JP7033797B2 - How to adjust the video monitoring device and the video monitoring device - Google Patents

Description

The present invention relates to an adjustment method of a video monitoring device capable of mechanically detecting an error in video or audio contained in a digital video signal, and a video monitoring device.

In the old analog television broadcasting era, the quality of the video and audio was such that the observer actually watched (monitored) the video and audio to detect the error. On the other hand, in the present age when digital television broadcasting has been shifted, the processing of video signals has become easier and the environment for mechanically monitoring video and audio is being prepared, and some of them have already been mechanically monitored. On the other hand, there is an evaluation that machine monitoring is still inferior to human monitoring in the accuracy of error detection, and there is a fact that monitoring by conventional observers is also performed in parallel.

However, in the future, in addition to the terrestrial business that transmits digital video, it is expected that video distribution services such as content online distribution business and IPTV (Internet Protocol Tele Vision) business will expand, and it will be distributed accordingly. Since the number of contents will increase dramatically, it is considered that it will be practically difficult for the observer to monitor all the contents. Therefore, improving the accuracy of error detection in machine monitoring to the same level as humans is an urgent issue for all video distribution services.

Patent Document 1 discloses an audio inspection method for detecting an image error caused by noise generated by various causes in a digital video signal and an audio error caused by noise generated by various causes in a digital audio signal. Has been done.

International Publication 2015/059782

According to Patent Document 1, a continuous digital audio signal is sampled by dividing it into 5 msec or less, a high frequency component is extracted from the sampled signal, and a value based on the extracted high frequency component is compared with a threshold value to obtain audio. The error that has occurred can be detected mechanically.

However, in a technique such as Patent Document 1, error detection is performed by comparing a characteristic value (parameter) of an audio signal with a threshold value, but there is a problem of how to set the threshold value. That is, if the threshold value is set tightly, error detection is frequently performed, but if many of the detected errors are negligible to the viewer, the detection may be wasted. On the other hand, if the threshold value is set loosely, the frequency of error detection decreases, but there is a risk that an error that cannot be ignored by the viewer will be overlooked. This is one of the reasons why machine monitoring is inferior to human monitoring. Changing one parameter affects the other parameters, especially when there are multiple parameters that are related to each other, so two or more parameters must be changed at the same time, and an appropriate threshold is set. Is very difficult.

One of an object of the present invention is to provide a method for adjusting a video monitoring device that appropriately detects a video and / or an error generated according to a content in a digital video signal.

Another object of the present invention is to provide a video monitoring device that appropriately detects video and / or errors in digital video signals through learning.

The first method for adjusting the video monitoring device of the present invention is a video monitoring device for detecting that an error has occurred in a monitoring item by inputting a video signal corresponding to the video and / or audio to be monitored. In the adjustment method
The video monitoring device is adapted to determine that the error has occurred when all of the parameters for each monitoring item exceed the threshold values determined according to the monitoring item, and for each monitoring item . At least two of the parameters of are interrelated,
Determine the threshold values of the parameters for each monitoring item , create a plurality of sets of threshold values, store them in the memory, and store them in the memory.
It is characterized in that any set of the threshold group stored in the memory is selected according to the video and / or audio content to be monitored.

As a result of diligent research, the present inventor has determined that the appropriate value of the threshold group is the content of the video and / or audio content to be monitored ("movie", "drama", "variety", "sports", "documentary"". , "Entertainment", "Anime", etc.). Based on this discovery, the present invention was derived. That is, if the threshold values of the plurality of parameters are determined, a plurality of sets of the threshold values are created, and stored in the memory, the threshold values are stored in the memory according to the video and / or audio contents to be monitored. By selecting any set of the threshold group, it is possible to set a threshold group more appropriate for monitoring as compared with the case of using a single threshold group, so that false detection of an error in the video monitoring device is effective. It can be prevented.

