JP3679233B2 - Monitoring image processing device - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a monitoring image processing apparatus that is also compatible with an electronic intensifying camera having a function of compensating for insufficient illuminance or the like by increasing the accumulation time of a light receiving element.
[0002]
[Prior art]
A conventional monitoring image processing apparatus will be described with reference to FIG. FIG. 7 is a block diagram showing a configuration of a conventional monitoring image processing apparatus.
[0003]
In FIG. 7, reference numeral 1 denotes a video input unit that receives video processed by the monitoring image processing apparatus, 2 denotes an A / D conversion unit that quantizes video input from the video input unit 1, and 3 denotes an A / D conversion unit 2 4 is a current image storage unit for storing current video data and 4 is a background image storage unit for storing a background image for comparison, which is generated by receiving the output from the A / D conversion unit 2 and performing a corresponding calculation. Reference numeral 5 denotes a background update unit that calculates data of the background image storage unit 4 according to a certain rule and updates the background, and is generally updated using a simple rule. For example, the average of the past five current images is set as the background image.
[0004]
In the figure, 6 is a background difference unit that compares two images of the current image storage unit 3 and the background image storage unit 4 and calculates the background difference data, and 7 is binarizing the data of the background difference unit 6. It is a threshold value calculation part which calculates the threshold value for performing, and it is common to obtain | require an optimal threshold value based on background difference data.
[0005]
Further, in the figure, 8 is a binarization unit that binarizes the background difference data with the threshold value obtained by the threshold value calculation unit 7, 9 receives the binary data output from the binarization unit 8, A feature amount calculation unit for calculating a feature amount, 10 is a report target feature amount storage unit for storing in advance a feature parameter of a regular report target such as a person or a vehicle, and 11 is output from the feature amount calculation unit 9 A recognition processing unit that compares the feature amount data that is generated and the feature amount parameter of the notification target from the notification target feature amount storage unit 10 to determine whether or not an event has occurred, 12 is a notification that notifies event discovery, and 13 is A notification processing unit that receives the notification 12 and issues a notification (eg, BEEP sound or the like).
[0006]
FIG. 8 is a flowchart showing in more detail the configuration (operation) of the conventional recognition processing unit 11 shown in FIG.
[0007]
Step 21 of FIG. 8 is a change area integration processing unit that integrates change areas that are considered to belong to the same moving object by looking at the binarized data, and steps 22 to 26 are integrated. This is a feature amount comparison unit that determines whether or not the change area is a report target by comparing it with a report target feature parameter.
[0008]
In step 22, it is checked whether the change area exists continuously for a predetermined time. Next, in step 23, it is determined whether or not the change area has a predetermined area. Next, in step 24, it is determined whether or not the change area has a predetermined vertical and horizontal dimension. Further, in step 25, it is determined whether or not the change area has a predetermined moving speed. Then, in response to the above result, in step 26, it is determined whether the notification target is found or not, and if it is determined that the event is found, the notification processing unit 13 in FIG. 7 is notified.
[0009]
Next, the operation of the conventional monitoring image processing apparatus will be described. A video signal given to the apparatus from the outside is received by the video input unit 1 and sent to the A / D conversion unit 2. The A / D converter 2 converts the received video signal into digital data for later processing. In general, conversion into multi-value data of 8 bits per pixel is performed.
[0010]
The current image storage unit 3 stores the input current image data and prepares for subsequent processing. The background image storage unit 4 stores a background image created based on the input current image data and prepares for subsequent processing. The background update unit 5 periodically performs background update processing on the background image stored in the background image storage unit 4 at a constant rule. This is generally calculated based on the current image that is periodically sampled. For example, the average value of the current images of the past five scenes is used as the background image, or the video of the frame before a certain time. In many cases.
