JP7753761B2 - Surveillance video processing device, program, surveillance video processing system, and surveillance video processing method - Google Patents

Description

The present invention relates to a surveillance video processing device, a program, a surveillance video processing system, and a surveillance video processing method.

In recent years, various mechanisms for detecting abnormalities on roads have been studied to ensure road traffic safety. Generally, road monitoring uses various sensors to detect abnormalities, but due to the significant social impact of accidents and road surface abnormalities, visual inspections are also carried out by inspectors. Visual monitoring uses a system in which multiple imaging devices capture images of the road, transmit the captured images over a network, and display them on a remotely installed monitor. In road monitoring, images from multiple locations are often monitored using a limited number of monitors, so a method is used in which multiple images are displayed on the same screen.

For example, Patent Document 1 discloses a method for monitoring multiple images on the same monitor by switching between images captured by multiple imaging devices. Alternatively, a method is disclosed for simultaneously displaying multiple images on a single screen by reducing the display size of each of the multiple images.

Japanese Patent Application Laid-Open No. 2006-345489

However, when switching between multiple videos to display on the screen, there are times when each video is not displayed, which impairs the real-time nature of monitoring and makes it take time to identify abnormalities. Furthermore, when reducing the display size of each video and displaying it on the same screen, the display size of each video becomes small, making it difficult to check the situation in detail and making it easy to overlook abnormalities.

The present invention has been made in consideration of the above problems, and its object is to provide a new and improved surveillance video processing device, program, surveillance video processing system, and surveillance video processing method that facilitates visual monitoring of multiple surveillance videos.

In order to solve the above problem, according to one aspect of the present invention, there is provided a surveillance video processing device comprising: a video acquisition unit that acquires surveillance video of a road from each of a plurality of imaging devices that capture images of the road; an analysis unit that determines a plurality of groups each containing two or more surveillance videos from the plurality of surveillance videos; a synthesis unit that creates a superimposed video for each of the plurality of groups by transparently superimposing the two or more surveillance videos within the same group; and a display unit that simultaneously displays the superimposed video created for each of the plurality of groups by the synthesis unit, wherein the analysis unit, as a first process, analyzes each of the plurality of surveillance videos acquired by the video acquisition unit; as a second process, determines the degree of similarity between the plurality of surveillance videos based on the results of the analysis; and as a third process, determines the plurality of groups based on the results of the determination .

As a second process, the analysis unit may determine the degree of similarity between the road shapes or structures contained in each of the multiple surveillance videos based on the results of the analysis.

The synthesis unit may set the transmittance of each of the two or more surveillance images to the same value.

Based on the result of the determination, the synthesis unit may set the transmittance of each of the two or more surveillance videos, for which the degree of similarity is relatively high among the surveillance videos in the same group, to be higher than that of surveillance videos in the same group that have a relatively low degree of similarity.

The combining unit may set an offset in the superimposition position or angle for each of the two or more surveillance videos, and superimpose the two or more surveillance videos.

The analysis unit may sequentially perform the first process, the second process, and the third process again when a predetermined time has elapsed since the most recent group determination.

The video acquisition unit may acquire surveillance video of the road from a memory unit or an external storage device.

In addition, in order to solve the above-mentioned problem, according to another aspect of the present invention, a program is provided that causes a computer to function as: an image acquisition unit that acquires surveillance footage of a road from each of a plurality of imaging devices that capture images of the road; an analysis unit that determines a plurality of groups each containing two or more surveillance footage from the plurality of surveillance footage; and a display screen generation unit that creates a superimposed image for each of the plurality of groups by transparently superimposing the two or more surveillance footage within the same group, and simultaneously displays the superimposed images created for each of the plurality of groups on a display unit, wherein the analysis unit, as a first process, analyzes each of the plurality of surveillance footage acquired by the image acquisition unit; as a second process, determines the degree of similarity between the plurality of surveillance footage based on the results of the analysis; and as a third process, determines the plurality of groups based on the results of the determination.

In addition, in order to solve the above-mentioned problem, according to another aspect of the present invention, there is provided a surveillance video processing system including: a video acquisition unit that acquires surveillance video of a road from each of a plurality of imaging devices that image the road; an analysis unit that determines a plurality of groups each containing two or more surveillance videos from the plurality of surveillance videos; a synthesis unit that creates a superimposed video for each of the plurality of groups by transparently superimposing the two or more surveillance videos within the same group; and a display unit that simultaneously displays the superimposed video created for each of the plurality of groups by the synthesis unit, wherein the analysis unit, as a first process, analyzes each of the plurality of surveillance videos acquired by the video acquisition unit; as a second process, determines the degree of similarity between the plurality of surveillance videos based on the results of the analysis; and as a third process, determines the plurality of groups based on the results of the determination .