Further, the video monitoring device is designed to issue an alarm when an error is detected.
In the learning parallel to the video and / or audio monitoring operation, the above-mentioned error in which an alarm should be issued at regular time intervals by inputting a video signal corresponding to the video and / or audio to be monitored. The number of the first event in which the alarm was issued and the number of the second event in which the alarm was issued for the error for which the alarm should not be issued are counted, respectively.
Further, the number of third events in which the alarm is not issued for the error in which the alarm should be issued by inputting the video signal for inspection whose content and location of the error are known to the video monitoring device. Count and
An evaluation value is obtained by weighting the obtained number of the first event, the number of the second event, and the number of the third event, and the threshold group is based on the obtained evaluation value. It is preferable to update.

In the learning, it is preferable to count the number of the first event, the number of the second event, and the number of the third event while individually changing the threshold value of the threshold group.

The second video monitoring device of the present invention is a video monitoring device that detects that an error has occurred in a monitoring item by inputting a video signal corresponding to the video and / or audio to be monitored.
A threshold storage unit that stores a threshold value of a parameter in which at least two of the parameters for each monitoring item are related to each other, and a threshold storage unit.
A determination unit that determines that an error has occurred and issues an alarm when all of the parameters for each monitoring item exceed the threshold value determined according to the monitoring item.
A learning unit that learns in parallel with video and / or audio monitoring operations,
An update unit that updates the threshold value based on the learning result in the learning unit, and an update unit.
When the determination unit detects the occurrence of the error, it has a video storage unit that stores video signals before and after the error occurs.
By analyzing the alarm result of the error, the learning unit learns and
When the learning unit inputs a video signal corresponding to the video and / or audio to be monitored, the alarm is issued for an error for which an alarm should be issued at regular time intervals. The number of events and the number of second events for which the alarm was issued for an error for which the alarm should not be issued are counted, and a video signal for inspection in which the content and location of the error are known is displayed. When input, the number of the third event in which the alarm was not issued is counted for the error for which the alarm should be issued, and the number of the obtained first event and the number of the second event are counted. The evaluation value is obtained by weighting the number of the third event and the calculation, and the threshold group is updated based on the obtained evaluation value .

According to the present invention, by analyzing the alarm result of the error and classifying it into, for example, "correct answer alarm", "unnecessary alarm", "passing through", etc., the learning unit learns and the threshold value is more appropriate. Since it can be updated to a value that is high, the accuracy of error detection is improved.

Further, it is preferable that the learning unit counts the number of the first event, the number of the second event, and the number of the third event while individually changing the threshold value of the monitoring item.

但し、
Ｗｔ（ｍ）は前記第１事象の重み付け
Ｗｆ（ｍ）は前記第２事象の重み付け
Ｗｈ（ｍ）は前記第３事象の重み付けFurther, the learning unit is the first in which the alarm is issued for an error for which an alarm should be issued between the times t1 and t2 for the mth video signal among the M video signals. The number of events is T (m), the number of second events for which the alarm is issued is F (m) for an error for which an alarm should not be issued, and the alarm should be issued for an error. When the number of the third event in which the alarm is not issued is H (m), it is preferable to obtain the evaluation value A (m) according to the following evaluation function.

However,
Wt (m) is the weighting of the first event Wf (m) is the weighting of the second event Wh (m) is the weighting of the third event.

Further, it is preferable that the video storage unit cuts out and stores the input video signal at a predetermined timing and at a predetermined length.

Further, it is preferable to have a display unit that displays the learning result of the learning unit and reproduces video and / or audio based on the video signals before and after the occurrence of the error.

In the present specification, "voice" includes not only human and animal voices but also sounds. The "video signal" includes the case of either a video signal or an audio signal. "Content" is the content of the video. Specifically, there are major categories of content such as "movie", "drama", "variety", "sports", "documentary", "entertainment", and "animation". On the other hand, as a sub-category of contents, taking "sports" as an example, there are "baseball", "soccer", "volleyball", "judo", "sumo", "athletics" and the like. "Learning" associates the monitoring result of the viewer watching the video and / or audio flowing in real time with the result of monitoring the video signal corresponding to the same video and / or audio with the video monitoring device, and uses it as a threshold value. Includes feedback. "Interrelated" means that adjusting one parameter affects the other. "Exceeding a threshold" includes both cases of exceeding the threshold and falling below the threshold.