[0011]
The background difference unit 6 compares the outputs of the current image storage unit 3 and the background image storage unit 4, obtains a difference for each pixel, and outputs difference data that is the difference as a frame image. The difference data generally represents a portion of the video where the luminance has changed, that is, a multi-value changing region. Usually, moving objects such as people and vehicles are the main, but in rare cases the brightness of non-reporting objects such as "appearance of shadows due to sunlight" and "reflection of car headlights at night" Sometimes changes are output.
[0012]
The threshold value calculation unit 7 obtains a threshold value for binarizing the multilevel change region sent from the background difference unit 6. The multi-value change area is multi-value data, and is not appropriate for the recognition process as it is. In order to make subsequent determinations at high speed, it is general to binarize and convert to binary data. The binarization unit 8 binarizes the multi-value change area with the threshold value. As a result, the change area is a binary change area thereafter. However, depending on the device, the multi-value change area may be directly recognized without performing this binarization.
[0013]
The change area will be described with reference to FIG. FIG. 9 is an image of a normal main gate. Now, a person is moving in the image. In this case, the position of the moving person becomes the change area as it is. FIG. 10 is an image in which the superimpose in which the change area is dyed in black is overlapped.
[0014]
The feature quantity calculation unit 9 receives the input change area data and calculates the feature quantity of the change area. As an example, the feature amounts are “area”, “vertical / horizontal dimension”, and “speed”. In the notification target feature amount storage unit 10, the feature amount of an object (for example, a person or a vehicle) that is a regular notification target of the present apparatus is recorded in advance. The recognition processing unit 11 receives the feature amount data from the feature amount calculation unit 9, and whether or not the feature amount matches the feature parameter of the report target stored in the report target feature storage unit 10. Make a decision. If it is determined that they are close to each other, the event is found and the notification 12 is output.
[0015]
In the recognition process, recognition is performed according to the following procedure. However, this is only an example. The change area integration processing unit 21 looks at the change areas and integrates the change areas that are considered to belong to the same moving object into one change area. Next, the feature amount comparison units 22 to 25 determine whether or not the change region integrated by the change region integration processing unit 21 is a report target. Here, it is determined whether or not the feature quantity in the change area matches the predetermined feature quantity parameter of the regular report target. Here, if the predetermined condition is met, it is regarded as a regular issue target.
[0016]
Here, the following determination is performed as an example.
In step 22, it is checked whether the change area exists continuously for a predetermined time.
In step 23, it is determined whether or not the change area has a predetermined area.
In step 24, it is determined whether or not the change area has a predetermined vertical and horizontal dimension.
In step 25, it is determined whether or not the change area has a predetermined moving speed.
In general, the “area”, “vertical / horizontal dimensions”, and “moving speed” are referred to by calculating an average during a predetermined time in step 22.
[0017]
However, conversely, even if something completely different from the regular alert appears here (eg, the appearance of a building shadow due to sunlight), if the feature value matches here, the device It will be judged and it will lead to wrong report as it is. Such an erroneous report due to a non-report target is hereinafter referred to as unnecessary detection.
[0018]
Whether it is unnecessary detection or normal detection, the event is transmitted from the recognition processing unit 11 to the notification processing unit 13 where the notification processing is performed. Usually, it is a process of sending a specific signal to a higher-level personal computer (PC) or sounding a buzzer of the apparatus. If the condition is not met, it is considered that there is no report target, and the event notification 12 is not output. Accordingly, in this case, nothing is reported to the alert processing unit 13, so that no alert is issued. In general, the recognition processing unit 11 and the notification processing unit 13 are processed by software (S / W).
[0019]
[Problems to be solved by the invention]
In the conventional monitoring image processing apparatus as described above, when an electronic intensifying camera is used, there is a possibility that the recognition performance is lowered due to its structure. That is, in the electronic sensitizing camera, the same image data may be sent out continuously for a plurality of frames due to its structure. When the monitoring image processing apparatus continuously captures the same image, the difference between the images cannot be detected because the images are the same. Even if the change area can be detected in the images before and after this, if time-series features are used for the determination of the intruder, normal recognition is hindered. This is called lack of continuity.
