 270 described later. For example, the predetermined condition may include a condition related to a recorded data amount of the video recording unit 230 and a condition related to a usage rate of the video recording unit 230 (ratio of recorded data amount to recordable data amount). The predetermined condition may include a condition related to the number of frames or the number of blocks of the video recording information recorded by the video recording unit 230. Further, the predetermined condition includes a condition relating to a time elapsed since the video recording unit 230 started recording, and the number of blocks recorded after the video data of the block having the video recording unit 230 is recorded (hereinafter, the number of elapsed blocks). May also be included. According to this configuration, the recorded video update unit 270 can perform update processing according to the video recording status of the video recording unit 230.

  The recording status determination unit 250 may determine whether the video recording status of the video recording unit 230 satisfies the plurality of predetermined conditions for a plurality of predetermined conditions. The number of predetermined conditions used for determination by the recording status determination unit 250 may be, for example, the number of stages of video compression performed by the video compression unit 290 described later. In such a case, video compression by the video compression unit 290 is performed based on a predetermined condition determined to be satisfied by the recording status determination unit 250. In the following, a plurality of conditions relating to the number of blocks (recording block number) of video recording information recorded by the video recording unit 230 (for example, the first condition is that the number of elapsed blocks is 4 or more, An example in which the number of elapsed blocks is 10 or more is used as the condition.

  The recording status determination unit 250 may determine whether or not a predetermined condition is satisfied for each block of the video recording information recorded by the video recording unit 230.

(Recorded video update section)
The recorded video update unit 270 controls the video compression unit 290 and the video recording unit 230 based on the determination of the recording status determination unit 250 and updates the video recording information recorded in the video recording unit 230. Have

  For example, when the recording status determination unit 250 determines that the video recording status of the video recording unit 230 satisfies a predetermined condition, the recorded video update unit 270 controls the video compression unit 290 to perform a compression rate based on the importance level information. Perform video compression. Further, the recorded video update unit 270 causes the video recording unit 230 to record the second video recording information based on the video compression by the video compression unit 290 instead of the first video recording information.

  The second video recording information according to the present embodiment includes importance level information. For example, the recorded video update unit 270 may cause the video recording unit 230 to record information associating the importance level information with the captured video compressed by the video compression unit 290 as the second video recording information. According to this configuration, the video compression unit 290 described later can further perform video compression processing on the captured video included in the second video recording information based on the importance level information included in the second video recording information. It becomes possible.

(Video compression part)
The video compression unit 290 has a video compression function that is controlled by the recorded video update unit 270 and performs video compression (recompression) processing of the captured video recorded in the video recording unit 230. In this embodiment, since the captured video recorded in the video recording unit 230 has already been subjected to encoding processing for compression, the video compression unit 290 decodes (decodes) the compressed captured video. The compression process may be performed again.

  For example, when the recording state determination unit 250 determines that the recording state of the recording unit 230 satisfies a predetermined condition, the video compression unit 290 is controlled by the recording video update unit 270 to obtain the first video recording information. Video compression is performed at a compression rate based on importance information for each area of the captured video included.

  For example, the video compression unit 290 performs video compression such that a region having a higher importance is compressed at a lower compression rate in the importance information. According to such a configuration, it is possible to reduce the data amount of the captured video that is accumulated while recording an important region with high definition at a low compression rate.

  In addition, the video compression unit 290 is controlled by the recorded video update unit 270 to compress the captured video recorded in the video recording unit 230 based on the determination by the recording status determination unit 250. For example, when the recording status determination unit 250 determines a plurality of predetermined conditions, the video compression unit 290 may perform video compression based on the determination of the predetermined condition with the same number of steps as the predetermined condition. . For example, the video compression unit 290 performs the first-stage video compression for a block that satisfies a predetermined condition corresponding to the first-stage video compression, and supports the first-stage video compression for the block. If the predetermined condition is satisfied, the second stage video compression may be further performed. In this case, the video compression unit 290 may output the video so that the amount of data to be output (the amount of data of the compressed captured video) is smaller in the second stage video compression than in the first stage video compression. Compression may be performed. For example, in the first stage of video compression, areas of importance “medium” or higher (areas of importance “medium” and importance “high”) are compressed at a low compression rate, and areas of importance “low” are compressed. Video compression may be performed so that the video is compressed at a high compression rate. In the second stage of video compression, the area of high importance is compressed with a low compression rate, and the area of importance "medium" or less (area of importance "medium" and area of importance "low") Video compression may be performed so that the video is compressed at a high compression rate.

