JP7433193B2 - Suspicious behavior monitoring support system and suspicious behavior monitoring support method - Google Patents

Description

The present application relates to a suspicious behavior monitoring support system and a suspicious behavior monitoring support method.

There are a wide variety of targets to be monitored in plants and other facilities that handle confidential matters.For example, when visually monitoring images from more than 200 cameras, even if a suspicious person is detected by one camera, tracking is dependent on the skill of the supervisor. There was a possibility that suspicious persons could be overlooked. Therefore, a surveillance system has been proposed that automatically tracks suspicious persons by extracting moving objects from images captured by multiple cameras using image recognition technology (see, for example, Patent Document 1).

JP2006-146378A (Paragraphs 0047-0064, Figures 1, 3, 8, 14-21)

However, although the tracking load can be reduced, there are many false alarms among those notified as alarms. Therefore, when a plurality of warnings are notified at the same time, there is a possibility that the response to the warning that has a serious impact may be postponed.

This application discloses a technology to solve the above-mentioned problems, and it is possible to efficiently monitor suspicious behavior in a facility without postponing response to alarms that have a serious impact. The purpose of the present invention is to obtain a suspicious behavior monitoring support system and a suspicious behavior monitoring support method.

The suspicious behavior monitoring support system disclosed in this application is a system for analyzing data output from a suspicious behavior detection system that detects suspicious behavior within a facility based on video data from multiple cameras installed within the facility. An ID is assigned to each alert from the suspicious behavior detection system that the suspicious behavior has been detected, and the alert type output with the alert and the number of the camera used for the detection are assigned. a suspicious behavior data processing unit that generates detection information linking information and the ID; and a suspicious behavior data processing unit that associates the imaging range of each of the plurality of cameras in the facility with a false alarm rate calculated from the confirmation result by a supervisor. Analyzing the degree of influence of the alarm on the operation of the facility based on a database in which association data is stored, and the imaging range, the false alarm rate, and the alarm type extracted from the detection information and the association data. The present invention is characterized in that it comprises an alarm display management section that is provided with a degree analysis section and an alarm display section that displays the contents of the alarm corresponding to the alarm together with the analyzed influence degree.

The suspicious behavior monitoring support method disclosed in the present application is a method for analyzing data output from a suspicious behavior detection system that detects suspicious behavior in a facility based on video data from a plurality of cameras installed in the facility. An ID is assigned to each alert from the suspicious behavior detection system that the suspicious behavior has been detected, and the alert type output with the alert and the number of the camera used for the detection are assigned. a suspicious behavior data processing step of generating detection information linking the information and the ID, and associating the imaging range in the facility for each of the plurality of cameras with a false alarm rate calculated from the confirmation result by a supervisor. an influence analysis step of extracting the imaging range, the false alarm rate, and the alarm type information from the association data and the detection information, and analyzing the degree of influence of the alarm on the operation of the facility, and the alarm The present invention is characterized by comprising an alarm display step of displaying the content of the alarm according to the analyzed degree of influence.

According to the suspicious behavior monitoring support system or the suspicious behavior monitoring support method disclosed in the present application, the degree of impact of automatically detected suspicious behavior can be determined, so that responding to serious alarms can be postponed. This makes it possible to efficiently monitor suspicious behavior at the facility.

1 is a block diagram for explaining the overall configuration of a suspicious behavior monitoring support system according to a first embodiment; FIG. FIG. 2 is a block diagram for explaining the configuration of an alarm analysis processing section of the suspicious behavior monitoring support system according to the first embodiment. FIG. 3 is a diagram showing an example of a display screen in the suspicious behavior monitoring support system according to the first embodiment. 2 is a flowchart for explaining a suspicious behavior data processing step of the operation of the suspicious behavior monitoring support system or the suspicious behavior monitoring support method according to the first embodiment. 2 is a flowchart for explaining an alarm analysis processing step in the operation of the suspicious behavior monitoring support system or the suspicious behavior monitoring support method according to the first embodiment. 1 is a block diagram showing an example of a hardware configuration of a part that executes arithmetic processing of the suspicious behavior monitoring support system according to the first embodiment; FIG. FIG. 3 is a block diagram for explaining the configuration of an alarm analysis processing section of the suspicious behavior monitoring support system according to the second embodiment. 12 is a flowchart for explaining a processing order setting step in an alarm analysis processing step in the operation of the suspicious behavior monitoring support system or the suspicious behavior monitoring support method according to the second embodiment. FIG. 7 is a block diagram for explaining the configuration of an alarm analysis processing section of the suspicious behavior monitoring support system according to the third embodiment. 12 is a flowchart for explaining an alarm analysis processing step for high-frequency events among operations of the suspicious behavior monitoring support system or the suspicious behavior monitoring support method according to the third embodiment.