[0020]
For example, as shown in FIG. 11, when an image from an electronic intensifying camera in which the image A and the image B are the same and the image C and the image D are the same is obtained, the conventional monitoring image processing apparatus uses the image A Since there is no change between the image B and the image B, it is determined that there is no intruder. Then, there is a change between the image B and the image C, and an intruder is found. However, since there was no intruder before and after that, there was a problem that it was judged that there was no intruder due to lack of continuity.
[0021]
The present invention has been made to solve the above-described problems. The sensitization magnification of the electronic sensitizing camera is automatically obtained, and the processing cycle is sequentially switched based on the obtained sensitization magnification. It is an object of the present invention to obtain a monitoring image processing apparatus capable of preventing the lack of image quality and improving the recognition rate.
[0022]
[Means for Solving the Problems]
A monitoring image processing apparatus according to the present invention includes a current image storage unit that stores a current image from an electronic intensifying camera, and a background image storage that stores a background image for comparison based on the image from the electronic intensifying camera. A background update unit that calculates a background image by calculating image data of the background image storage unit according to a certain rule, and compares the two images of the current image storage unit and the background image storage unit to obtain background difference data A background difference unit for calculating a change area, Based on the change of the area of the change area or the number of labels The sensitization magnification of the electronic sensitizing camera By analogy Sensitization magnification analogy processing unit for notification, feature amount calculation unit for calculating the feature amount based on the background difference data, report target feature amount storage unit for storing the feature parameter of the report target in advance, and the notification Was The recognition processing cycle is determined according to the sensitization magnification, and the recognition A recognition processing unit that determines whether an event has occurred by comparing the feature amount data calculated by the feature amount calculation unit with the feature amount parameter for each processing cycle, and notification of event discovery from the recognition processing unit And a report processing unit that reports based on the above.
[0023]
The monitoring image processing apparatus according to the present invention includes: A current image storage unit that stores a current image from an electronic sensitizing camera, a background image storage unit that stores a background image for comparison based on an image from the electronic sensitizing camera, and image data of the background image storage unit A background update unit that calculates a background image by calculating a constant image, and a background difference unit that compares two images of the current image storage unit and the background image storage unit to calculate a change area that is background difference data; A sensitization magnification analogy processing unit for analogizing and notifying the sensitization magnification of the electronic sensitizing camera based on identification of characters or symbols superimposed on the image by the electronic sensitizing camera, and based on the background difference data A feature amount calculation unit for calculating the feature amount, a report target feature amount storage unit for storing the feature parameter of the report target in advance, and a recognition processing cycle according to the notified sensitization magnification. A recognition processing unit that determines whether an event has occurred by comparing the feature amount data calculated by the feature amount calculation unit and the feature amount parameter for each recognition processing cycle; And a report processing unit that reports based on event discovery notifications Is.
[0025]
DETAILED DESCRIPTION OF THE INVENTION
Embodiment 1 FIG.
A monitoring image processing apparatus according to Embodiment 1 of the present invention will be described with reference to FIG. FIG. 1 is a block diagram showing the configuration of a monitoring image processing apparatus according to Embodiment 1 of the present invention. In addition, in each figure, the same code | symbol shows the same or equivalent part.
[0026]
In FIG. 1, the video input unit 1 to the notification target feature amount storage unit 10 and the event notification 12 to the notification processing unit 13 are the same as those in the conventional example, and are omitted. Reference numeral 11A denotes a recognition processing unit, and reference numeral 14 denotes a sensitization magnification analogy processing unit that automatically detects the sensitization magnification (length of accumulation time) of the electronic sensitization camera. The details will be described later in Embodiments 2 and 3. It shows with. Further, 15 is a notification that informs the processing cycle based on the sensitization magnification obtained by the sensitization magnification analogy processing unit 14.
[0027]
FIG. 2 shows a flow showing the configuration (operation) of the recognition processing unit 11A shown in FIG. 1 in more detail.