In addition, in order to solve the above-mentioned problem, according to another aspect of the present invention, there is provided a surveillance video processing method executed by a computer, which includes acquiring surveillance video of a road from each of a plurality of imaging devices that capture images of the road, determining a plurality of groups each including two or more surveillance videos from the plurality of surveillance videos, creating a superimposed video for each of the plurality of groups by transparently superimposing the two or more surveillance videos within the same group, and simultaneously displaying the superimposed video created for each of the plurality of groups on a display unit , wherein determining the groups includes, as a first process, analyzing each of the plurality of surveillance videos, as a second process, determining the degree of similarity between the plurality of surveillance videos based on the results of the analysis, and as a third process, determining the plurality of groups based on the results of the determination.

The present invention described above makes it possible to easily visually monitor multiple surveillance images.

1 is an explanatory diagram illustrating an example of a surveillance video processing system according to an embodiment of the present invention; 1 is an explanatory diagram illustrating an example of the functional configuration of a surveillance video processing device 10 according to an embodiment of the present invention; FIG. 2 is an explanatory diagram illustrating an example of a screen displayed on a display unit 160 according to an embodiment of the present invention. 4 is a flowchart showing the operation of the surveillance video processing device 10. 1 is a block diagram showing a hardware configuration of a surveillance video processing device 10 according to an embodiment of the present invention.

Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Note that in this specification and drawings, components that have substantially the same functional configuration will be assigned the same reference numerals, and redundant explanations will be omitted.

Furthermore, in this specification and drawings, multiple components having substantially the same functional configuration may be distinguished by adding different letters after the same reference numeral. For example, multiple components having substantially the same functional configuration or logical significance may be distinguished as necessary, such as surveillance video display areas 50A and 50B. However, if there is no need to particularly distinguish between multiple components having substantially the same functional configuration, only the same reference numeral is used for each of the multiple components. For example, if there is no need to particularly distinguish between surveillance video display areas 50A and 50B, each surveillance video display area will be simply referred to as surveillance video display area 50.

<1. Overview of the surveillance video processing system>
An embodiment of the present invention relates to a surveillance video processing system that captures images of a road using multiple imaging devices installed in remote locations, analyzes the captured surveillance images, and synthesizes the analyzed surveillance images to create a superimposed image for visual surveillance. The surveillance video processing system is applied, for example, to monitoring road conditions such as on expressways or in tunnels for abnormalities. The configuration of a surveillance video processing system according to an embodiment of the present invention will be described below with reference to FIG. 1 .

Figure 1 is an explanatory diagram showing the configuration of a surveillance video processing system according to one embodiment of the present invention. As shown in Figure 1, the surveillance video processing system according to one embodiment of the present invention includes a surveillance video processing device 10 and multiple imaging devices 20.

Multiple imaging devices 20 are installed in remote locations to be monitored. In the example shown in Figure 1, multiple imaging devices 20 are installed at intervals within a tunnel 30, and each imaging device 20 captures images of the road conditions within the tunnel. Each imaging device 20 transmits the captured surveillance video to the surveillance video processing device 10 via network 1.

The surveillance video processing device 10 is an information processing terminal that receives surveillance video transmitted from multiple imaging devices 20, analyzes and synthesizes the received surveillance video, and creates a superimposed video for visual surveillance.

As shown in FIG. 1, the surveillance video processing device 10 and multiple imaging devices 20 are configured to be able to communicate via network 1.

(Identifying issues)
When monitoring surveillance images received from multiple imaging devices visually, one possible method is to display multiple surveillance images on a monitoring screen. For example, multiple surveillance images can be monitored on the same screen by switching the surveillance images displayed on the screen at regular intervals or by switching the displayed surveillance images in response to a monitor's operation. Alternatively, one possible method is to simultaneously display multiple surveillance images by reducing the display size of each surveillance image and dividing the display screen.

However, when switching between surveillance images displayed on a screen, there are times when each surveillance image is not displayed on the screen, which can delay the detection of an abnormality through visual monitoring. Furthermore, when reducing the display size of each surveillance image, the display size of each image becomes smaller, making it difficult to check the details of the situation, and making it easy to overlook an abnormality.