Embodiment 1.
1 to 5 are for explaining the suspicious behavior monitoring support system or the suspicious behavior monitoring support method according to the first embodiment, and FIG. 1 explains the basic overall configuration of the suspicious behavior monitoring support system. FIG. 2 is a block diagram for explaining the detailed configuration of the alarm analysis processing section. FIG. 3 is a diagram showing an example of a display screen when displaying the alarm history on the alarm screen. Further, FIG. 4 is a flowchart for explaining the suspicious behavior data processing step executed by the suspicious behavior data processing unit among the operations of the suspicious behavior monitoring support system or the suspicious behavior monitoring support method, and FIG. 5 is a flowchart for explaining the suspicious behavior data processing step executed by the suspicious behavior data processing unit. It is a flowchart for explaining the alarm analysis process to be executed.

A suspicious behavior monitoring support system and a suspicious behavior monitoring support method according to each embodiment of the present application will be described based on the drawings. As shown in FIG. 1, the suspicious behavior monitoring support system 1 detects the contents of alerts Ad regarding suspicious behavior detected by the suspicious behavior detection system 9 based on images from a plurality of cameras 8 installed in a facility (not shown). This is a system that supports facility monitoring activities by analyzing warning information and scrutinizing the contents of warnings.

The suspicious behavior monitoring support system 1 includes a suspicious behavior management unit 2 that manages the data of alerted Ads, generates and records the display contents on the monitoring screen 4m, and analyzes and records the content of alerted Ads and sends them to the alarm screen. and an alarm display management section 3 that executes generation of display contents.

The suspicious behavior management unit 2 includes an alarm Ad, a suspicious behavior data processing unit 21 that processes data regarding suspicious behavior received from the suspicious behavior detection system 9 in conjunction with the alert Ad, and a video management database that stores processed data. 22 (abbreviated as "DB" in the figure) is provided. Furthermore, a suspicious behavior display unit 23 that generates real-time display content on the monitoring screen 4m, and a detection history search/playback unit 24 that reads past data from the video management database 22 to be played back on the monitoring screen 4m from the detection history are provided. There is.

The suspicious behavior data processing unit 21 assigns a unique ID to the alert Ad that includes information such as the alert period, alert type, and target camera number received from the suspicious activity detection system 9, and performs detection linked to the ID. The information Isb is output to the alarm display management section 3 and the video management database 22. In the video management database 22, together with the detection information Isb, video data of the target camera 8 and data on the degree of influence on plant (facility) operation outputted from the alarm analysis processing section 31, which will be described later, are accumulated.

The suspicious behavior display unit 23 has a function of displaying the video data of the target camera accumulated since the alarm was issued on the monitoring screen 4m. The detection history search/playback section 24 has a function of searching and playing back videos of past warnings. It also has a function of searching for necessary data from the above-mentioned detection information Isb and degree of influence, displaying a list of relevant data, and reproducing the video associated with the selected ID.

In other words, the suspicious behavior management unit 2 outputs the detection information Isb for alarm analysis to the alarm display management unit 3, and links the video of the target camera in the detected area with the analysis result output from the alarm display management unit 3. , can be stored in the video management database 22.

The alarm display management section 3 is provided with an alarm analysis processing section 31 that analyzes the degree of influence of the detection information Isb on the plant, and an alarm management database 32 that accumulates analyzed data as an alarm history. Furthermore, an alarm display section 33 that generates real-time alarm content on the alarm screen 4a, and an alarm history search/display section 34 that reads past alarm history from the alarm management database 32 to be displayed on the alarm screen 4a from the alarm history are provided. ing.

The alarm analysis processing unit 31 receives the ID, alarm type, and target camera number as detection information Isb, and also receives information on the false alarm rate of the target camera stored in the alarm management database 32. The impact on plant operations is then analyzed from three points: alarm type, detection area, and false alarm rate of the detected camera. In addition, in response to an alarm, a surveillance officer will check the actual camera footage or go to the scene and check the results (whether it was a correct alarm, a false alarm, and if it is a false alarm, the correct cause) for each camera necessary for impact analysis. It has a function to calculate the false alarm rate and output it along with the confirmation results.