[0028]
Next, the operation of the first embodiment will be described. Since the video input unit 1 to the notification target feature amount storage unit 10 and the event notification 12 to the notification processing unit 13 are the same as the conventional example, the description thereof is omitted.
[0029]
Below, an example about the case where a recognition and determination cycle is changed according to the sensitization magnification of an electronic sensitization camera is shown. Based on the sensitization magnification determined by the sensitization magnification analogy processing unit 14, the sensitization magnification is notified 15 to the recognition processing unit 11A, the cycle for performing the recognition / determination process is determined, and the recognition process is performed in accordance with the cycle. I do.
[0030]
As shown in FIG. 2, in step 27, the current cycle determines a recognition cycle from the sensitization magnification, and the recognition / determination processing in steps 21 to 26 is performed in that cycle. For example, when the sensitization magnification is 4 (the same image is input in 4 frames), the recognition process is performed once in 4 frames.
[0031]
The same effect can be obtained by changing the image capture cycle instead of changing the recognition processing cycle.
[0032]
As described above, according to the present embodiment, the monitoring image processing apparatus avoids capturing the same continuous image input from the electronic intensifying camera, or is recognized and determined based on the same continuous image result. By avoiding it, the lack of continuity is prevented and the recognition rate is improved.
[0033]
That is, in the first embodiment, a video input unit 1 for inputting a video signal, an A / D conversion unit 2 for A / D converting the video signal taken in from the input unit, and current image data are obtained (necessary). A background image storage unit 3 that obtains a background image as comparison image data or records it as necessary, and a background image in a certain procedure (eg, average of past 5 images). A background update unit 5 for updating the current image data, a background difference unit 6 for comparing the current image data with the background image data, and extracting a moving object / changed object (multi-value change region) in the image as a difference, and a change region A threshold value calculation unit 7 for calculating a threshold value for binarizing, a binarization unit 8 for binarizing the change region, and feature quantities of the change region after binarization (for example, area, vertical and horizontal dimensions) ) For various calculations, and operator in advance Report target feature amount storage unit 10 for storing set values (eg, upper and lower limits of area, upper and lower limits of vertical and horizontal dimensions: feature amount parameters) of the determined report target (eg, person, car) And a recognition processing unit 11A for recognizing that the feature value of the binary change area corresponds to the feature parameter of the regular report target, and a notification for notifying the event (when matching is found in the recognition process). In the monitoring image processing apparatus having the processing unit 13, when the electronic sensitizing camera is connected, when the length of the current electronic sensitizing camera accumulation time (sensitization magnification) is obtained, In order to prevent malfunction or deterioration of accuracy of the monitoring image processing device, it has a function that can arbitrarily set the image capture cycle from the camera or the recognition processing cycle according to the sensitization magnification, thereby repeatedly inputting the same image Because evils or to avoid adverse effects for performing recognition on consecutive identical images, the determination has a function of preventing malfunction or deterioration in accuracy of the device.
[0034]
As described above, according to the first embodiment, when the same image is input from the electronic sensitizing camera for a certain period, the recognition / determination process cycle is set based on the sensitization magnification. , The change area cannot be detected, and even if it can be detected, there is a risk that it will be erroneously determined in the final judgment due to the lack of continuity. " This makes it possible to connect an electronic intensifying camera.
[0035]
Embodiment 2. FIG.
A monitoring image processing apparatus according to Embodiment 2 of the present invention will be described with reference to FIG. FIG. 3 is a block diagram showing the configuration of the monitoring image processing apparatus according to Embodiment 2 of the present invention. In addition, in each figure, the same code | symbol shows the same or equivalent part.
[0036]
In FIG. 3, the video input unit 1 to the notification processing unit 13 are the same as those in the first embodiment, and are omitted. 14A is a sensitization magnification analogy processing unit that infers the sensitization magnification from the area of the change region or the change in the number of labels.