INDUSTRIAL APPLICABILITY According to the present invention, it is possible to provide a method for adjusting a video monitoring device that appropriately detects a video and / or an error generated according to a content in a digital video signal. Further, according to the present invention, it is possible to provide a video monitoring device that appropriately detects a video and / or an error through learning in a digital video signal.

It is a block diagram which shows the image monitoring apparatus 100. It is a figure which shows the example of the inspection item in the video / audio monitoring unit 103 displayed on the display unit 107. It is a figure which shows the example of the alarm information displayed on the display part 107. It is a figure which shows the example of the parameter for each monitoring item displayed on the display part 107. It is a figure which shows the example which summarized the correct answer alarm, unnecessary alarm, and slip-through which occurred when error detection was performed using the same threshold value for each monitoring item and content. It is a figure which shows the list of the example ((a) before update, (b) after update) of a plurality of groups of threshold values when such an update is performed a plurality of times in the inspection item freeze concerning a certain content.

The image monitoring device and the adjustment method thereof according to the present embodiment will be described with reference to the drawings. FIG. 1 is a block diagram showing a video monitoring device 100. In FIG. 1, the video monitoring device 100 inputs a video signal for inspection and a main input unit 101 for inputting a video signal corresponding to video and / or audio to be monitored (hereinafter referred to as an inspection target video signal). A sub-input unit 102, a video / audio monitoring unit (determination unit) 103 having a built-in memory for storing a threshold, a video / audio clip storage unit (video storage unit) 104, an alarm output unit 105, and a built-in memory (threshold). A learning unit (learning unit / updating unit) 106 for parameter optimization including a storage unit) 106a, a display unit 107 such as a display capable of visually recognizing the information displayed by the observer MN, and an observer MN can input information. It has a monitor input unit 108 such as a keyboard.

The monitoring operation of the video monitoring device 100 will be described. FIG. 2 is a diagram showing an example of inspection items in the video / audio monitoring unit 103 displayed on the display unit 107. The video signals to be monitored include video signals in all formats such as SDI signals, files, IP formats, and HDMI (registered trademark). While looking at the monitoring items displayed on the display unit 107, the observer MN changes the inside of the box corresponding to each monitoring item via the observer input unit 108, and “inspects” or “off” for each monitoring item. You can choose either. The inspection item for which the observer has selected "inspection" will be monitored by the video monitoring device 100, but the inspection item for which "off" has been selected will not be monitored.

Monitoring items related to video include "freeze", "blackout", "block freeze", "block blackout", "block noise", "blinking red", "blinking brightness", "scene change", and "video inversion". , "Line noise", "Abnormal cut point", "Time code discontinuity". On the other hand, the monitoring items related to voice include "mute", "cutoff mute", "audio pop noise", "skipping", "voice noise", "loudness", and "true peak". The inspection items are not limited to these.

As a premise of the monitoring operation, it is assumed that a plurality of threshold values (threshold values, details described later) are set in the video / audio monitoring unit 103 for each monitoring item. With reference to FIG. 1, when the video monitoring device 100 inputs an inspection target video signal from the main input unit 101, an image frame, pixel data, and audio sampling data are extracted from the input inspection target video signal, and the video is obtained. -It is transmitted to the voice monitoring unit 103, and parameters corresponding to various sensitivity adjustments, durations, etc. that can be applied to the monitoring algorithm are calculated here.

The video / audio monitoring unit 103 compares a plurality of obtained parameters with the threshold values corresponding to the monitoring items according to the monitoring algorithm, and detects an error corresponding to the monitoring item when all the parameters exceed the threshold values. The determination is made, and the alarm signal associated with the monitoring item is output to the alarm output unit 105. Since the alarm output unit 105 inputs alarm information including the error occurrence time, the content of the detected error, and the severity thereof to the display unit 107 according to the input alarm signal, the display unit 107 inputs the alarm information. It can be displayed and visually recognized by the observer MN. Further, the video / audio monitoring unit 103 cuts out the video signals before and after the parameter exceeds the threshold value and stores them in the video / audio clip storage unit 104.