Therefore, as shown in FIG. 2, the alarm analysis processing unit 31 includes a data receiving unit 311 that receives data such as detection information Isb, and an impact analysis unit that analyzes the degree of impact on the plant from data such as detection information Isb. A section 312 is provided. Further, there are provided a false alarm rate calculation unit 313 that calculates the false alarm rate for each camera based on the confirmation results input by the monitor, and an impact update unit 314 that updates the impact level based on the calculated false alarm rate. It is being A transmission data generation section 315 that generates data for transmission from analyzed, calculated, and updated data, and a data transmission section 316 that transmits the generated data to a necessary part are provided.

Further, although not shown, the system is configured to have a function of changing the status of each alert Ad, such as whether it is in a suspicious behavior analysis state or whether confirmation has been completed. Furthermore, the relationship between each camera and the detection area (imaging range, monitoring target device, etc.) is configured to be obtained from a database such as the alarm management database 32 or the video management database 22.

Thereby, the alarm analysis processing unit 31 can analyze the degree of influence on plant operation from three points: information on the alarm type and detection area obtained from the detection information Isb, and information on the accumulated false alarm rate of the camera. Then, the false alarm rate can be calculated from the accumulated data and new confirmation results by the monitor, and the degree of impact can be updated together with the confirmation results. Then, for the alert Ad whose status has become confirmed, the ID, alert type, impact level, confirmation result, etc. can be linked and registered in the alarm management database 32 and video management database 22. .

When the status is in the suspicious behavior analysis state, the alarm display section 33 displays the results analyzed by the alarm analysis processing section 31 as an ID, alarm type, and impact level, and when the confirmation state is reached, the alarm display section 33 displays the results of the analysis by the alarm analysis processing section 31, and when the status is in the confirmation completion state, it combines the confirmation results by the monitor. to be displayed. The alarm history search/display unit 34 has a function of searching and displaying past alarms based on ID, alarm type, target camera number, degree of influence, etc. For the alarm screen 4a, as shown in FIG. 3, the display screen Si5 includes an ID column C1, an alarm period column C2, a target camera number column C3 (indicated as camera No. in the figure), an area column C4, The alarm type column C5, the influence degree column C6, the confirmation result column C7, etc. can be displayed in a list.

In other words, the alarm display management section 3 receives the detection information Isb from the suspicious behavior management section 2 in the alarm analysis processing section 31, returns the analyzed results together with data such as the false alarm rate, etc. to the suspicious behavior management section 2, and also It becomes possible to display the data on the alarm screen 4a.

The operation will be explained based on the above-described configuration. First, the operation of the suspicious behavior data processing unit 21 that receives the alarm Ad from the suspicious behavior detection system 9 will be described with reference to the flowchart in FIG. 4.

When the suspicious behavior data processing unit 21 receives the alert Ad outputted by the suspicious behavior detection system 9 to notify the detection of suspicious behavior ("Yes" in step S100), the alert type and the detected target area are Related data such as a camera number is received (step S110). It is assumed that the setting of the alarm type and the association between the area and the camera number have been made in advance. When the data is received, a unique ID is assigned to each alert Ad of detected suspicious behavior (step S120).

Subsequently, detection information Isb is generated in which data such as alarm type and camera number are linked to the assigned ID, and transmitted to the video management database 22 and the alarm analysis processing section 31 (step S130). The video management database 22 that has received the detection information Isb starts accumulating the video of the target camera number.

Further, the alarm analysis processing unit 31 starts analyzing the content of the alarm, such as analyzing the degree of influence on plant operation. Next, the analysis processing operation in the alarm analysis processing section 31 will be explained with reference to the flowchart of FIG. 5.

Information such as an ID, alarm type, and target camera number is received as detection information Isb from the suspicious behavior data processing unit 21 (step S200). Using the relationship data accumulated in the alarm management database 32, information on the detection area (imaging range) and false alarm rate corresponding to the target camera number obtained from the received detection information Isb is read. Then, the degree of influence on plant operation is analyzed from three points: information on the alarm type and detection area, and information on the false alarm rate of the camera (step S400).