  According to this configuration, for example, the video recorded in the video recording unit 230 can be recompressed so that the data amount corresponds to the recording status of the video recording unit 230, and the video recording unit 230 records the data. It is possible to more effectively utilize the amount of data possible.

<1-5. Example of operation>
The configuration of the video storage system according to the first embodiment of the present invention has been described above. Subsequently, an operation example of the video storage system according to the present embodiment will be described with reference to FIGS. In the following, the operation of the surveillance camera 10 will be described first with reference to FIG. 6, and then the operation of the video storage device 20 will be described with reference to FIG. Furthermore, a specific example of processing related to video recompression by the video storage device 20 will be described with reference to FIG.

(Operation of surveillance camera)
FIG. 6 is an explanatory diagram illustrating an operation example of the monitoring camera 10 according to the present embodiment. First, the surveillance camera 10 acquires a captured video based on the imaging of the imaging unit 110 (S102). Subsequently, the detection unit 132 of the video analysis unit 130 detects a monitoring target event from the acquired captured video (S104). Further, the situation recognition unit 134 of the video analysis unit 130 recognizes (analyzes) the situation related to the detected monitoring target event (S106).

  Subsequently, the importance level identifying unit 150 identifies the importance level for each area of the captured video based on the analysis result by the video analysis unit 130 and generates importance level information (S108). Further, the video compression unit 170 compresses the captured video (S110), and the transmission unit 190 transmits the compressed captured video and importance information to the video storage device 20 (S112). The processes in steps S102 to S112 are repeated (NO in S114) until the photographing is ended by a user instruction or the like (YES in S114).

(Operation of video storage device)
The operation example of the monitoring camera 10 has been described above. Next, an operation example of the video storage device 20 will be described. FIG. 7 is an explanatory diagram illustrating an operation example of the video storage device 20 according to the present embodiment. In FIG. 7, the meanings of the variables and constants are as follows.
n: Current block number for receiving / recording.
Dn: Video recording information of the nth block.
M: Maximum value of the compression stage.
m: compression stage. The larger the m, the smaller the amount of data after compression.
Tm: The number of elapsed blocks where the m-th stage compression process is started.
k: Block number to be compressed.

  First, the current block number n is set to 1 (S202). If reception unit 210 has not received data (NO in S204), the process ends. If data has been received (YES in S204), the receiving unit 210 obtains one block of captured video and importance information from the monitoring camera 10 (S206).

  The captured video and importance information for one block acquired by the receiving unit 210 are recorded in the video recording unit 230 as video recording information Dn of the nth block (S208). Subsequently, a video recompression loop process (S210 to S220) by the video recording unit 230, the recording status determination unit 250, the recorded video update unit 270, and the video compression unit 290 is started (S210). As shown in FIG. 7, the recompression loop process is performed the same number of times as the value that the compression stage m can take (that is, the same number of times as the maximum compression value M).

  In the recompression loop process, first, the recording state determination unit 250 determines whether or not the current block number n is larger than the number of elapsed blocks Tm at which the m-th stage compression process is started (S212). If the current block number n is not larger than the elapsed block number Tm at which the m-th stage compression process is started (NO in S212), the recompression process for the current compression stage m is not performed, and the process is as follows. Transition to the loop.

  On the other hand, when the current block number n is larger than the elapsed block number Tm at which the m-th stage compression process is started (YES in S212), the block number k to be compressed is determined by the calculation of k = n−Tm. (S214). Subsequently, the video compression unit 290 recompresses the video included in the video recording information Dk to be compressed based on the m-th stage compression condition based on the importance level information recorded in the video recording unit 230 (S216). . Further, the recorded video update unit 270 replaces (updates) the video included in the video recording information Dk with the recompressed video obtained by the recompression (S218), and the process proceeds to the next loop.

  When the above-described recompression process is repeated after the same number of times as the maximum value M at the compression stage (S220), the current block number n is incremented (S222), and the process returns to step S204.

(Concrete example)
The operation flow of the monitoring camera 10 and the operation flow of the video storage device 20 according to the present embodiment have been described above. Next, a specific example of video recompression processing by the video storage device 20 will be described with reference to FIG. FIG. 8 is an explanatory diagram for describing a specific example of video recompression processing by the video storage device 20 according to the present embodiment.

