Monitoring support system, method and program

Abstract

To provide a monitoring support system that detects a moving object that has entered an area to be monitored, and performs monitoring response processing suitable for the moving object when the moving object is a target for a warning. The system analyzes the image capture results of a camera installed in a specified monitoring area to identify the type and behavior of a moving object captured by the camera. Based on the identified type and behavior of the moving object, it determines whether the object's behavior satisfies a monitoring response condition. If it is determined that the monitoring response condition is met, a predetermined monitoring response process is executed on the moving object.

Description

[Technical Field]

[0001] The present invention relates to a surveillance support system, method, and program that acquires video of a specified surveillance area, recognizes moving objects present in the acquired video of the surveillance area, and performs alarm and avoidance processing when a pre-registered moving object is recognized. [Background technology]

[0002] 2. Description of the Related Art Conventionally, surveillance devices that recognize people and vehicles by image have been used to monitor illegal fishing and poaching. For example, as shown in Patent Document 1, a surveillance device acquires images of the object to be monitored using a camera attached to an aircraft such as a drone, performs image recognition of people and vehicles in the acquired images, and uses the image information to measure the status of the surveillance area. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2017-152964 Summary of the Invention [Problem to be solved by the invention]

[0004] However, although the above-mentioned conventional monitoring devices can detect suspicious moving objects, they cannot eliminate inappropriate behavior of the moving objects.

[0005] In order to solve such problems, the present invention aims to provide a surveillance support system, method and program that detects moving objects that have entered a monitored area and, if the moving object is subject to a warning, performs appropriate warning and avoidance processing for the moving object. [Means for solving the problem]

[0006] The present invention is a surveillance support system in which a computer executes the following steps: a first step of analyzing the image capture results of a camera installed in a specified surveillance area and identifying the type of moving object and its movement captured by the camera; a second step of determining whether the movement of the moving object satisfies specified surveillance response conditions based on the identified type and movement of the moving object; and a third step of executing a surveillance response process on the moving object to prevent the moving object from entering the surveillance area, if it is determined in the second step that the surveillance response conditions are met.

[0007] Preferably, the third step executes the monitoring response process to prevent a moving object, which is predefined for each type of moving object, from entering the monitoring target area.

[0008] Preferably, after the monitoring response processing, the computer further executes a fourth step of detecting the action taken by the moving object in response to the monitoring response processing, evaluating the effectiveness of the monitoring response processing based on the detection results, and updating the monitoring response processing in accordance with the evaluation results.

[0009] Preferably, the appropriateness of the monitoring response process is determined based on the evaluation result, and the monitoring response conditions are learned and updated based on the determination result.

[0010] Preferably, the third step executes the monitoring response process that is predetermined for the type of the moving object and the movement of the moving object.

[0011] Preferably, the first step identifies multiple types of the moving object and their movements, including their probabilities, and if the evaluation of the monitoring response process is low in the fourth step, the second step and the third step are executed based on the type and its movement identified as the next most likely.

[0012] Preferably, the computer further executes a fifth step of acquiring at least one of judgment information regarding the weather, time, and event schedule of the monitored area at the time of image capture by the camera, and the second step determines whether the movement of the moving object satisfies the monitoring response conditions based on the judgment information acquired in the fifth step.

[0013] Preferably, the second step determines whether or not the monitoring response condition is met based on a learning model, and the third step executes a process for manual determination if it is determined that the monitoring response condition is met, performs the monitoring response processing on the condition that a manual confirmation is made and an instruction to perform the monitoring response processing is input, and trains the learning model using the result of the determination in the second step and the input instruction as training data.

[0014] Preferably, the fourth step detects at least one of the following behaviors of the moving object: fleeing, approaching, or not moving, in accordance with the surveillance response processing, and the surveillance response processing is at least one of alarm processing, deterrence processing, intrusion prevention processing, and crime prevention processing.