The alarm type is classified according to the definition of suspicious behavior such as "wandering around," "trespassing into a prohibited area," or "device destruction," and the suspicious behavior detection system 9 automatically detects suspicious behavior. This is information that is identified and output along with the alert Ad.

In this example, for example, the alert level of suspicious behavior, detection area, and camera false alarm rate is set in three levels, and the integrated value of each is evaluated as the degree of influence on plant operation. When the monitoring target is a plant, a warning level may be set in advance for each detection area according to its importance to the plant, and added to the relevance data. Further, regarding the alarm type, the degree of influence on the plant is set in advance according to the type of classified suspicious behavior, and may be added to the relevance data.

Next, depending on the evaluated impact, if the impact is less than 5, level 1, if the impact is 5 or more and less than 10, level 2, and if the impact is 10 or more, level 3. are classified into three levels (step S500). In the case of level 1, a notification that the degree of influence is "small" is notified to the alarm display unit 33 (step S510), and in the case of level 2, a notification that the degree of influence is "medium" is displayed as an alarm. 33 (step S520), and in the case of level 3, a notification that the degree of influence is "high" is notified to the alarm display section 33 (step S530).

In addition to notification of the evaluated degree of impact, a status (white in status column C8 in FIG. 3) indicating that the system is in a suspicious behavior analysis state where on-site confirmation has not yet been performed is notified as an alarm state (step S540). . For example, the alarm display unit 33 allows a monitoring officer who has seen the displayed alarm contents to confirm whether the alarm was a correct alarm or a false alarm by checking the camera image or on-site confirmation, and inputs the confirmation result. There is a sign urging you to do so.

Therefore, for example, when a confirmation result is received from an input device such as a touch screen or a keyboard that constitutes the alarm screen 4a ("Yes" in step S550), the current correct/incorrect information is added to the past performance and the alarm is updated. The false alarm rate for the corresponding camera is recalculated (step S560). Then, based on the recalculated false alarm rate, the degree of influence is updated if necessary (step S570). Further, the status indicating that the process is in progress is changed to the status indicating that the on-site confirmation has been completed (step S580), and this is displayed (the status column C8 in FIG. 3 is filled in). Furthermore, the updated data such as the degree of influence and the false alarm rate are registered in databases such as the alarm management database 32 and the video management database 22 (step S590).

As a result, it is possible to notify the suspicious behavior detected by the suspicious behavior detection system 9 by adding information that analyzes the degree of influence, so you will not be distracted by trivial events and miss important events. This allows for efficient monitoring. Furthermore, since the false alarm rate and degree of influence are updated based on the results of confirmation by the monitor, it becomes possible to analyze the degree of influence in accordance with the actual situation.

In addition, in the suspicious behavior monitoring support system 1 that executes the above-described suspicious behavior monitoring support method, the part that performs calculation processing is implemented by one piece of hardware 10 including a processor 101 and a storage device 102, as shown in FIG. It is also possible to configure Although not shown, the storage device 102 includes a volatile storage device such as a random access memory and a nonvolatile auxiliary storage device such as a flash memory. Further, an auxiliary storage device such as a hard disk may be provided instead of the flash memory. Processor 101 executes a program input from storage device 102 . In this case, the program is input to the processor 101 from the auxiliary storage device via the volatile storage device. Furthermore, the processor 101 may output data such as calculation results to a volatile storage device of the storage device 102, or may store data in an auxiliary storage device via the volatile storage device. This also applies to the suspicious behavior monitoring support system 1 according to each of the subsequent embodiments.

Embodiment 2.
In the first embodiment, the presentation of the analyzed influence degree and the updating of data of the false alarm rate, which is an index of the influence degree, based on correct or incorrect results, have been described. In Embodiment 2, a configuration will be described in which a function is added to determine priorities and perform processing when multiple alarms are received at the same time. 7 and 8 are for explaining the suspicious behavior monitoring support system or the suspicious behavior monitoring support method according to the second embodiment, and FIG. 7 is a block diagram for explaining the detailed configuration of the alarm analysis processing section. 8 are flowcharts for explaining the alarm analysis processing step executed by the alarm analysis processing section. Note that the components other than the alarm analysis processing section and the alarm analysis processing step are the same as those in the first embodiment, and FIGS. 1, 3, and 4 used in the first embodiment will be referred to. Further, a part of FIG. 5 is also used in the alarm analysis processing step.