  In the specific example shown in FIG. 8, the maximum value M = 2 of the compression stage is set, the number of elapsed blocks T1 = 4 at which the first stage compression process is started, and the number of elapsed blocks T2 = at which the second stage compression process is started. 10 is assumed. In this specific example, the degree of importance is three levels (high, medium, and low), and the captured video received by the video storage device 20 is a video in which the entire image (full screen) is compressed at a low compression rate. And Further, in the first stage compression process, only the area of medium importance or higher is compressed with a low compression ratio, and the other areas are compressed with a high compression ratio. In the second-stage compression process, only the high importance area is compressed with a low compression ratio, and the other areas are compressed with a high compression ratio.

  First, when a time corresponding to the number of blocks T1 has elapsed since the start of recording and the current number of blocks is n = T1 (= 4), as shown in FIG. Video recording information D1 to D4 including video compressed at a rate is recorded.

  Subsequently, when the current number of blocks is n = T1 + 1 (= 5), video recording information D1 to D5 is recorded in the video recording unit 230 as shown in FIG. Of the video recording information D1 to D5 recorded in the video recording unit 230, the video recording information D1 is obtained by the first-stage compression processing (processing in which m = 1 in steps S214 to S218 described with reference to FIG. 7). Only the area of medium importance or higher is updated with the recompressed video compressed at the low compression rate.

  Similarly, until the current number of blocks reaches n = T2 (= 10), each time the current number of blocks advances, the video recording information recorded in the video recording unit 230 is one block at a time. Updated with the recompressed video recompressed by the compression process. As a result, when the current number of blocks is n = T2, as shown in FIG. 8, the video recording unit 230 includes video recording information including recompressed video in which only the area of medium importance or higher is compressed at a low compression rate. D1 to D6 and video recording information D7 to D10 including a video whose screen is compressed at a low compression rate are recorded.

  Subsequently, when the current number of blocks is n = T2 + 1 (= 11), as shown in FIG. 8, video recording information D1 to D11 is recorded in the video recording unit 230. Among the video recording information D1 to D11 recorded in the video recording unit 230, the video recording information D1 is obtained by the second-stage compression processing (processing in which m = 2 in steps S214 to S218 described with reference to FIG. 7). Only the high importance area is updated with the recompressed video compressed at the low compression rate.

<1-6. Effect>
The configuration example and the operation example of the video storage system according to the first embodiment of the present invention have been described above in detail. According to the present embodiment, it is possible to reduce the amount of stored video data while recording a high-definition important area with a low compression rate.

<1-7. Modification>
The first embodiment of the present invention has been described above. Hereinafter, some modifications of the first embodiment of the present invention will be described. In addition, each modification demonstrated below may be applied to 1st embodiment of this invention independently, and may be applied to 1st embodiment of this invention in combination. Each modification may be applied instead of the configuration described in the first embodiment of the present invention, or may be applied in addition to the configuration described in the first embodiment of the present invention. Also good.

(First modification)
In the above description, the importance information specified by the monitoring camera 10 has been recorded without being updated in the video storage device. However, the present embodiment is not limited to such an example. For example, the importance level information specified by the monitoring camera 10 may be updated in the video storage device. Hereinafter, as a first modification, a configuration example of a video storage device in which the video storage device updates importance information will be described.

  FIG. 9 is an explanatory diagram illustrating a configuration example of a video storage device according to the present modification. The video storage device 40 illustrated in FIG. 9 is an information processing apparatus including a reception unit 410, a video recording unit 430, a recording status determination unit 250, a recorded video update unit 270, and a video compression unit 290. Among the above, the configurations of the recording status determination unit 250, the recorded video update unit 270, and the video compression unit 290 are the same as the recording status determination unit 250, the recorded video update unit 270, and the video compression unit 290 described with reference to FIG. Since they are substantially the same as those in FIG.

  The receiving unit 410 receives the captured video and the importance level information in the same manner as the receiving unit 210 described with reference to FIG. The receiving unit 410 according to this modification provides the received captured video and importance information to the video recording unit 430 and further to the importance level updating unit 420.

  The importance level update unit 420 updates the importance level information recorded in the video recording unit 430 based on the importance level information received by the reception unit 410 and the importance level information recorded in the video recording unit 430. .

  For example, the importance level update unit 420 stores the importance level information recorded in the video recording unit 430 based on the importance level information corresponding to the first time, and corresponding to the second time before the first time. It may be updated. Similar to the video storage device 20 described with reference to FIG. 5, the video storage device 40 includes the video recording unit 430 that records the importance level information. It is possible to update the importance level information corresponding to the second time before the first time.

  Also, the importance level update unit 420 receives the first time after the first time, which is received by the reception unit 410 or recorded in the video recording unit 430, based on the importance level information corresponding to the first time. The importance level information corresponding to the third time may be updated. Note that the importance level update unit 420 may perform the update based on the importance level information corresponding to the first time received by the reception unit 410, or periodically access the video recording unit 430. Thus, the importance level information corresponding to the first time may be acquired and the above update may be performed.