[0015] The present invention is a surveillance support method in which a computer executes the following steps: a first step of analyzing the image capture results of a camera installed in a specified surveillance area and identifying the type of moving object and its movement captured by the camera; a second step of determining whether the movement of the moving object satisfies specified surveillance response conditions based on the identified type and movement of the moving object; and a third step of executing a predetermined surveillance response process on the moving object to prevent the moving object from entering the surveillance area if it is determined in the second step that the surveillance response conditions are met.

[0016] The present invention is a program that causes a computer to execute the following steps: a first step of analyzing the image capture results of a camera installed in a specified monitored area and identifying the type of moving object and its behavior captured by the camera; a second step of determining whether the behavior of the moving object satisfies specified monitoring response conditions based on the type and behavior of the moving object identified; and a third step of executing a monitoring response process on the moving object to prevent the moving object from entering the monitored area, if it is determined in the second step that the monitoring response conditions are met. [Effects of the Invention]

[0017] According to the present invention, it is possible to provide a surveillance support system, method and program that detects a moving object that has entered an area to be monitored, and if the moving object is subject to a warning, performs warning and avoidance processing appropriate for the moving object. [Brief explanation of the drawings]

[0018] [Figure 1] FIG. 1 is a diagram for explaining an environment in which a monitoring support system 31 according to a first embodiment of the present invention is applied. [Figure 2] FIG. 2 is a diagram showing a network configuration used in the monitoring support system 31 of this embodiment. [Figure 3] FIG. 3 is a functional block diagram of the monitoring support system 31. [Figure 4] FIG. 4 is a flowchart illustrating an example of the operation of the monitoring support system 31. [Figure 5] FIG. 5 is a flowchart for explaining the operation of changing the monitoring response process in the monitoring support system 31. [Figure 6] FIG. 6 is a flowchart for explaining the operation of the monitoring support system according to the first embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0019] A monitoring support system according to an embodiment of the present invention will be described below. First Embodiment FIG. 1 is a diagram for explaining an environment to which a monitoring support system 31 according to an embodiment of the present invention is applied. FIG. 2 is a diagram showing a network configuration used in the monitoring support system 31 of this embodiment.

[0020] As shown in FIG. 1, in a monitoring target area 3 of a monitoring support system 31, a monitoring camera 21 and a monitoring corresponding device 23 are arranged. The monitoring camera 21 and the monitoring device 23 are installed near a predetermined monitoring target area 3. The monitoring camera 21 captures an image of the monitoring target area 3 as an imaging target, and transmits the imaging result to the monitoring support system 31 via the network 9.

[0021] The monitoring response device 23 performs monitoring response processing on a moving object in the monitoring target area 3 in response to an instruction from the monitoring support system 31 . In this embodiment, moving objects include people, animals, vehicles, ships, aircraft, and the like. In this embodiment, for example, it is possible to prevent humans from entering prohibited areas and engaging in poaching, and to prevent animals from eating crops in fields, etc.

[0022] The surveillance camera 21 is, for example, an infrared camera, and is capable of capturing images even at night.

[0023] The monitoring response device 23 is a device that performs processing to make moving objects retreat from the monitoring target area 3, for example, by outputting an alarm sound or generating a repellent or sound that moving objects dislike.

[0024] The monitoring support system 31 receives and stores the image capture results of the monitoring camera 21. The surveillance support system 31 analyzes the imaging results and identifies the type of moving object captured by the surveillance camera 21 and its movement.

[0025] The surveillance support system 31 determines whether or not the movement of the moving object satisfies the surveillance response conditions based on the type and movement of the moving object that has been identified. For example, the monitoring response condition may be a motion of a moving object attempting to enter the monitoring target area 3, or a suspicious behavior (such as theft) within the monitoring target area 3.

[0026] When the monitoring support system 31 determines that the monitoring response conditions are satisfied, it transmits an instruction to the monitoring response device 23 to perform a predetermined monitoring response process on the moving object. For example, for each type of moving object, a monitoring response process is predefined that outputs a sound, smell, light, or electric current that is unpleasant to the moving object toward the moving object, and the monitoring response process is stored in the monitoring support system 31. The monitoring support system 31 performs the monitoring response process in accordance with the monitoring response process associated with the moving object determined to satisfy the monitoring response condition.