[0037]
A flow showing the sensitization magnification analogy processing unit 14A in more detail is shown in FIG. Step 31 looks at every frame to see if there is a change area. Next, step 32 looks at the magnitude relationship between the number of frames in which there is no change area and the current sensitization magnification. Step 33 counts the number of times the state without the change area has continued. Step 34 increases the value of the current sensitization magnification. Step 35 sets the value of the accumulation counter as a new sensitization magnification when the number of frames in which the state of no change area stored in the accumulation counter continues is smaller than the current sensitization magnification.
[0038]
The flow showing the recognition processing unit 11A in FIG. 3 in more detail is the same as that in FIG.
[0039]
Next, a typical example of the operation will be described. Since the video input unit 1 to the notification processing unit 13 are the same as those in the first embodiment, description thereof is omitted.
[0040]
Below, an example about the case where a sensitization magnification is calculated | required using the area of a change area | region is shown. When an electronic sensitizing camera is used, since the same image is input for a certain period (which is determined by the sensitization magnification), there is no change area during that period. Further, even when the time exceeds the sensitization magnification, if there is no moving object, the change area does not appear. Using this feature, the sensitization magnification analogy processing unit 14A detects the sensitization magnification.
[0041]
In the flowchart of the sensitization magnification analogy processing unit 14A shown in FIG. 4, it is considered whether there is a change area when the current image is compared with the previous image in step 31, and if there is no change area, in step 33 The accumulation counter counts the number of frames in which an image having no change area continues continuously. If there is a change area, the number of continuous frames stored in the accumulation counter in step 32 and having no change area counted up to now is compared with the current sensitization magnification. If it is smaller than the sensitization magnification, this value is set as a new sensitization magnification. Further, in order to cope with the case where the sensitization magnification of the electronic sensitization camera is increased, if the number of consecutive frames is larger than the sensitization magnification in step 34, the sensitization magnification is increased (for example, increased by 1). However, the maximum value of the sensitization magnification is set in advance.
[0042]
That is, the number of frames in which an image without a change area continues after the change area appears until the next change area appears is counted, and when the number of frames is smaller than the current sensitization magnification, The sensitization magnification is used.
[0043]
In this method, even if an image having no change region is continuously input and the sensitization magnification is increased, an accurate sensitization magnification can be obtained as soon as the change region is generated.
[0044]
As described above, according to the present embodiment, the sensitization magnification can be automatically detected from the obtained image, and the monitoring image processing apparatus itself can correspond to the electronic sensitization camera in accordance with the magnification. Has an effect.
[0045]
That is, the second embodiment automatically detects the sensitization magnification from the obtained image in the monitoring image processing apparatus of the first embodiment when the electronic sensitizing camera is connected. As a function, it has a function of analogizing the sensitization magnification by using the fact that the area of the change region or the number of labels changes or does not change extremely in a certain cycle.
[0046]
As described above, according to the second embodiment, when the same image is input from the electronic intensifying camera for a certain period, “whether or not the area of the change region or the number of labels changes in a certain cycle” is determined. By using this, the current sensitization magnification is determined, and based on the determination result, the monitoring image processing apparatus itself can correspond to the electronic sensitization camera.
[0047]
Embodiment 3 FIG.
A monitoring image processing apparatus according to Embodiment 3 of the present invention will be described with reference to FIG. FIG. 5 is a block diagram showing a configuration of a monitoring image processing apparatus according to Embodiment 3 of the present invention. In addition, in each figure, the same code | symbol shows the same or equivalent part.
[0048]
In FIG. 5, the video input unit 1 to the notification processing unit 13 are the same as those in the first embodiment, and are omitted. 14B is a sensitization magnification analogy processing unit for analogizing the sensitization magnification by identifying characters and symbols superimposed by the electronic sensitization camera.
[0049]
A flow showing the sensitization magnification analogy processing unit 14B in more detail is shown in FIG. In step 41, the superimposed character is detected. Next, the character detected in step 42 is identified by character recognition. Next, in step 43, the sensitization magnification is determined from the character.
[0050]
The flow showing the recognition processing unit 11A in FIG. 5 in more detail is the same as that in FIG.