  For example, the importance level update unit 420 may include either or both of the second time and the third time for an area having an importance level equal to or higher than a predetermined value in the importance level information corresponding to the first time. The importance level information corresponding to may be updated. According to such a configuration, for example, even in frames before and after the time when the importance of the area becomes high, it is possible to set the importance of the area high, and it is possible to set the importance with higher accuracy. It becomes.

  For example, when a fire occurs, the area corresponding to the location of the fire is detected as an area that should be assigned a high importance after the fire occurs. Therefore, it is desirable to record with high definition at a low compression rate. According to the above configuration, even in such a case, it is possible to identify the area corresponding to the fire occurrence point as a highly important area even in the frame before the fire occurrence, and the area with a low compression rate. High-definition recording is possible.

  In addition, the importance level update unit 420 includes, in the importance level information corresponding to the first time, for the area based on the monitored event included in the area having an importance level equal to or higher than a predetermined value, The importance level information corresponding to both or one of the third times may be updated. The region based on the monitoring target event is, for example, the monitoring target in the image at each time obtained by the detection unit 132 included in the monitoring camera 10 described with reference to FIG. 2 tracking the monitoring target event. It may be an event area.

  According to such a configuration, for example, when an abnormal behavior of a person is detected at the first time, not only the importance information corresponding to the first time but also the importance corresponding to the times before and after the first time Also in the degree information, it is possible to assign a high degree of importance to the person's area.

  Similar to the video recording unit 230 described with reference to FIG. 5, the video recording unit 430 includes various programs such as a program for executing each process, video recording information in which importance level information and captured video are associated, and the like. It is a recording device that records (stores) various data. The importance level information recorded by the video recording unit 430 according to this modification is updated by the importance level update unit 420 as described above.

(Second modification)
In the above description, an example in which the video compression unit 170 of the surveillance camera 10 performs the video compression processing for compressing the entire image at a low compression rate has been described, but the present embodiment is not limited to this example. For example, the video compression unit 170 may perform video compression based on importance information, like the video compression unit 290 included in the video storage device 20. Further, for example, when the communication network 30 connecting the monitoring camera 10 and the video storage device 20 has a wide communication band and can transmit uncompressed captured video, the monitoring camera 10 does not perform video compression and performs no compression. The captured video may be transmitted to the video storage device 20.

(Third modification)
In the above description, the example in which the connection between the monitoring camera 10 and the video storage device 20 is performed via the network (communication network 30) has been described. However, the present embodiment is not limited to such an example. For example, the monitoring camera 10 and the video storage device 20 may be directly connected by a USB (Universal Serial Bus) connection or the like. Further, the monitoring camera and the video storage device may be integrated. In such a case, the transmission / reception process of the captured video and the importance information is performed in the apparatus without using a network or a USB cable.

(Fourth modification)
The configuration of the monitoring camera 10 and the video storage device 20 included in the video storage system 1 described above is an example, and another device may have the function of the one device described above. For example, the example in which the monitoring camera 10 is provided with the function of the video analysis unit 130 and the function of the importance level specifying unit 150 has been described above, but the present embodiment is not limited to such an example. For example, the video storage device has functions corresponding to the video analysis unit 130 and the importance level specifying unit 150, and the video storage device that has received the captured video from the surveillance camera performs steps S104 to S108 described with reference to FIG. Processing or the like may be performed.

<< 2. Second embodiment >>
<2-1. Overview>
Heretofore, the first embodiment and modifications of the present invention have been described. In the first embodiment described above, the video recording information recorded by the video recording unit of the video storage device includes the captured video and the importance information in association with each other. On the other hand, in the following, as a second embodiment of the present invention, it is necessary to re-compress the captured video recorded in the video recording unit by the recording status determination unit, in which only the captured video is included in the video recording information. An example will be described in which importance level information is dynamically specified when it is determined that there is.

  Note that the second embodiment described below partially has the same configuration as the first embodiment described above, and therefore will be described while being omitted as appropriate. In the following, first, the configuration of the surveillance camera 50 according to the present embodiment will be described with reference to FIG. 10, and then the configuration of the video storage device 60 according to the present embodiment will be described with reference to FIG. Note that the monitoring camera 50 and the video storage device 60 according to the present embodiment may be connected via the communication network 30 in the same manner as the monitoring cameras 10A and 10B and the video storage device 20 described with reference to FIG. Good.