The inventors of the present invention have come up with an embodiment of the present invention with the above circumstances in mind. This embodiment of the present invention makes it possible to easily visually monitor multiple surveillance videos. Below, we will explain in detail the configuration and operation of a surveillance video processing device 10 according to this embodiment of the present invention.

2. Configuration of a surveillance video processing device according to one embodiment of the present invention
2 is an explanatory diagram showing an example of the functional configuration of a surveillance video processing device 10 according to an embodiment of the present invention. As shown in FIG. 2, the surveillance video processing device 10 according to this embodiment has a video acquisition unit 120, an analysis unit 130, a display screen generation unit 140, a storage unit 150, a display unit 160, and an operation unit 170.

(Video acquisition unit)
The video acquisition unit 120 acquires monitoring video. For example, the video acquisition unit 120 receives monitoring video transmitted from a plurality of image capture devices 20 via the network 1.

(Analysis Department)
As a first process, the analysis unit 130 analyzes the surveillance videos to distinguish, from among a plurality of surveillance videos, surveillance videos that contain similar road shapes or compositions, and as a second process, calculates the degree of similarity between each of the surveillance videos. The analysis unit 130 calculates the degree of similarity between each of the surveillance videos based on the degree of similarity between background images created from each of the surveillance videos.

More specifically, as a first process, the analysis unit 130 uses the average background method, which is a background model generation method, to create a background image from the multiple surveillance videos, removing moving objects such as vehicles. Furthermore, as a second process, the analysis unit 130 calculates the degree of similarity between the background images. In this case, the analysis unit 130 may particularly calculate the degree of similarity between road shapes or structures contained in the background images. The degree of similarity may be calculated by determining the distribution of brightness histograms, edge amounts, or distances between feature points, and multiplying each value by a predetermined coefficient. Alternatively, the calculation method may use machine learning or deep learning to calculate the degree of similarity between the background images.

Furthermore, the analysis unit 130 calculates the degree of similarity between each surveillance video based on the degree of similarity between the background images, and then, as a third process, determines groups for each of the two or more surveillance videos so that two or more surveillance videos with a high degree of similarity are grouped together. For example, the analysis unit 130 uses a cluster analysis method to group the surveillance videos with a high degree of similarity together. The cluster analysis method may be the K-means method or another method. In this case, the number of groups may be set in advance to match the screen configuration displayed on the display unit 160. Alternatively, the number of groups may be dynamically determined according to the calculation results of the degree of similarity.

(Display screen generation section)
The display screen generation unit 140 generates a monitoring screen and displays the monitoring screen on the display unit 160. As shown in FIG. 2 , the display screen generation unit 140 functions as a composition unit 141. The composition unit 141 creates a superimposed image in which two or more monitoring images are combined. The monitoring screen includes the superimposed image created by the composition unit 141. However, the image included in the monitoring screen may be switched between the superimposed image and the monitoring image before superimposition acquired from the image acquisition unit 120 based on an operation by the monitor.

The function of the composition unit 141 will now be described in more detail. The composition unit 141 acquires multiple surveillance videos from the video acquisition unit 120 and creates a superimposed video by transparently superimposing two or more of the acquired surveillance videos. When creating the superimposed video, the composition unit 141 creates a superimposed video of two or more surveillance videos for each group in accordance with the groups determined by the analysis unit 130.

When performing the above-mentioned transparency processing, the synthesis unit 141 sets the transparency of each surveillance video to the same value. Alternatively, if there are multiple surveillance videos that are particularly similar among two or more surveillance videos classified into the same group by the above-mentioned group determination, the transparency of those multiple surveillance videos may be set relatively high to improve visibility on the superimposed video.

Generally, surveillance footage used to monitor road conditions often contains similar road shapes or compositions. In particular, surveillance footage from inside tunnels often contains similar compositions due to restrictions on the installation location or height of the imaging device. When images with similar road shapes or compositions are superimposed, the normal movement in the images will be similar. If an abnormality occurs on one of the monitored roads, the movement in the surveillance footage at the location of the abnormality will be significantly different from the movement in the other surveillance footage, allowing a monitor to easily recognize that an abnormality has occurred even from a video in which multiple surveillance footage are superimposed. Therefore, the synthesis unit 141 creates a superimposed video of surveillance footage with a high degree of similarity based on the group determined by the analysis unit 130, making it possible to consolidate a large number of surveillance footage into a smaller number of images for monitoring than the number of surveillance footage before superimposition.