[0051]
Next, a typical example of the operation will be described. Since the video input unit 1 to the notification processing unit 13 are the same as those in the first embodiment, description thereof is omitted.
[0052]
Below, an example about the case where a sensitization magnification is calculated | required using the character superimposed by the electronic sensitization camera is shown. The sensitization magnification is displayed in a certain area in the image by the electronic sensitizing camera. The sensitization magnification analogy processing unit 14B extracts only the portion of the character superimposed in the image at step 41, then reads the character by character recognition at step 42, and then at step 43 reads the current character. Determine the sensitization magnification.
[0053]
The displayed character may not be the current sensitization magnification. If the same character is superimposed during the sensitization magnification time with the electronic sensitization camera, the sensitization magnification can be obtained by reading the character and counting how many times the same character is repeated. it can. This is also possible with symbols instead of letters.
[0054]
As described above, according to the present embodiment, the sensitization magnification can be automatically detected from the obtained image more accurately than the method of the second embodiment, and the monitoring image is matched to the magnification. There exists an effect that processing apparatus itself can respond to an electronic intensifying camera.
[0055]
That is, in the monitoring image processing apparatus according to the first embodiment, a character or symbol monitoring area is provided at a specific location of an image input from the electronic intensifying camera, and the electronic enhancement is performed in the area (section). It has a function of identifying a character or a symbol superimposed by the sensation camera and estimating the sensitization magnification of the current electronic sensitization camera therefrom.
[0056]
As described above, according to the third embodiment, when the same image is input from the electronic intensifying camera for a certain period of time, “superimpose characters and symbols by the electronic intensifying camera and recognize the characters and symbols. By using this, the current sensitization magnification is determined more accurately than the method of the second embodiment, and the monitoring image processing apparatus itself performs electronic sensitization according to the magnification based on the determination result. It is possible to correspond to the camera.
[0057]
【The invention's effect】
As described above, the monitoring image processing apparatus according to the present invention includes a current image storage unit that stores a current image from an electronic sensitizing camera, and a background image for comparison based on the image from the electronic sensitizing camera. Comparing the two images of the background image storage unit to store, the background update unit that updates the background image by calculating the image data of the background image storage unit according to a certain rule, the current image storage unit and the background image storage unit A background difference unit that calculates a change area that is background difference data; Based on the change of the area of the change area or the number of labels The sensitization magnification of the electronic sensitizing camera By analogy Sensitization magnification analogy processing unit for notification, feature amount calculation unit for calculating the feature amount based on the background difference data, report target feature amount storage unit for storing the feature parameter of the report target in advance, and the notification Was The recognition processing cycle is determined according to the sensitization magnification, and the recognition A recognition processing unit that determines whether an event has occurred by comparing the feature amount data calculated by the feature amount calculation unit with the feature amount parameter for each processing cycle, and notification of event discovery from the recognition processing unit Since it is provided with a report processing unit that reports based on the above, it is possible to prevent the lack of continuity and improve the recognition rate.
[0058]
Moreover, the monitoring image processing apparatus according to the present invention is as described above. A current image storage unit that stores a current image from an electronic sensitizing camera, a background image storage unit that stores a background image for comparison based on an image from the electronic sensitizing camera, and image data of the background image storage unit A background update unit that calculates a background image by calculating a constant image, and a background difference unit that compares two images of the current image storage unit and the background image storage unit to calculate a change area that is background difference data; A sensitization magnification analogy processing unit for analogizing and notifying the sensitization magnification of the electronic sensitizing camera based on identification of characters or symbols superimposed on the image by the electronic sensitizing camera, and based on the background difference data A feature amount calculation unit for calculating the feature amount, a report target feature amount storage unit for storing the feature parameter of the report target in advance, and a recognition processing cycle according to the notified sensitization magnification. A recognition processing unit that determines whether an event has occurred by comparing the feature amount data calculated by the feature amount calculation unit and the feature amount parameter for each recognition processing cycle; And a report processing unit that reports based on event discovery notifications Therefore, the lack of continuity can be prevented, and the recognition rate can be improved.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a configuration of a monitoring image processing apparatus according to Embodiment 1 of the present invention.