FIG. 3 is a diagram showing an example of alarm information displayed on the display unit 107. In FIG. 3, the detected errors and contents are displayed in chronological order in the lower part of the screen, and the upper part of the screen shows the "category" indicating that the error is video or audio, and the error level is normal or serious. The "class" to indicate, the "inspection item" to indicate the type of error, and the "number of occurrences" of the error are collectively displayed. When the observer MN selects one of the errors via the observer input unit 108, the video / audio clip storage unit 104 reads out the video signals before and after the corresponding error and displays them on the display unit 107. Entered. As a result, the video and / or audio before and after the error is output from the display unit 107, so that the observer MN can actually see or hear the content of the error.

By the way, when the monitor MN compares the content of the detection error displayed on the display unit 107 with the actual video and / or audio, and the alarm is issued for the error to be issued (correct answer). When an alarm is issued for an error that should not be issued (called an alarm), and when an alarm is not issued for an error that should be issued (pass through). ) And can be recognized respectively. Ideally, all the alarms issued by the video monitoring device 100 when an error is detected are correct alarms, but in reality, unnecessary alarms and omissions occur. This is because the error detection standard by the machine monitoring of the video / audio monitoring unit 103 does not exactly match the error detection standard by the monitoring of the observer MN. Therefore, unless the error detection by machine monitoring is close to the error detection by human monitoring, it is difficult to monitor the image monitoring device 100 alone.

Therefore, in order to bring the error detection standard by the machine monitoring of the video / audio monitoring unit 103 closer to the error detection standard by the monitoring of the monitor MN, the threshold value of the parameter set for each monitoring item is changed. This is called threshold tuning. Here, when there are m monitoring items and the number of the parameters is I (m), the number of threshold values to be tuned is 1 · I (1) + 2 · I (2) + ... + m ·. It becomes I (m), and it can be seen that it increases as the number of monitoring items increases.

FIG. 4 is a diagram showing an example of parameters for each monitoring item displayed on the display unit 107. The observer MN can input an arbitrary value for each parameter in the box corresponding to the parameter via the observer input unit 108 while looking at the parameter displayed on the display unit 107. There is.

As an example, there are four parameters, "sensitivity threshold (activity)", "sensitivity threshold (noise)", "time threshold (start)", and "time threshold (end)", corresponding to the inspection item "freeze". There is one. The "graph scale" represents the scale of the graph for display and is not a parameter here. That is, in order to detect the video freeze as an error, the threshold values (threshold value group) of the four parameters must be set appropriately. However, the "sensitivity threshold value (activity)" and the "sensitivity threshold value (noise)" are the upper limit value and the lower limit value of the values dispersed for each small block included in one frame of the video as parameters, and are related to each other. It can be said that it matches. Such parameters are disclosed in detail in WO 2015-059782. Further, the "time threshold value (start)" and the "time threshold value (end)" indicate the length of the period in which the video is determined to be a phrase, and are related to each other. Therefore, when one of the thresholds is adjusted, the freeze cannot be detected properly unless the other threshold is also changed.

Here, if appropriate threshold values are not input for all inspection items, unnecessary alarms and omissions will occur when an error is detected. However, if the number of inspection items is large as shown in FIG. 4, all inspection items It is difficult to determine an appropriate threshold value for. Therefore, it is desirable to determine the default threshold value (initial value) in advance. Such a default threshold value can be stored and used in, for example, the built-in memory of the video / audio monitoring unit 103. However, according to the results of the study by the present inventor, when the same threshold value is used for all contents, unnecessary alarms and omissions are reduced in some contents, but unnecessary alarms and omissions occur in other contents. I understood.

FIG. 5 is a diagram showing an example in which correct alarms, unnecessary alarms, and slip-throughs that occur when an error is detected using the same threshold value are summarized for each monitoring item and content. From the example of FIG. 5, it can be seen that the frequency of occurrence of correct alarms, unnecessary alarms, and slip-throughs differs depending on the content. Based on the results of this study, the present inventor has found that the default threshold value may be determined according to the content of the content. Such default thresholds can be determined from simulations and accumulated experience.