(Storage part)
The storage unit 150 stores information used in the operation of the surveillance video processing device 10. For example, the storage unit 150 stores pre-set layout information for screen display, which is referenced when the display screen generation unit 140 generates a surveillance screen.

(Display)
The display unit 160 displays various screens under the control of the display screen generation unit 140. For example, the display unit 160 displays a monitoring screen generated by the display screen generation unit 140.

Figure 3 is an explanatory diagram showing an example of a monitoring screen displayed on display unit 160. As shown in Figure 3, the monitoring screen includes a monitoring video display area 50, group information 51, and an imaging device location map 53. The monitoring video display area 50 displays the superimposed video created by the composition unit 141, or the monitoring video before superimposition. In the example shown in Figure 3, each of monitoring video display areas 50A to 50C displays the superimposed video of monitoring video belonging to a different group.

Group information 51 is information that indicates to which group the superimposed video displayed in the corresponding surveillance video display area 50 belongs. In the example shown in Figure 3, group information 51 is an icon resembling an imaging device, and the color of the icon indicates the group.

The imaging device location map 53 indicates where each of the multiple imaging devices 20 is located on the road being monitored, and which group it corresponds to. In the example shown in Figure 3, the imaging device location map 53 is composed of two levels, with the upper level displaying multiple imaging device icons U1-U11 corresponding to multiple imaging devices 20 capturing images of roads in the uphill direction, and the lower level displaying multiple imaging device icons D1-D11 corresponding to multiple imaging devices 20 capturing images of roads in the downhill direction. The location of each imaging device icon is set based on the actual installation location of the imaging device.

Furthermore, each imaging device icon is colored to indicate which group the surveillance video captured by the corresponding imaging device 20 belongs to. In the example shown in FIG. 3, imaging device icons U1 to U3, U9, U10, D2, D3, D7, D9, and D10 are colored the same as the icons in group information 51A. Therefore, it can be seen that the surveillance video display area 50A corresponding to group information 51A displays superimposed images of surveillance video captured by the imaging devices 20 corresponding to imaging device icons U1 to U3, U9, U10, D2, D3, D7, D9, and D10.

Similarly, the imaging device icons U4 to U6, D8, and D11 are colored the same as the icons in group information 51B. Therefore, it can be seen that the surveillance video display area 50B corresponding to group information 51B displays superimposed images of surveillance video captured by the imaging devices 20 corresponding to imaging device icons U4 to U6, D8, and D11. Furthermore, the imaging device icons U7, U8, U11, D1, D4 to D6 are colored the same as the icons in group information 51C. Therefore, it can be seen that the surveillance video display area 50C corresponding to group information 51C displays superimposed images of surveillance video captured by the imaging devices 20 corresponding to imaging device icons U7, U8, U11, D1, D4 to D6.

In addition, the display unit 160 may display surveillance video captured by a single imaging device 20, rather than superimposed video, by having the monitor operate the operation unit 170 to specify that imaging device 20. This specification may be made by selecting, from the imaging device icons 52, an imaging device icon 52 corresponding to the imaging device 20 for which the monitor wishes to display surveillance video.

(Operation unit)
The operation unit 170 is configured to be operated by a monitor or an operator of the surveillance video processing device 10 to input instructions or information to the surveillance video processing device 10. For example, when an abnormality is found in the superimposed video displayed on the display unit 160, the operator may operate the operation unit 170 to switch the displayed surveillance video in order to identify the location where the abnormality occurred.

The above-mentioned identification method may use, for example, the concept of a binary search algorithm, or other methods. One example of using the concept of a binary search algorithm is a method in which a monitor repeatedly selects an image in which an abnormality is detected from superimposed images displayed on a screen, thereby identifying the surveillance image of the point where an abnormality has occurred.

Specifically, when a monitor discovers an abnormality in the superimposed video displayed in the monitoring video display area 50A, he or she operates the operation unit 170 to select the monitoring video display area 50A. The display screen generation unit 140 divides two or more monitoring videos included in the superimposed video displayed in the selected monitoring video display area 50A into two groups. The synthesis unit 141 then creates a superimposed video of the monitoring videos belonging to each group. The display screen generation unit 140 displays the two created superimposed videos on the screen of the display unit 160. The monitoring video processing device 10 repeats this process of dividing the groups and creating superimposed videos based on the monitor's selection of superimposed videos until only one monitoring video belongs to a group, thereby enabling the monitoring video of the location where the abnormality is occurring to be quickly identified.