FIG. 2 is a flowchart showing an operation of a recognition processing unit of the monitoring image processing apparatus according to the first embodiment of the present invention.
FIG. 3 is a block diagram showing a configuration of a monitoring image processing apparatus according to Embodiment 2 of the present invention.
FIG. 4 is a flowchart showing an operation of a sensitization magnification analogy processing unit of the monitoring image processing apparatus according to the second embodiment of the present invention.
FIG. 5 is a block diagram showing a configuration of a monitoring image processing apparatus according to Embodiment 3 of the present invention.
FIG. 6 is a flowchart showing the operation of the sensitization magnification analogy processing unit of the monitoring image processing apparatus according to the third embodiment of the present invention.
FIG. 7 is a block diagram illustrating a configuration of a conventional monitoring image processing apparatus.
FIG. 8 is a flowchart illustrating an operation of a recognition processing unit of a conventional monitoring image processing apparatus.
FIG. 9 is a diagram illustrating a current image according to a conventional monitoring image processing apparatus.
FIG. 10 is a diagram illustrating a current image obtained by superimposing a change area according to a conventional monitoring image processing apparatus.
FIG. 11 is a diagram showing an image obtained by an electronic intensifying camera.
[Explanation of symbols]
1 video input unit, 2 A / D conversion unit, 3 current image storage unit, 4 background image storage unit, 5 background update unit, 6 background difference unit, 7 threshold value calculation unit, 8 binarization unit, 9 feature value calculation , 10 notification target feature amount storage unit, 11A recognition processing unit, 13 notification processing unit, 14, 14A, 14B sensitization magnification analogy processing unit.

Claims (2)

A current image storage unit for storing a current image from the electronic intensifying camera;
A background image storage unit for storing a background image for comparison based on an image from the electronic intensifying camera;
A background update unit that calculates image data of the background image storage unit according to a certain rule and updates a background image;
A background difference unit that compares two images of the current image storage unit and the background image storage unit to calculate a change area that is background difference data; and
A sensitization magnification analogy processing unit for informing and informing the sensitization magnification of the electronic sensitizing camera based on the change of the area of the change region or the number of labels ,
A feature amount calculation unit for calculating the feature amount based on the background difference data;
A report target feature amount storage unit that pre-stores a feature amount parameter of a report target;
A recognition processing cycle is determined in accordance with the notified sensitization magnification, and an event occurs by comparing the feature amount data calculated by the feature amount calculation unit with the feature amount parameter for each recognition processing cycle. A recognition processing unit for determining whether or not
A monitoring image processing apparatus comprising: an alarm processing unit that generates an event based on an event discovery notification from the recognition processing unit. A current image storage unit for storing a current image from the electronic intensifying camera;
A background image storage unit for storing a background image for comparison based on an image from the electronic intensifying camera;
A background update unit that calculates image data of the background image storage unit according to a certain rule and updates a background image;
A background difference unit that compares two images of the current image storage unit and the background image storage unit to calculate a change area that is background difference data; and
A sensitization magnification analogy processing unit for analogizing and notifying the sensitization magnification of the electronic sensitizing camera based on identification of characters or symbols superimposed on the image by the electronic sensitizing camera;
A feature amount calculation unit for calculating the feature amount based on the background difference data;
A report target feature amount storage unit that pre-stores a feature amount parameter of a report target;
A recognition processing cycle is determined in accordance with the notified sensitization magnification, and an event occurs by comparing the feature amount data calculated by the feature amount calculation unit with the feature amount parameter for each recognition processing cycle. A recognition processing unit for determining whether or not
A notification processing unit that issues a notification based on a notification of event discovery from the recognition processing unit;
Monitor image processing apparatus comprising the.

Images