<2-2. Configuration of surveillance camera>
FIG. 10 is an explanatory diagram illustrating a configuration example of the monitoring camera 50 according to the present embodiment. As illustrated in FIG. 10, the monitoring camera 50 is an information processing apparatus including an imaging unit 510, a video compression unit 570, and a transmission unit 590.

(Imaging part)
The imaging unit 510 is a camera module that acquires a captured video in the same manner as the imaging unit 110 described in the first embodiment. The captured video acquired by the imaging unit 510 is provided to the video compression unit 570.

(Video compression part)
Similar to the video compression unit 170 described in the first embodiment, the video compression unit 570 illustrated in FIG. 10 performs video compression processing with the captured video acquired by the imaging unit 510 as an input. The compressed captured video is provided to the transmission unit 590.

(Transmitter)
Similar to the transmission unit 190 described in the first embodiment, the transmission unit 590 illustrated in FIG. 10 performs communication processing with other devices. For example, the transmission unit 590 transmits the compressed captured video provided from the video compression unit 570 to the video storage device 60 described later.

<2-3. Configuration of video storage device>
The configuration example of the monitoring camera 50 according to the second embodiment of the present invention has been described above. Next, a configuration example of the video storage device 60 according to the present embodiment will be described. FIG. 11 is an explanatory diagram showing a configuration example of the video storage device 60 according to the second embodiment of the present invention. As shown in FIG. 11, the video storage device 60 includes a receiving unit 610, a video recording unit 630, a recording status determination unit 650, a video analysis unit 660, a recorded video update unit 670, an importance level specifying unit 680, and a video compression unit 690. Is an information processing apparatus.

(Receiver)
The receiving unit 610 performs communication processing with other devices in the same manner as the receiving unit 210 described in the first embodiment. For example, the receiving unit 610 receives a captured video from the monitoring camera 50. In addition, the receiving unit 610 may receive the captured video in units of one block in which a predetermined number of frames are collected. The captured video received by the receiving unit 610 is provided to the video recording unit 630.

(Video recording part)
The video recording unit 630 includes a recording status determination unit 650, a video analysis unit 660, a recorded video update unit 670, an importance level specifying unit 680, and a video compression unit 690 that execute programs described below and various programs. It is a recording device that records (stores) various data. For example, the video recording unit 630 records a captured video as video recording information.

  The video recording unit 630 may record the captured video received from the monitoring camera 10 by the receiving unit 610 as the first video recording information. Also, the video recording unit 230 replaces the second video recording information based on the captured video compressed by the video compression unit 690 described later with the first video recording information based on the update processing by the recorded video update unit 670 described later. May be recorded.

  Note that the video recording unit 630 is implemented by a recording medium such as an HDD, for example, in the same manner as the video recording unit 230 described in the first embodiment.

(Recording status judgment unit)
The recording status determination unit 650 determines whether or not it is necessary to recompress the captured video recorded in the video recording unit 630, similarly to the recording status determination unit 250 described in the first embodiment. Has a judgment function. For example, the recording status determination unit 650 determines whether or not recompression needs to be performed by determining whether or not the video recording status of the video recording unit 630 satisfies a predetermined condition, and the result of the determination To the video analysis unit 660 and the recorded video update unit 670 described later. The predetermined condition used by the recording status determination unit 650 according to the present embodiment may be the same as the predetermined condition used by the recording status determination unit 250 described in the first embodiment.

(Video Analysis Department)
The video analysis unit 660 has a video analysis function for analyzing the captured video based on the determination by the recording status determination unit 650. For example, the video analysis unit 660, when the recording status determination unit 650 determines that the video recording status of the video recording unit 630 satisfies a predetermined condition, the monitoring target to be monitored from the captured video recorded in the video recording unit 630 Detect events and analyze the status of monitored events.

  The video analysis unit 660 according to the present embodiment includes a detection unit 662 and a situation recognition unit 664 as shown in FIG. The functions of the detection unit 662 and the situation recognition unit 664 are substantially the same as the functions of the detection unit 132 and the situation recognition unit 134 described in the first embodiment, and thus description thereof is omitted here.

(Recorded video update section)
The recorded video update unit 670 controls the video compression unit 690 and the video recording unit 630 based on the determination of the recording status determination unit 650 and updates the video recording information recorded in the video recording unit 630. Have

  For example, when the recording status determination unit 650 determines that the video recording status of the video recording unit 630 satisfies a predetermined condition, the recorded video update unit 670 controls the video compression unit 690 so that the importance level specifying unit 680 described later Video compression is performed at a compression rate based on the identified importance information. Further, the recorded video update unit 670 causes the video recording unit 630 to record the second video recording information based on the video compression by the video compression unit 690 instead of the first video recording information. In the present embodiment, the second video recording information may be a captured video recompressed by the video compression unit 690.