[0027] After the monitoring response process, the monitoring support system 31 detects the behavior of the target moving object in response to the monitoring response process, and evaluates the effectiveness of the monitoring response process based on the detection result. The monitoring support system 31 updates the monitoring response process in accordance with the evaluation result so that it becomes more effective. For example, the monitoring support system 31 determines the appropriateness of the monitoring response process based on the evaluation result, and learns and updates the monitoring response conditions based on the determination result. Analysis is AI analysis

[0028] If the monitoring support system 31 determines that the monitoring response conditions are met, it may execute a process to manually determine the need for monitoring response processing from video, etc., and if it determines after manual confirmation that monitoring response processing should be executed, it may execute the monitoring response processing.

[0029] The monitoring support system 31 may execute a process of notifying a predetermined monitoring organization such as a security company or the police as a monitoring response process.

[0030] The configuration of the monitoring support system 31 will be described below. FIG. 3 is a functional block diagram of the monitoring support system 31. As shown in FIG. 3, the monitoring support system 31 includes, for example, a display 51, an operation unit / input unit 54, a communication unit 55, a database 57, a memory 59, and a processing unit 61.

[0031] The display 51 displays an image based on a signal from the processing unit 61 . The communication unit 55 communicates with the surveillance camera 21 and the surveillance-enabled device 23 . The operation unit / input unit 54 is an operation means such as a touch panel, a keyboard, or a mouse. The database 57 stores various data used by the processing unit 61 . The memory 59 stores the program executed by the processing unit 61 . The processing unit 61 executes the program PRG stored in the memory 59 to perform the processing of the monitoring support system 31 defined in this embodiment.

[0032] An example of the operation of the monitoring support system 31 will now be described. FIG. 4 is a flowchart for explaining an example of the operation of the monitoring support system 31. Each step will now be described. The following processing is performed by the processing unit 61 of the monitoring support system 31 executing the program PRG stored in the memory 59.

[0033] Step ST11: The monitoring support system 31 receives the image pickup results of the monitoring camera 21 via the communication unit 55 and stores them in the database 57 .

[0034] Step ST12: The monitoring support system 31 analyzes the imaging results.

[0035] Step ST13: The monitoring support system 31 identifies the type of moving object captured by the monitoring camera 21 and its movement based on the analysis results of step ST12.

[0036] Step ST14: The surveillance support system 31 determines whether or not the behavior of the moving object satisfies the surveillance response condition based on the type and behavior of the moving object identified in step ST13. For example, the monitoring response condition may be a motion of a moving object attempting to enter the monitoring target area 3, or a suspicious behavior (such as theft) within the monitoring target area 3.

[0037] Step ST15: When the monitoring support system 31 determines that the monitoring response conditions are satisfied, it transmits an instruction to the monitoring response device 23 to perform a predetermined monitoring response process on the moving object. For example, for each type of moving object, a monitoring response process is predefined that outputs a sound, smell, light, or electric current that is unpleasant to the moving object toward the moving object, and the monitoring response process is stored in the monitoring support system 31. For example, if there is a bear on the border of the monitored area 3, a light that dislikes bears is shone on it. If there is a deer, the sound of a carnivorous animal that deer instinctively dislike is output from a speaker. An electric current is sent through an electric fence, etc. Processing is carried out to guide the bear so that it does not enter the monitored area 3. The monitoring support system 31 performs the monitoring response process in accordance with the monitoring response process associated with the moving object determined to satisfy the monitoring response condition.

[0038] Step ST16: The monitoring support system 31 determines whether or not a predetermined notification condition is met, and if it is determined that the condition is met, the process proceeds to step ST17.

[0039] Step ST17: The monitoring support system 31 notifies a predetermined monitoring organization such as a security company or the police.