On the other hand, if the default threshold value is determined according to the content, there is a possibility that unnecessary alarms and skipping can be reduced to some extent, but it is not always optimal. Even if the content is the same, the frequency of unnecessary alarms and passing through may change depending on the reception status and the like. Therefore, it is preferable to let the video monitoring device 100 learn about the currently input video signal in parallel with the monitoring operation to determine whether the default threshold value is appropriate and to update it further if it is not appropriate. I can say. This makes it possible to increase the number of correct alarms and reduce the frequency of unnecessary alarms and passing through. The updated threshold value can be newly set as the default threshold value of the content.

(Learning mode)
Hereinafter, the learning function of the video monitoring device 100 will be described. In the following learning example, it can be determined which is superior to the default threshold value when there is a threshold value candidate to be changed. In the image monitoring device 100 of FIG. 1, the observer MN sets a predetermined learning period from the observer input unit 108 while actually performing the video and / or audio monitoring operation. Then, the video monitoring device 100 can perform learning during this learning period.

Specifically, in M video signals of the same type of content, a monitoring operation is performed using a default threshold value for one monitoring item. First, during the learning period (time t1 to t2, for example, time units such as time, day, week, month, etc.), the error detected by the video monitoring device 100 is displayed on the display unit 107 as shown in FIG. .. Since the errors displayed as shown in FIG. 3 may include inappropriate ones, it is necessary to check the suitability of the errors for learning.

Here, the observer MN reads out the video signals before and after the error stored in the video / audio clip storage unit 104 by designating any of the errors displayed in FIG. 3 with one click, and responds to the error. The video and / or audio can be viewed on the display unit 107. As a result, the observer MN can count the number of correct alarms and the number of unnecessary alarms that occurred between the times t1 and t2. The video signals before and after each error stored in the video / audio clip storage unit 104 are about 3 seconds in length, so it does not take long to watch, and this check is completed in a short time. The burden is small.

However, the above-mentioned check cannot count the number of slip-through cases. Therefore, a video signal for inspection, which is prepared in advance and whose error content and occurrence location (time) are known, is input to the video / audio monitoring unit 103 via the sub-input unit 102, and has the same threshold value as described above. The video / audio monitoring unit 103 detects an error using the above. When the alarm information similar to that shown in FIG. 3 is obtained as a result, the observer MN obtains the number of correct alarms and the number of slip-throughs by collating the contents of known errors with the locations where they occur. be able to. Here, the number of slip-through cases is extracted and used. Since the video signal for inspection has a length corresponding to a viewing time of about several tens of minutes for each content, the inspection is not troublesome. The observer MN learns from the observer input unit 108 the number of correct alarms, the number of unnecessary alarms, and the number of slip-throughs obtained for each of the M video signals as described above for parameter optimization. Input to unit 106.

但し、
Ｗｔ（ｍ）は正解アラームの重み付け
Ｗｆ（ｍ）は不要アラームの重み付け
Ｗｈ（ｍ）はすり抜けの重み付けHere, the number of correct alarms (first event) in the m-th video signal is T (m), the number of unnecessary alarms (second event) is F (m), and the number of slip-throughs (third event) is Assuming H (m), the parameter optimization learning unit 106 obtains the evaluation value A (m) according to the following evaluation function.

However,
Wt (m) is correct alarm weighting Wf (m) is unnecessary alarm weighting Wh (m) is weighting for slip-through

In error detection, it is generally preferable that the number of correct alarms is large, the number of unnecessary alarms is small, and it is preferable to eliminate slip-through as much as possible. Therefore, it is preferable to set Wt (m)> 0> Wf (m)> Wh (m) as the weighting stored in the memory 106a. For example, Wt (m) = + 3 and Wf (m) = -1. And Wh (m) = -5. However, the weighting may be fixed for the same type of content. According to this evaluation function, the higher the obtained evaluation value A (m) is, the more accurate the error detection is, and the lower the value is, the more inaccurate the error detection is.