(Importance level identification part)
The importance level specifying unit 680 has an importance level specifying function for generating importance level information by specifying the importance level for each region of the captured video based on the analysis result by the video analysis unit 660. The importance level specifying unit 680 according to the present embodiment has substantially the same function as the importance level specifying unit 150 described in the first embodiment, except that the generated importance level information is provided to the video compression unit 690. Therefore, the description here is omitted.

(Video compression part)
The video compression unit 690 has a video compression function that is controlled by the recorded video update unit 670 and performs video compression (recompression) processing of the captured video recorded in the video recording unit 630. The video compression unit 690 is controlled by the recorded video update unit 670 to compress the video at a compression rate based on the importance level information specified by the importance level specification unit 680 for each area of the captured video included in the first video recording information. I do. The video compression processing at the compression rate based on the importance level information performed by the video compression unit 690 is substantially the same as the video compression processing performed by the video compression unit 290 described in the first embodiment, and therefore will be described here. Is omitted.

<2-4. Example of operation>
The configuration of the video storage system according to the second embodiment of the present invention has been described above. Subsequently, an operation example of the video storage system according to the present embodiment will be described with reference to FIGS. In the following, first, the operation of the surveillance camera 50 will be described with reference to FIG. 12, and then the operation of the video storage device 60 will be described with reference to FIG.

(Operation of surveillance camera)
FIG. 12 is an explanatory diagram illustrating an operation example of the monitoring camera 50 according to the present embodiment. First, the surveillance camera 50 acquires a captured image based on the image captured by the image capturing unit 510 (S302). Subsequently, the video compression unit 570 compresses the captured video (S304), and the transmission unit 590 transmits the compressed captured video to the video storage device 60 (S306). The processes in steps S302 to S306 are repeated (NO in S308) until shooting is terminated (YES in S308) due to a user instruction or the like.

(Operation flow of video storage device)
The operation example of the monitoring camera 50 has been described above. Subsequently, an operation example of the video storage device 60 will be described. FIG. 13 is an explanatory diagram illustrating an operation example of the video storage device 60 according to the present embodiment. Note that the variables and constants in FIG. 13 are the same as the variables and constants described with reference to FIG.

  First, the current block number n is set to 1 (S402). If reception unit 610 has not received data (NO in S404), the process ends. If the receiving unit 610 has received data (YES in S404), the captured image for one block is acquired from the monitoring camera 50 (S406).

  The captured video for one block acquired by the receiving unit 610 is recorded in the video recording unit 630 as video recording information Dn of the nth block (S408). Subsequently, a video recompression loop process (S410 to S426) is started (S410). As shown in FIG. 12, the recompression loop process is performed the same number of times as the value that the compression stage m can take (that is, the same number of times as the maximum compression value M).

  In the recompression loop process, first, the recording state determination unit 650 determines whether or not the current block number n is larger than the elapsed block number Tm at which the m-th stage compression process is started (S412). If the current block number n is not larger than the elapsed block number Tm at which the m-th stage compression process is started (NO in S412), the recompression process for the current compression stage m is not performed, and the process Transition to the loop.

  On the other hand, when the current block number n is larger than the elapsed block number Tm at which the m-th stage compression process is started (YES in S412), the block number k to be compressed is determined by the calculation of k = n−Tm. (S414).

  Subsequently, the detection unit 662 of the video analysis unit 660 detects a monitoring target event from the captured video recorded in the video recording unit 630 (S416). Further, the situation recognition unit 664 of the video analysis unit 660 recognizes (analyzes) the situation related to the detected monitoring target event (S418). Subsequently, the importance level identifying unit 680 identifies the importance level for each area of the captured video based on the analysis result by the video analysis unit 660 and generates importance level information (S420).

  Note that the processing in steps S416 to S420 described above may be performed on the captured video included in the video recording information Dk of the block to be compressed, and the video recording information of the blocks before and after the video recording information Dk. It may be performed on the captured video included.

  Subsequently, the video compression unit 690 recompresses the video included in the video recording information Dk that is the compression target based on the m-th stage compression condition based on the importance level information generated by the importance level specifying unit 680 (S422). ). Further, the recorded video update unit 670 replaces (updates) the video included in the video recording information Dk with the recompressed video obtained by the recompression (S424), and the processing shifts to the next loop.