The suspicious behavior monitoring support system 1 in the second embodiment is the same as the suspicious behavior monitoring support system 1 described in the first embodiment by adding the following configuration to the alarm analysis processing section 31. Specifically, in contrast to FIG. 2 described in Embodiment 1, as shown in FIG. A processing order setting unit 318 has been added that sets the processing order for multiple alarms based on the results.

Next, the analysis processing operation in the alarm analysis processing section 31 will be explained with reference to the flowchart of FIG. 8. The steps from receiving the detection information Isb to impact analysis (steps S200 to S400) are the same as those described in the first embodiment. On the other hand, in the second embodiment, when a plurality of notification Ads are received at the same time ("Yes" in step S410), the processing order setting process from step S420 onward is executed, and then the processing order setting process described in the first embodiment is performed. The process moves to an analysis processing step (after step S500) according to the degree of influence. On the other hand, if the alert Ad is a single issue ("No" in step S410), the process directly proceeds to the analysis process (step S500 and subsequent steps) according to the degree of influence described in the first embodiment.

When the similar alarm confirmation unit 317 determines that multiple alert Ads have been received at the same time, it searches for an alarm similar to the detection information Isb for each alert Ad from the history information stored in the alarm management database 32 (step S420). . Then, for each issued Ad, the presence or absence of a similar alarm is checked (step S430). If there is no similar alarm in any of the alert Ads (“No” in step S440), the processing order setting unit 318 simply sets the processing order so that those with a large influence are processed preferentially (step S440). S460) Based on the set order, the processes from step S500 onward are performed for each alert Ad.

On the other hand, if there is a similar alarm among the issued Ads (“Yes” in step S440), the processing order setting unit 318 gives first priority to those that have not had false alarms in the past, and among them, A processing order is set so that the largest one is processed preferentially (step S450), and the processing from step S500 onward is performed for each alert Ad based on the set order.

As a result, when alerting Ads are received at the same time, it becomes possible to deal with the events that should be prioritized first. Note that the term "simultaneously" used here does not mean that there is no time difference that is less than the time resolution. For example, it refers to the time required for confirming the alarm content on the alarm screen 4a, or the time required for a supervisor to confirm at the scene, which is substantially simultaneous in the monitoring work.

Embodiment 3.
In the first and second embodiments described above, the presentation of the degree of influence and the setting of the priority order of processing according to the presence or absence of similar alarms have been described. In the third embodiment, a configuration will be described in which a function is added to analyze the frequency of received alarm events and set and display them as special events so that high-frequency events are not overlooked. 9 and 10 are for explaining the suspicious behavior monitoring support system or the suspicious behavior monitoring support method according to the third embodiment, and FIG. 9 is a block diagram for explaining the detailed configuration of the alarm analysis processing section. 10 are flowcharts for explaining the alarm analysis processing step executed by the alarm analysis processing section. Note that the components other than the alarm analysis processing section and the alarm analysis processing step are the same as those in the first or second embodiment, and FIGS. 1, 3, and 4 used in the first embodiment will be referred to. Further, a part of FIG. 5 is also used in the alarm analysis processing step.

The suspicious behavior monitoring support system 1 in the third embodiment is the same as the suspicious behavior monitoring support system 1 described in the first embodiment or the second embodiment, with the following configuration added to the alarm analysis processing section 31. . Specifically, in contrast to FIG. 2 described in Embodiment 1, as shown in FIG. A special event setting section 320 for setting an event as a special event that requires caution has been added.

Next, the analysis processing operation in the alarm analysis processing section 31 will be explained with reference to the flowchart of FIG. 10. The process of receiving the detection information Isb (step S200) is similar to the operation described in the first and second embodiments above. On the other hand, in the third embodiment, based on the detection information Isb received by the frequency analysis unit 319, based on the history information stored in the alarm management database 32, similar alarms occur at a certain frequency or more due to the same cause in a certain period of time. It is analyzed whether or not an alarm has been issued (step S300).

If an event similar to the detection information Isb does not occur frequently (“No” in step S310), the process from step S400 onwards is executed as in the first or second embodiment. On the other hand, if an event similar to the detection information Isb occurs frequently ("Yes" in step S310), the special event setting unit 320 sets the event as a special event regardless of the degree of impact (step S320). ). Then, information about the set special event is displayed (step S330), and the process ends.