[0040] As described above, the surveillance support system 31 can identify a moving object that has entered an area to be monitored, and if the moving object is subject to a warning, can perform surveillance response processing appropriate for the moving object. This makes it possible to prevent moving objects from entering the monitored area 3 and engaging in unauthorized behavior.

[0041] The operation of changing the monitoring response process will be described below. FIG. 5 is a flowchart for explaining the operation of changing the monitoring response process in the monitoring support system 31. Each step will be explained.

[0042] Step ST21: After the monitoring response process in step ST15 shown in FIG. 4, the monitoring support system 31 determines the effect of the process. For example, whether or not the moving object has immediately retreated from the monitoring target area 3 through the monitoring response process.

[0043] Step ST22: The monitoring support system 31 determines whether or not the change conditions for changing the monitoring response process are met based on the effect determination result of step ST21, and if it determines that the change conditions are met, the process proceeds to step ST23.

[0044] Step ST23: The monitoring support system 31 updates the monitoring response process to make it more effective. For example, the monitoring support system 31 determines the appropriateness of the monitoring response process based on the evaluation result, and learns and updates the monitoring response conditions based on the determination result.

[0045] As described above, the monitoring support system 31 can verify the effectiveness of the monitoring response process and change the content of the monitoring response process as necessary, thereby improving the effectiveness of the monitoring response process.

[0046] Second Embodiment A monitoring support system according to a second embodiment of the present invention will be described below. FIG. 6 is a flowchart for explaining the operation of the monitoring support system according to the second embodiment of the present invention. In this embodiment, for example, the predetermined monitoring response process is executed not only for the type of moving object but also for the movement of the moving object. Furthermore, after performing a monitoring response process, the monitoring support system detects at least one of the following behaviors of the moving object: fleeing, approaching, or not moving, depending on the monitoring response process.Then, based on the results, the effectiveness of the monitoring response process is verified and evaluated, and the content of the monitoring response process is modified.For example, if a fleeing behavior is detected, the monitoring support system recognizes that the actual monitoring response process was correct.

[0047] Furthermore, the monitoring support system acquires at least one of the determination information items of the weather, time, and event schedule of the monitoring target area at the time of capturing an image with the camera, as shown in FIG. 6 (step ST50). Then, based on the acquired information for determination, it is determined whether or not the movement of the moving object satisfies the forward monitoring response condition (step ST14). Furthermore, in this embodiment, it is determined whether the above-described monitoring response conditions are met based on the learning model.

[0048] In addition, in this embodiment, if it is determined that the monitoring response conditions are met, a process for manual judgment is executed, and output is performed in the monitoring response process on the condition that a manual confirmation is made and an instruction to perform the monitoring response process is entered. Then, the learning model of this embodiment is trained using the judgment results and manually input instructions as training data.

[0049] According to this embodiment, the monitoring response conditions are determined by further using at least one of the judgment information items, such as climate, time, and event schedule, which indicate the environment of the monitored area, thereby enabling more accurate judgments that are suited to the conditions of the monitored area.

[0050] The present invention is not limited to the above-described embodiments. That is, those skilled in the art may make various modifications, combinations, subcombinations, and substitutions of the components of the above-described embodiments within the technical scope of the present invention or its equivalents. For example, within the monitored area 3, a legitimate person may transmit predetermined information, and the monitoring support system 31 may be configured not to perform monitoring response processing on that person when receiving the information.

[0051] Furthermore, the monitoring response process may be either an alarm process or an avoidance process. Furthermore, as described above, a monitoring response condition may be set by identifying a prior action of a moving object before it takes an inappropriate action, and performing a corresponding monitoring response process (alarm output / avoidance process).