  When the above-described recompression process is repeated after the same number of times as the maximum value M at the compression stage (S426), the current block number n is incremented (S428), and the process returns to step S404.

<2-5. Effect>
The configuration example and the operation example of the video storage system according to the second embodiment of the present invention have been described above in detail. According to the present embodiment, as in the first embodiment, it is possible to reduce the amount of stored video data while recording a high-definition region with a low compression rate and high definition.

  In addition, according to the present embodiment, the analysis processing of the recompressed captured video and the importance level specifying processing are performed according to the determination related to the video recording status of the video recording unit. Compared to the case where the processing is performed, the processing amount of the entire system can be reduced. Furthermore, since the importance level information need not be recorded in the video recording unit, the amount of data recorded in the video recording unit can be reduced.

<2-6. Supplement>
In the above, the example in which the importance level information is not recorded in the video recording unit 630 has been described, but the present embodiment is not limited to such an example. For example, the importance information may be recorded in the video recording unit 630 for the frames for which the importance information is once generated by the importance specifying unit 680. According to such a configuration, when the frame is recompressed again, it is possible to reduce the processing costs related to the video analysis process and the importance level specifying process.

  Moreover, it is also possible to apply each modification demonstrated in 1st embodiment to 2nd embodiment.

<< 3. Hardware configuration >>
In the above, each embodiment and each modification of this invention were demonstrated. Information processing such as the above-described monitoring target event detection processing, situation recognition processing, importance level identification processing, video compression processing, video recording information update processing, etc. is performed by software and information processing devices (monitoring cameras 10 and 50 and video storage device 20). , 40, 60) in cooperation with hardware. Hereinafter, a hardware configuration example of the information processing device 1000 will be described as a hardware configuration example of the monitoring cameras 10 and 50 and the video storage devices 20, 40, and 60 which are information processing devices according to the present embodiment.

  FIG. 14 is an explanatory diagram illustrating a hardware configuration example of the information processing apparatus 1000 according to the present embodiment. As illustrated in FIG. 14, the information processing apparatus 1000 includes a CPU (Central Processing Unit) 1001, a ROM (Read Only Memory) 1002, a RAM (Random Access Memory) 1003, an input device 1004, and an output device 1005. A storage apparatus 1006 and a communication apparatus 1007.

  The CPU 1001 functions as an arithmetic processing unit and a control unit, and controls the overall operation in the information processing apparatus 1000 according to various programs. Further, the CPU 1001 may be a microprocessor. The ROM 1002 stores programs used by the CPU 1001 and calculation parameters. The RAM 1003 temporarily stores programs used in the execution of the CPU 1001, parameters that change as appropriate during the execution, and the like. These are connected to each other by a host bus including a CPU bus. Mainly, the functions of the video analysis unit, the importance level specifying unit, the video compression unit, the recording state determination unit, the recorded video update unit, and the importance level update unit are realized by the cooperation of the CPU 1001, the ROM 1002, the RAM 1003, and the software.

  The input device 1004 includes input means for a user to input information, such as a mouse, keyboard, touch panel, button, microphone, switch, and lever, and an input control circuit that generates an input signal based on the input by the user and outputs the input signal to the CPU 1001 Etc. A user of the information processing apparatus 1000 can input various data and instruct a processing operation to the information processing apparatus 1000 by operating the input device 1004.

  The output device 1005 includes a display device such as a liquid crystal display (LCD) device, an OLED device, and a lamp. Furthermore, the output device 1005 includes an audio output device such as a speaker and headphones. For example, the display device displays a captured image or a generated image. On the other hand, the audio output device converts audio data or the like into audio and outputs it.

  The storage device 1006 is a device for storing data. The storage device 1006 may include a storage medium, a recording device that records data on the storage medium, a reading device that reads data from the storage medium, a deletion device that deletes data recorded on the storage medium, and the like. The storage device 1006 stores programs executed by the CPU 1001 and various data. The storage device 1006 corresponds to the video recording units 230, 430, and 630.

  The communication device 1007 is a communication interface configured with, for example, a communication device for connecting to a communication network. Further, the communication device 1007 may include a wireless LAN (Local Area Network) compatible communication device, an LTE (Long Term Evolution) compatible communication device, a wire communication device that performs wired communication, or a Bluetooth (registered trademark) communication device. The communication device 1007 corresponds to the transmission units 190 and 590 and the reception units 210, 410, and 610.

<< 4. Conclusion >>
As described above, according to the embodiment of the present invention, it is possible to reduce the data amount of the accumulated video while recording the important area with high definition.