<3. Operation>
The configuration of the surveillance video processing device 10 according to one embodiment of the present invention has been described above. Next, the operation of the surveillance video processing device 10 according to one embodiment of the present invention will be summarized with reference to FIG.

Figure 4 is a flowchart showing the operation of the surveillance video processing device 10. First, the video acquisition unit 120 receives surveillance video transmitted from multiple imaging devices 20 via the network 1 (S410).

The analysis unit 130 creates a background image for each of the multiple surveillance videos acquired by the video acquisition unit 120 (S420).

Next, the analysis unit 130 calculates the degree of similarity between each of the created background images (S430).

Furthermore, the analysis unit 130 determines groups of each surveillance video that include two or more surveillance videos based on the calculated degree of similarity between the background images of each surveillance video (S440).

The synthesis unit 141 performs transparency processing on each of the multiple surveillance videos acquired by the video acquisition unit 120 (S450).

The composition unit 141 overlays the multiple monitoring images that have been subjected to transparency processing for each of the determined groups to create a superimposed image (S460). The display screen generation unit 140 updates the superimposed image included on the monitoring screen displayed on the display unit 160 to the content of the superimposed image created by the composition unit 141 in S460 (S470).

The surveillance video processing device 10 ends surveillance video processing when the surveillance person operates the operation unit 170 to issue an instruction to end processing (S480/Yes). Alternatively, processing may be set to end at a preset time. If no instruction to end processing is given, the surveillance video processing device 10 continues surveillance video processing (S480/No).

The display screen generation unit 140 determines whether a predetermined time has elapsed since the analysis unit 130 most recently determined the group. If the determination shows that the predetermined time has elapsed, the surveillance video processing device 10 again sequentially performs steps S410 to S480 (S490/Yes).

If the display screen generation unit 140 determines that the predetermined time has not yet passed (S490/No), the image acquisition unit 120 acquires the surveillance image (S500), and the surveillance image processing device 10 sequentially repeats the processes of S450 to S480 again. In this way, the analysis unit 130 creates background images, calculates the degree of similarity, and determines groups at predetermined intervals, thereby periodically updating the groups. By periodically updating the groups, the visibility of the superimposed image can be maintained even if changes occur on the monitored road, such as changes in lighting conditions or the installation of construction vehicles or signs for road construction.

<4. Effects>
According to the embodiment of the present invention described above, a variety of operational effects can be obtained. For example, according to the embodiment of the present invention, the synthesis unit 141 performs transparency processing on each of the multiple surveillance videos acquired by the video acquisition unit 120, and overlays the videos to create a superimposed video. This processing makes it possible to consolidate multiple surveillance videos into a smaller number of videos than the surveillance videos before superimposition. When the multiple surveillance videos are displayed on the same screen, the use of the superimposed video reduces the degree to which the display size of each surveillance video is reduced. Therefore, a surveillance officer visually monitoring multiple surveillance videos on the same screen can easily check the details that occur in the surveillance videos.

Furthermore, according to one embodiment of the present invention, the synthesis unit 141 creates a superimposed image of two or more surveillance videos for each group determined by the analysis unit 130 so that two or more surveillance videos with a high degree of similarity are grouped together. Surveillance videos with a high degree of similarity will have similar movements under normal circumstances. Therefore, it becomes easier for a surveillance officer to recognize that an abnormality has occurred, even from the superimposed image.

5. Hardware Configuration
The above describes one embodiment of the present invention. The above-described information processing, such as analysis and composition of surveillance video, is realized by cooperation between software and the hardware of the surveillance video processing device 10 described below.

Figure 5 is a block diagram showing the hardware configuration of the surveillance video processing device 10 according to this embodiment. The surveillance video processing device 10 may include a CPU (Central Processing Unit) 102, a ROM (Read Only Memory) 104, a RAM (Random Access Memory) 106, an internal bus 108, an input/output interface 110, a display device 112, an input device 113, an audio output unit 114, a storage device 115, a drive 116, a network interface 117, and an external interface 118.

The CPU 102 functions as an arithmetic processing unit and control unit, and controls the overall operation of the surveillance video processing device 10 in accordance with various programs. By cooperating with the ROM 104, RAM 106, and software described below, the CPU 102 can realize functions such as the video acquisition unit 120, analysis unit 130, and display screen generation unit 140.