Thereby, it is possible to notify the monitoring staff of suspiciously occurring consecutive events (alarms) without missing them. Furthermore, it becomes possible to make effective use of alarm history, which until now has only been accumulated and rarely utilized, and it becomes possible to prevent abnormalities that have not yet surfaced.

It should be noted that while this application describes various exemplary embodiments and examples, the various features, aspects, and functions described in one or more embodiments may differ from the specific embodiments. The present invention is not limited to application, but can be applied to the embodiments alone or in various combinations. Accordingly, countless variations not illustrated are envisioned within the scope of the technology disclosed herein. For example, this includes cases where at least one component is modified, added, or omitted, and cases where at least one component is extracted and combined with components of other embodiments.

For example, the addition of the frequency analysis section 319 and the special event setting section 320 described in the third embodiment may be combined with the addition of the similar alarm confirmation section 317 and the processing order setting section 318 described in the second embodiment. . In addition, regarding the influence of past alarm history, although we have given an example of reading from the database, this is not limited to this, but it can be calculated each time from the stored false alarm rate, detection area, and alarm type. You can.

As described above, according to the suspicious behavior monitoring support system 1 according to each embodiment, suspicious behavior detection detects suspicious behavior in a facility based on video data from a plurality of cameras 8 installed in the facility. An analysis system for data output from the system 9, which assigns an ID to each alert Ad that detects suspicious behavior from the suspicious behavior detection system 9, and assigns an ID to the alert type outputted with the alert Ad. The suspicious behavior data processing unit 21 generates detection information Isb that links information on the number of the camera used for the detection and the ID, based on the imaging range in the facility of each of the plurality of cameras and the confirmation results by the surveillance personnel. A database (e.g., video management database 22, alarm management database 32) that stores association data that associates the calculated false alarm rate with the imaging range, false alarm rate, and alarm type extracted from the detection information Isb and the association data. An alarm display includes an influence analysis section 312 that analyzes the influence of the issued Ad on the operation of the facility based on the above information, and an alarm display section 33 that displays the content of the alarm according to the issued Ad together with the analyzed influence. The system is configured to include a management section 3. Therefore, since the degree of influence of automatically detected suspicious behavior can be known, response to serious alarms is not postponed, and suspicious behavior in the facility can be efficiently monitored.

In particular, the alarm display management unit 3 includes a false alarm rate calculation unit 313 that calculates a false alarm rate based on the input of confirmation results by the monitor according to the display, and updates the degree of impact analyzed based on the calculated false alarm rate. If the configuration includes an impact update unit 314 that stores the false alarm rate in a database (e.g., video management database 22, alarm management database 32), the impact level and false alarm rate can be updated according to accumulated monitoring results. The reliability becomes higher and it becomes possible to analyze the degree of influence more accurately.

In addition, the alarm display management unit 3 includes a similar alarm confirmation unit 317 that checks whether there is a similar alert Ad in the past for each alert Ad when multiple alert Ads are received; If the configuration is provided with a processing order setting unit 318 that sets the processing order for each alarm based on the impact level and false alarm rate analyzed for the alarm Ad, it is possible to deal with events that require higher priority. It becomes possible to do so.

The alarm display management unit 3 includes a frequency analysis unit 319 that analyzes the frequency at which the same event as the alert is issued when an alert Ad is received, and a frequency analysis unit 319 that analyzes the frequency at which the same event as the alert is issued when an alert Ad is received, and a frequency analysis unit 319 that analyzes the frequency at which the same event as the alert is issued, and a frequency analysis unit 319 that analyzes the frequency at which the same event as the alert is issued when an alert Ad is received. A special event setting section 320 is provided for setting an event, and when the event of the received alarm Ad is an event set as a special event, the alarm display section 33 displays an event that is the same as the special event regardless of the degree of influence. By configuring the system to display alarms in association with each other, it is possible to notify monitors of suspicious events (alarms) that are occurring continuously, even if their impact is not rated high, without missing them. can.