  The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to such examples. It is obvious that a person having ordinary knowledge in the technical field to which the present invention pertains can come up with various changes or modifications within the scope of the technical idea described in the claims. Of course, it is understood that these also belong to the technical scope of the present invention.

  For example, each step in the above embodiment does not necessarily have to be processed in time series in the order described as a flowchart. For example, each step in the processing of the above embodiment may be processed in an order different from the order described as the flowchart diagram or may be processed in parallel.

  In addition, the monitoring cameras 10 and 50 and the video storage devices 20, 40, and 60 described above are included in hardware such as the CPU 1001, the ROM 1002, and the RAM 1003 built in the monitoring cameras 10 and 50 and the video storage devices 20, 40, and 60 described above. It is also possible to create a computer program for exercising these functions. A storage medium storing the computer program is also provided.

DESCRIPTION OF SYMBOLS 1 Image | video storage system 10,50 Surveillance camera 20,40,60 Image | video storage apparatus 30 Communication network 110,510 Image pick-up part 130,530 Image | video analysis part 132 Detection part 134 Situation recognition part 150 Importance specification part 170,570 Video compression part 190 , 590 Transmission unit 210, 410, 610 Reception unit 230, 430, 630 Video recording unit 250, 650 Recording status determination unit 270, 670 Recorded video update unit 290, 690 Video compression unit 420 Importance update unit 660 Video analysis unit 662 Detection Part 664 Situation Recognition Part 680 Importance Level Identification Part

Claims (9)

A video analysis unit that detects a monitoring target event to be monitored from the captured video and analyzes a situation related to the monitoring target event;
Based on the analysis result by the video analysis unit, an importance level identifying unit for identifying the importance level for each area of the captured video and generating the importance level information,
A video recording unit that records first video recording information in which the importance information and the captured video are associated;
When the video recording status of the video recording unit satisfies a predetermined condition, a video compression unit that performs video compression at a compression rate based on the importance information for each region of the captured video included in the first video recording information When,
A recording video update unit that records the second video recording information based on the video compression in the video recording unit instead of the first video recording information;
An importance update unit that updates the importance information that is recorded in the video recording unit and that corresponds to the second time before the first time, based on the importance information corresponding to the first time; ,
A video storage system.   The video storage system according to claim 1, wherein the video compression unit performs the video compression such that a region having a higher importance is compressed at a lower compression rate in the importance information.   The video storage system according to claim 1, further comprising a recording status determination unit that determines whether or not the video recording status satisfies the predetermined condition.   The video storage system according to claim 3, wherein the second video recording information includes the importance information.   The recording status determination unit performs the determination for a plurality of the predetermined conditions, and the video compression unit compresses the captured video recorded in the video recording unit based on the determination by the recording status determination unit. The video storage system according to claim 4. The importance level update unit updates the importance level information corresponding to the second time for an area having an importance level equal to or higher than a predetermined value in the importance level information corresponding to the first time. 2. The video storage system according to 1. The video analysis unit tracks the monitoring target event, and the importance level update unit includes the monitoring target included in a region having an importance level equal to or higher than a predetermined value in the importance level information corresponding to the first time. the region based on the event, updates the importance information corresponding to the second time, the video storage system according to claim 1. Importance that generates importance information by identifying importance for each area of the captured video based on the analysis result obtained by analyzing the situation related to the monitored event that is detected from the captured video A specific part,
A video recording unit that records first video recording information in which the importance information and the captured video are associated;
When the video recording status of the video recording unit satisfies a predetermined condition, a video compression unit that performs video compression at a compression rate based on the importance information for each region of the captured video included in the first video recording information When,
A recording video update unit that records the second video recording information based on the video compression in the video recording unit instead of the first video recording information;
An importance update unit that updates the importance information that is recorded in the video recording unit and that corresponds to the second time before the first time, based on the importance information corresponding to the first time; ,
A video storage device comprising: On the computer,
Importance that generates importance information by identifying importance for each area of the captured video based on the analysis result obtained by analyzing the situation related to the monitored event that is detected from the captured video Specific functions,
When the video recording status of the recording apparatus that records the first video recording information in which the importance information and the captured video are associated with each other satisfies a predetermined condition, the captured video included in the first video recording information A video compression function for performing video compression at a compression rate based on the importance information for each of the areas;
A recorded video update function for causing the recording device to record the second video recording information based on the video compression instead of the first video recording information;
Based on the importance information corresponding to the first time, the importance update function that is recorded in the recording device and updates the importance information corresponding to the second time before the first time;
A program to realize

Images