ROM 104 stores programs and calculation parameters used by CPU 102. RAM 106 temporarily stores programs used by CPU 102 and parameters that change as needed during execution.

The CPU 102, ROM 104, and RAM 106 are interconnected by an internal bus 108, and are further connected via an input/output interface 110 to the display device 112, input device 113, audio output unit 114, storage device 115, drive 116, network interface 117, and external interface 118, which will be described later.

The display device 112 is, for example, a CRT display device, a liquid crystal display (LCD), an OLED device, or other display device, and converts video data into video and outputs it. The input device 113 may be composed of a mouse, keyboard, touch panel, buttons, microphone, sensors, switches, control circuits, and the like. The audio output unit 114 is an audio output device such as a speaker or headphones, and converts audio data and the like into audio and outputs it.

The storage device 115 is a data storage device configured as an example of the storage unit 150 according to this embodiment. The storage device 115 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, and a deletion device that deletes data recorded on the storage medium. The storage device 115 is configured, for example, as an HDD (Hard Disk Drive) or SSD (Solid Storage Drive), or memory with equivalent functionality. This storage device 115 drives storage and stores programs executed by the CPU 102 and various data.

Drive 116 is a reader/writer for storage media, and is either built into the surveillance video processing device 10 or attached externally. Drive 116 reads information stored on an attached removable storage medium such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, and outputs the information to RAM 106. Drive 116 can also write information to removable storage media.

The network interface 117 is a communication interface composed of devices for connecting to a communication network such as the Internet. The network interface 117 may be a communication device compatible with a wired LAN (Local Area Network) or a wireless LAN, or it may be a wired communication device that performs wired communication.

The external interface 118 is a connection interface consisting of connection ports for connecting external devices, such as a USB (Universal Serial Bus) port, an IEEE 1394 port, a SCSI (Small Computer System Interface) port, an RS-232C port, or an optical audio terminal.

<6. Supplementary Information>
Although the preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, the present invention is not limited to these examples. It is clear that a person skilled in the art to which the present invention pertains can conceive of various modifications and alterations within the scope of the technical ideas set forth in the claims, and it is understood that these also naturally fall within the technical scope of the present invention.

For example, in the above embodiment, an example was described in which the video acquisition unit 120 acquires surveillance video from multiple imaging devices 20 via the network 1, but the video acquisition unit 120 may also acquire surveillance video that has been stored in advance in the storage unit 150, or may read surveillance video from an external storage device.

In addition, in the above embodiment, the analysis unit 130 determines two or more groups of surveillance footage, but the present invention is not limited to such an example. For example, a surveillance officer may visually determine surveillance locations with similar road shapes or compositions in advance, and group the locations based on that determination. The synthesis unit 141 may create a superimposed image based on the grouping results. If the grouping is performed in advance, the grouping results may be stored in the memory unit 150, the display screen generation unit 140 may read the results from the memory unit 150, and the synthesis unit 141 may create a superimposed image based on the results. Furthermore, the analysis unit 130 may calculate the similarities between multiple surveillance footage and store the grouping results in the memory unit 150. The display screen generation unit 140 may read the results from the memory unit 150, and the synthesis unit 141 may create a superimposed image based on the results.

In addition, in the above embodiment, an example was described in which the synthesis unit 141 creates a superimposed image by making each of the multiple surveillance videos transparent and simply superimposing the surveillance videos, but the present invention is not limited to such an example. For example, when creating a superimposed image, a process may be performed in which an offset in the superimposition position or angle is set in the surveillance videos, and similar road shapes or compositions included in each of the surveillance videos are aligned so that they overlap.

Furthermore, the steps in the processing of the operation of the surveillance video processing device 10 according to this embodiment do not necessarily have to be processed chronologically in the order depicted in the explanatory diagram. For example, the steps in the processing of the operation of the surveillance video processing device 10 may be processed in an order different from the order depicted in the explanatory diagram, or may be processed in parallel.

It is also possible to create a computer program that causes hardware such as the CPU, ROM, and RAM built into the surveillance video processing device 10 to perform functions equivalent to those of each component of the surveillance video processing device 10 described above.

Furthermore, the surveillance video processing device 10 according to this embodiment may be provided as a surveillance video processing system including multiple information processing devices. For example, the above-mentioned analysis unit 130 and display screen generation unit 140 may be provided separately in multiple information processing devices.