Next, the observer MN replaces the default threshold value with the threshold value desired to be changed via the observer input unit 108, and executes the same monitoring operation as described above using the video signal of the same content. To find the evaluation value. If the evaluation value of the monitoring operation using the default threshold value is equal to or higher than the evaluation value of the monitoring operation using the threshold value desired to be changed, the parameter optimization learning unit 106 continues to use the default threshold value in the content. As a matter of fact, it does not change the stored default threshold. On the other hand, if the evaluation value of the monitoring operation using the default threshold value is lower than the evaluation value of the monitoring operation using the threshold value desired to be changed, the parameter optimization learning unit 106 has the default threshold value in the content. Judging that it is necessary to change, replace it with the threshold value that you want to change, that is, perform learning. This makes it possible to further improve the accuracy of error detection.

FIG. 6 is a diagram showing a list of examples ((a) before update, (b) after update) of a plurality of groups of threshold values when such an update is performed a plurality of times in an inspection item related to a certain content: freeze. .. A plurality of sets of threshold values shown in FIG. 6 are listed and stored in the built-in memory 106a, displayed on the display unit 107 as needed, and can be confirmed by the observer MN.

According to the pre-update list of FIG. 6A, the default threshold group is currently listed at the highest priority as priority 1, but the evaluation value A (m) is “85”. On the other hand, the evaluation value A (m) of the threshold group newly evaluated as the first candidate is "92", and the evaluation value A (m) of the threshold group newly evaluated as the second candidate is "81". Suppose there was.

In such a case, the evaluation value A (m)-"92" of the first candidate threshold group is higher than the evaluation value A (m) "85" of the default threshold group so far, so that the parameter optimization learning unit 106 However, as shown in FIG. 6B, it is replaced with a new default threshold group by setting the priority to 1 by updating, and is transmitted to the video / audio monitoring unit 103 for monitoring. As a result, the default threshold group up to now is moved down to priority 2.

On the other hand, since the evaluation value A (m) "81" of the second candidate threshold group is lower than the evaluation value A (m) "85" of the replaced default threshold group, the parameter optimization learning unit 106 However, by updating to priority 3, it will be listed at a lower level. Such a list is stored and used in the memory 106a of the parameter optimization learning unit 106. As a result, the threshold group having a high evaluation value A (m) can be set as the default threshold group for the content. However, if the contents are different, the priority may be different even if the threshold group uses the same value. It should be noted that such an update of the threshold group may be performed automatically by the parameter optimization learning unit 106, or may be performed after waiting for the permission of the observer MN. Alternatively, regardless of the value of the evaluation value A (m), the threshold value specified by the monitor MN via the monitor input unit 108 may be set as the default threshold value.

As for how to determine the first candidate, the second candidate, ..., The observer MN inputs an arbitrary value from the observer input unit 108 to the parameter optimization learning unit 106, and the answer is correct each time. The evaluation value may be calculated after obtaining the number of alarms, the number of unnecessary alarms, and the number of slip-throughs. Alternatively, the parameter optimization learning unit 106 individually changes the threshold value by + 5% or -5% with respect to the default threshold value group, and each time, the number of correct alarms and the number of unnecessary alarms are passed through. After obtaining the number of, the evaluation value may be calculated. Evaluation values can be obtained for other monitoring items in the same way.

The video signal for inspection can be input between the inputs of the video signal to be monitored, or can be performed in parallel with the input of the video signal to be monitored to perform the inspection in the background. This allows error detection to be performed using the same threshold. Further, the video / audio storage clip unit 104 cuts the monitored video signal input from the main input unit 101 at a predetermined timing over a predetermined length, and associates it with the monitoring result performed by the monitor MN. , May be stored as an inspection video signal in a memory (not shown). The stored inspection video signal is input from the sub-input unit 102 at a required timing and is used for threshold value update as described above.

INDUSTRIAL APPLICABILITY According to the present invention, it is possible to provide an adjustment method of a video monitoring device that appropriately detects a video and / or an error generated according to a content in a digital video signal, and appropriately video and / or an error through learning in the digital video signal. It is possible to provide a video monitoring device that detects.