[0052] In the above-described embodiment, multiple types of moving objects and their movements may be identified, including their possibilities. In this case, monitoring response processing is performed based on the type of moving object and its behavior that is first identified, and if the evaluation of that monitoring response processing is low, monitoring response conditions are determined based on the type of moving object and its behavior that is next identified as having the highest probability, and if the monitoring response conditions are met, monitoring response processing is performed and evaluation is performed again. [Industrial Applicability]

[0053] The present invention is applicable to a monitoring support system. [Explanation of symbols]

[0054] 3...Monitored area 31...Monitoring support system

Claims

1. A first step of analyzing the image captured by a camera installed in a predetermined monitoring area and identifying the type and behavior of a moving object captured by the camera; a second step of determining whether or not the movement of the moving object satisfies a predetermined monitoring response condition based on the type and movement of the moving object identified; a third step of executing a monitoring response process for the moving object, which is predetermined for each type of moving object, to prevent the moving object from entering the monitoring target area when it is determined in the second step that the monitoring response condition is satisfied; a fourth step of detecting, after the monitoring response process, an action taken by the moving object in response to the monitoring response process, evaluating the effectiveness of the monitoring response process based on the result of the detection, and updating the monitoring response process in response to the evaluation result; A computer-run monitoring support system.

2. Based on the evaluation result, the appropriateness of the monitoring response process is determined, and based on the determination result, the monitoring response conditions are learned and updated. The monitoring support system according to claim 1 .

3. The third step executes the predetermined monitoring response process for the type of the moving object and the movement of the moving object. The monitoring support system according to claim 2 .

4. The first step includes identifying a plurality of types of the moving object and their movements, including their possibilities; In the fourth step, if the evaluation of the monitoring response process is low, the second step and the third step are executed based on the type and its operation identified as the next most likely. The monitoring support system according to claim 3 .

5. a fifth step of acquiring at least one of information for determination regarding the weather, time, and event schedule of the monitored area at the time of capturing an image by the camera; The computer further executes The second step determines whether or not the movement of the moving object satisfies the monitoring response condition based on the determination information acquired in the fifth step. The monitoring support system according to claim 4.

6. The second step determines whether the monitoring response condition is satisfied based on a learning model; The third step executes a process for manual determination when it is determined that the monitoring response condition is satisfied, and performs the monitoring response process on the condition that a manual confirmation is made and an instruction to perform the monitoring response process is input, The learning model is trained using the result of the determination in the second step and the input instruction as training data. The monitoring support system according to claim 5 .

7. the fourth step detects at least one of the following behaviors of the moving object: running away, approaching, and not moving, in response to the monitoring response process; The monitoring response process is at least one of an alarm process, a deterrent process, an intrusion prevention process, and a crime prevention process. The monitoring support system according to claim 6.

8. A first step of analyzing the image captured by a camera installed in a predetermined monitoring area and identifying the type and behavior of a moving object captured by the camera; a second step of determining whether or not the movement of the moving object satisfies a predetermined monitoring response condition based on the type and movement of the moving object identified; a third step of executing a monitoring response process for the moving object, which is predetermined for each type of moving object, to prevent the moving object from entering the monitoring target area when it is determined in the second step that the monitoring response condition is satisfied; a fourth step of detecting, after the monitoring response process, an action taken by the moving object in response to the monitoring response process, evaluating the effectiveness of the monitoring response process based on the result of the detection, and updating the monitoring response process in response to the evaluation result; A computer-implemented monitoring method.

9. A first step of analyzing the image captured by a camera installed in a predetermined monitoring area and identifying the type and behavior of a moving object captured by the camera; a second step of determining whether or not the movement of the moving object satisfies a predetermined monitoring response condition based on the type and movement of the moving object identified; a third step of executing a monitoring response process for the moving object, which is predetermined for each type of moving object, to prevent the moving object from entering the monitoring target area when it is determined in the second step that the monitoring response condition is satisfied; a fourth step of detecting, after the monitoring response process, an action taken by the moving object in response to the monitoring response process, evaluating the effectiveness of the monitoring response process based on the result of the detection, and updating the monitoring response process in response to the evaluation result; A program that a computer executes.

Images