The present invention is applicable to road traffic situations where road conditions are monitored using multiple imaging devices installed in remote locations, and is particularly applicable to visual monitoring of road surface abnormalities in tunnels.

REFERENCE SIGNS LIST 10 Surveillance video processing device 20 Imaging device 120 Video acquisition unit 130 Analysis unit 140 Display screen generation unit 141 Synthesis unit 150 Storage unit 160 Display unit 170 Operation unit

Claims (10)

an image acquisition unit that acquires monitoring images of the road from each of a plurality of imaging devices that capture images of the road;
an analysis unit that determines a plurality of groups each including two or more surveillance videos from the plurality of surveillance videos;
a synthesis unit that creates a superimposed image by transparently superimposing the two or more surveillance images in the same group for each of the plurality of groups;
a display unit that simultaneously displays the superimposed images created for each of the plurality of groups by the synthesis unit,
The analysis unit
As a first process, each of the plurality of surveillance videos acquired by the video acquisition unit is analyzed;
As a second process, a degree of similarity between the plurality of surveillance videos is determined based on the results of the analysis;
As a third process, the surveillance video processing device determines the plurality of groups based on the result of the determination. The analysis unit
As a second process, based on the results of the analysis, a degree of similarity between road shapes or structures included in each of the plurality of surveillance videos is determined.
The surveillance video processing device according to claim 1 . the combining unit sets the transmittance of each of the two or more monitoring videos to an equal value.
3. The surveillance video processing device according to claim 1. Based on the result of the determination, the synthesis unit sets a higher transmittance for a surveillance video having a relatively high degree of similarity among the two or more surveillance videos in the same group than for a surveillance video having a relatively low degree of similarity among the surveillance videos in the same group.
3. The surveillance video processing device according to claim 1. the combining unit sets an offset of a superposition position or an angle for each of the two or more surveillance videos, and superimposes the two or more surveillance videos;
The surveillance video processing device according to any one of claims 1 to 4. the analysis unit sequentially performs the first process, the second process, and the third process again when a predetermined time has elapsed since the most recent group determination.
The surveillance video processing device according to any one of claims 1 to 5. A surveillance video processing device according to any one of claims 1 to 6, wherein the video acquisition unit acquires surveillance video of the road from a memory unit or an external storage device. Computer,
an image acquisition unit that acquires monitoring images of the road from each of a plurality of imaging devices that capture images of the road;
an analysis unit that determines a plurality of groups each including two or more surveillance videos from the plurality of surveillance videos;
a display screen generation unit that creates a superimposed image for each of the plurality of groups by transparently superimposing the two or more monitoring images within the same group, and simultaneously displays the superimposed images created for each of the plurality of groups on a display unit;
It functions as
The analysis unit
As a first process, each of the plurality of surveillance videos acquired by the video acquisition unit is analyzed;
As a second process, a degree of similarity between the plurality of surveillance videos is determined based on the results of the analysis;
As a third process, the program determines the plurality of groups based on a result of the determination. an image acquisition unit that acquires monitoring images of the road from each of a plurality of imaging devices that capture images of the road;
an analysis unit that determines a plurality of groups each including two or more surveillance videos from the plurality of surveillance videos;
a synthesis unit that creates a superimposed image by transparently superimposing the two or more surveillance images in the same group for each of the plurality of groups;
a display unit that simultaneously displays the superimposed images created for each of the plurality of groups by the synthesis unit,
The analysis unit
As a first process, each of the plurality of surveillance videos acquired by the video acquisition unit is analyzed;
As a second process, a degree of similarity between the plurality of surveillance videos is determined based on the results of the analysis;
As a third process, the surveillance video processing system determines the plurality of groups based on the result of the determination. acquiring a monitoring image of the road from each of a plurality of imaging devices that capture images of the road;
determining a plurality of groups including two or more surveillance videos of the plurality of surveillance videos;
For each of the plurality of groups, creating a superimposed image by transparently superimposing the two or more surveillance images in the same group;
simultaneously displaying the superimposed images created for each of the plurality of groups on a display unit ;
Including,
determining the group
As a first process, each of the plurality of surveillance videos is analyzed;
As a second process, a degree of similarity between the plurality of surveillance videos is determined based on the results of the analysis;
A computer-implemented surveillance video processing method including, as a third process, determining the plurality of groups based on a result of the determination.