Further, according to the suspicious behavior monitoring support method according to each embodiment, the suspicious behavior detection system 9 that detects suspicious behavior within the facility outputs the video data from the plurality of cameras 8 installed within the facility. This is a method of analyzing the data that has been sent, in which an ID is assigned to each alert Ad that suspicious behavior has been detected from the suspicious behavior detection system 9, and the alert type output with the alert Ad and the detection concerned are Suspicious behavior data processing step (steps S100 to S130) of generating detection information Isb linking the number information and ID of the camera used, the imaging range in the facility for each of the plurality of cameras, and the confirmation results by the surveillance personnel. Impact analysis that extracts information on the imaging range, false alarm rate, and alarm type from the detection information Isb and the association data that associates the false alarm rate calculated from , and analyzes the impact of the alarm Ad on the operation of the facility. step (step S400), and an alarm display step (steps S500 to S530, S540 to S580) for displaying the content of the alarm corresponding to the alert Ad together with the analyzed degree of influence. Therefore, since the degree of influence of automatically detected suspicious behavior can be known, response to serious alarms is not postponed, and suspicious behavior in the facility can be efficiently monitored.

1: Suspicious behavior monitoring support system, 2: Suspicious behavior management unit, 21: Suspicious behavior data processing unit, 22: Video management database (database), 23: Suspicious behavior display unit, 24: Detection history search/playback unit, 3: Alarm display management unit, 31: Alarm analysis processing unit, 312: Impact analysis unit, 313: False alarm rate calculation unit, 314: Impact update unit, 317: Similar alarm confirmation unit, 318: Processing order setting unit, 319: Frequency Analysis section, 320: Special event setting section, 32: Alarm management database (database), 33: Alarm display section, 34: Alarm history search/display section, 8: Camera, 9: Suspicious behavior detection system, Ad: Alarm, Isb: Detection information.

Claims (5)

A system that provides monitoring support based on information from a suspicious behavior detection system that detects suspicious behavior within the facility based on video data from a plurality of cameras installed within the facility,
An ID is assigned to each alert from the suspicious behavior detection system that the suspicious activity has been detected, and information on the alert type output with the alert, the number of the camera used for the detection, and the ID. a suspicious behavior data processing unit that generates detection information linked to
a database storing association data that associates the imaging range in the facility for each of the plurality of cameras with a false alarm rate calculated from a confirmation result by a supervisor; an impact analysis unit that analyzes the impact of the alarm on the operation of the facility based on the imaging range, the false alarm rate, and the alarm type; and an impact analysis unit that analyzes the impact of the alarm on the operation of the facility, and the analyzed impact of the warning content in response to the alarm. an alarm display management section provided with an alarm display section for displaying;
A suspicious behavior monitoring support system comprising: The alarm display management section includes:
a false alarm rate calculation unit that calculates the false alarm rate based on input of the confirmation result by the monitor according to the display;
The suspicious behavior monitoring support system according to claim 1, further comprising: an impact update unit that updates the analyzed impact based on the calculated false alarm rate and stores it in the database together with the false alarm rate. . The alarm display management section includes:
a similar alarm confirmation unit that, when receiving multiple alarms, checks whether there have been similar alarms in the past for each alarm;
A processing order setting unit is provided that sets a processing order for each of the alerts based on the influence degree and false alarm rate analyzed for the confirmed past similar alerts. The suspicious behavior monitoring support system according to 1 or 2. The alarm display management section includes:
a frequency analysis unit that analyzes the frequency with which the same event as the alert is issued when an alert is received;
A special event setting unit is provided for setting an event whose frequency exceeds a standard in a certain period as a special event,
The alarm display section is characterized in that, when the received alarm event is an event set as the special event, the alarm display unit displays the alarm of the same event in association with the special event, regardless of the degree of impact. The suspicious behavior monitoring support system according to any one of claims 1 to 3. A method for providing monitoring support based on information from a suspicious behavior detection system that detects suspicious behavior in the facility based on video data from a plurality of cameras installed in the facility, the method comprising:
An ID is assigned to each alert from the suspicious behavior detection system that the suspicious activity has been detected, and information on the alert type output with the alert, the number of the camera used for the detection, and the ID. a suspicious behavior data processing step for generating detection information associated with the
Association data that associates the imaging range in the facility for each of the plurality of cameras with a false alarm rate calculated from a confirmation result by a supervisor, and the imaging range, the false alarm rate, and the alarm type based on the detection information. an impact analysis step of extracting information on the information and analyzing the impact of the warning on the operation of the facility; and an alarm display step of displaying the content of the warning in response to the warning together with the analyzed impact.
A suspicious behavior monitoring support method comprising:

Images