100 Video monitoring device 101 Main input unit 102 Sub input unit 103 Video / audio monitoring unit 104 Video / audio clip storage unit 105 Alarm output unit 106 Parameter optimization learning unit 106a Built-in memory 107 Display unit 108 Monitorer input unit MN Monitorer

Claims (8)

In the adjustment method of the video monitoring device that detects the occurrence of an error for the monitoring item by inputting the video signal corresponding to the video and / or audio to be monitored.
The video monitoring device is adapted to determine that the error has occurred when all of the parameters for each monitoring item exceed the threshold values determined according to the monitoring item, and for each monitoring item . At least two of the parameters of are interrelated,
Determine the threshold values of the parameters for each monitoring item , create a plurality of sets of threshold values, store them in the memory, and store them in the memory.
A method for adjusting a video monitoring device, which comprises selecting any set of the threshold values stored in the memory according to the video and / or audio content to be monitored. The video monitoring device is designed to issue an alarm when an error is detected.
In the learning parallel to the video and / or audio monitoring operation, the above-mentioned error in which an alarm should be issued at regular time intervals by inputting a video signal corresponding to the video and / or audio to be monitored. The number of the first event in which the alarm was issued and the number of the second event in which the alarm was issued for the error for which the alarm should not be issued are counted, respectively.
Further, the number of third events in which the alarm is not issued for the error in which the alarm should be issued by inputting the video signal for inspection whose content and location of the error are known to the video monitoring device. Count and
An evaluation value is obtained by weighting the obtained number of the first event, the number of the second event, and the number of the third event, and the threshold group is based on the obtained evaluation value. The method for adjusting a video monitoring device according to claim 1 , wherein the image monitoring device is updated. The second aspect of the present invention is characterized in that, in the learning, the number of the first event, the number of the second event, and the number of the third event are counted while individually changing the threshold value of the threshold group. The method of adjusting the video monitoring device described. In a video monitoring device that detects that an error has occurred for a monitoring item by inputting a video signal corresponding to the video and / or audio to be monitored.
A threshold storage unit that stores a threshold value of a parameter in which at least two of the parameters for each monitoring item are related to each other, and a threshold storage unit.
A determination unit that determines that an error has occurred and issues an alarm when all of the parameters for each monitoring item exceed the threshold value determined according to the monitoring item.
A learning unit that learns in parallel with video and / or audio monitoring operations,
An update unit that updates the threshold value based on the learning result in the learning unit, and an update unit.
When the determination unit detects the occurrence of the error, it has a video storage unit that stores video signals before and after the error occurs.
By analyzing the alarm result of the error, the learning unit learns and
When the learning unit inputs a video signal corresponding to the video and / or audio to be monitored, the alarm is issued for an error that should be issued at a fixed time interval. The number of events and the number of second events for which the alarm was issued for an error for which the alarm should not be issued are counted, and a video signal for inspection in which the content and location of the error are known is displayed. When input, the number of the third event in which the alarm was not issued is counted for the error for which the alarm should be issued, and the number of the obtained first event and the number of the second event are counted. , A video monitoring device characterized in that an evaluation value is obtained by weighting the number of the third event and the calculation is performed, and the threshold value is updated based on the obtained evaluation value. 4. The learning unit is characterized in that it counts the number of the first event, the number of the second event, and the number of the third event while individually changing the threshold value of the monitoring item. The video monitoring device described in. The learning unit is the first event in which the alarm is issued for an error for which an alarm should be issued between times t1 and t2 for the m-th video signal among the M video signals. The number of cases is T (m), the number of second events in which the alarm is issued for an error for which an alarm should not be issued is F (m), and the alarm is for an error for which an alarm should be issued. The video monitoring device according to claim 5 , wherein the evaluation value A (m) is obtained according to the following evaluation function, where H (m) is the number of third events for which is not issued.
However,

Wt (m) is the weighting of the first event Wf (m) is the weighting of the second event Wh (m) is the weighting of the third event. The video monitoring device according to any one of claims 4 to 6 , wherein the video storage unit cuts out and stores an input video signal at a predetermined timing and a predetermined length. The invention according to any one of claims 4 to 7 , further comprising a display unit that displays the learning result of the learning unit and reproduces video and / or audio based on the video signals before and after the occurrence of the error. Video monitoring device.

Images