Automatic security inspection method and system based on unmanned aerial vehicle

Abstract

The invention relates to the technical field of security inspection, and provides an unmanned aerial vehicle-based automatic security inspection method and system, and the method comprises the steps: constructing a to-be-inspected region needing to be inspected by an unmanned aerial vehicle through security region data and fixed camera data, setting an unmanned aerial vehicle inspection region through unmanned aerial vehicle data, and carrying out the traversal of the to-be-inspected region, according to a traversal result, an optimal inspection route for unmanned aerial vehicle inspection is constructed, the unmanned aerial vehicle flies on the inspection route to obtain a real-time inspection image, then risk behaviors of the image are identified, automatic security inspection of the unmanned aerial vehicle is realized, a security area can be fully covered by inspection, and the security inspection efficiency is improved. And the area which cannot be monitored by the fixed camera is inspected in a most efficient manner, so that the safety and the inspection efficiency in the security area are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of security inspection, and in particular to an automatic security inspection method and system based on a drone. Background Art

[0002] The construction of smart cities requires comprehensive and real-time monitoring and management of traffic, security and other aspects. Currently, surveillance cameras are installed in major traffic arteries, key intersections, public places and other areas. However, the area that needs to be inspected is large, and the cost of installing surveillance cameras throughout the inspection area is high. Manual inspection is generally used, but it is inefficient. Summary of the invention

[0003] The present invention provides an automatic security inspection method based on a drone, which is used to solve the problem of high cost and low efficiency in realizing comprehensive security inspection in the prior art.

[0004] The first aspect of the present invention provides an automatic security inspection method based on a drone, comprising: Obtain security area data and fixed camera data, construct security area coordinates based on security area data, and construct inspected area coordinates based on fixed camera data; remove inspected area coordinates from security area coordinates to obtain the coordinates of the area to be inspected; Obtain drone camera data, and build the size of the drone inspection area based on the drone camera data; traverse the drone inspection area in the area to be inspected to build the best inspection route; The inspection route is sent to the drone, real-time drone inspection images are obtained, and risk behavior identification is performed based on the drone inspection images.

[0005] Optionally, after traversing the area to be inspected by using a drone, the method further includes: Obtain historical inspection data, determine areas with high incidence of inspection risk behaviors, obtain the necessary points in the drone inspection area corresponding to the traversal plan based on the regional coordinates, and adaptively increase the number of times the corresponding necessary points are passed when constructing the optimal inspection route.

[0006] Optionally, after the risk behavior identification is performed based on the drone inspection image, the method further includes: Identify risky behaviors in drone inspection images, obtain corresponding drone inspection coordinates based on the image frames where risky behaviors appear, and send the corresponding risk coordinates to the drone for key inspections.

[0007] The second aspect of the present application provides an automatic security inspection system based on a drone, comprising: The module for constructing the area to be inspected is used to obtain the security area data and the fixed camera data, construct the security area coordinates according to the security area data, and construct the inspected area coordinates according to the fixed camera data; the coordinates of the area to be inspected are obtained by removing the coordinates of the inspected area from the coordinates of the security area; Inspection route planning module, used to obtain drone camera data, build the size of the drone inspection area based on the drone camera data; traverse the drone inspection area on the area to be inspected to build the best inspection route; The automatic inspection control module is used to send the inspection route to the drone, obtain real-time drone inspection images, and identify risky behaviors based on the drone inspection images.

[0008] Optionally, in the inspection route planning module, after traversing the area to be inspected with the drone, the module further includes: Obtain historical inspection data, determine areas with high incidence of inspection risk behaviors, obtain the necessary points in the drone inspection area corresponding to the traversal plan based on the regional coordinates, and adaptively increase the number of times the corresponding necessary points are passed when constructing the optimal inspection route.

[0009] Optionally, in the automatic inspection control module, after identifying risk behaviors according to the drone inspection images, the module further includes: Identify risky behaviors in drone inspection images, obtain corresponding drone inspection coordinates based on the image frames where risky behaviors appear, and send the corresponding risk coordinates to the drone for key inspections.

[0010] The third aspect of the present application provides an automatic security inspection method device based on a drone, the device comprising a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute an automatic security inspection method based on a drone as described in any one of the first aspects of the present invention according to the instructions in the program code.

[0011] The fourth aspect of the present application provides a computer-readable storage medium, which is used to store program code, and the program code is used to execute an automatic security inspection method based on a drone as described in any one of the first aspects of the present invention.

[0012] It can be seen from the above technical scheme that the present invention has the following advantages: the area to be inspected that requires drone inspection is constructed through security area data and fixed camera data, and then the drone inspection area is set with drone data, and the area to be inspected is traversed, and the best inspection route for drone inspection is constructed according to the traversal results. The drone flies on the inspection route to obtain real-time inspection images, and then identifies risk behaviors in the images to realize automatic security inspection by drones, so that the security area can be fully covered by the inspection, and the areas that cannot be monitored by fixed cameras are inspected in the most efficient way, thereby improving the safety and inspection efficiency in the security area. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0014] Figure 1 This is a flow chart of an automatic security inspection method based on drones; Figure 2 This is a schematic diagram of the area to be inspected; Figure 3 A schematic diagram of the area to be inspected after excluding the inspected areas in the security area; Figure 4 This is a structural diagram of an automatic security inspection system based on drones. DETAILED DESCRIPTION

[0015] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] The present invention provides an automatic security inspection method based on a drone, which is used to solve the problem of high cost and low efficiency in realizing comprehensive security inspection in the prior art.

[0017] See also Figure 1 , Figure 1 The present invention provides a first flow chart of an automatic security inspection method based on a drone in an embodiment of the present invention.

[0018] S100, obtaining security area data and fixed camera data, constructing security area coordinates according to the security area data, and constructing inspected area coordinates according to the fixed camera data; removing the inspected area coordinates from the security area coordinates to obtain the coordinates of the area to be inspected; It should be noted that the security area data includes the size and position of the area that needs to be secured, establishes a spatial or plane coordinate system, and constructs the security area coordinates with the coordinate size. The security area needs to be secured through monitoring images, which is generally an open area around the building. The edge of the security area is generally the outer wall of the building, and drones cannot pass through; the fixed camera data includes the installation position of each camera, as well as the camera parameters and the distance range that can be clearly photographed. According to the fixed installation position of the camera and the shooting distance parameters of the camera, the coordinates of the inspected area monitored by each camera can be constructed, that is, the size and shape of the inspected area are set according to the shooting distance parameters of the camera. The position coordinates of the camera are within the security area, and the overlapping area of ​​the inspected area in the security area is determined according to the installation coordinates of the camera. In order to save costs in the security area, fixed cameras are generally only set in some key areas or road conditions; please refer to Figure 2 , Figure 2 Figure 1 is a schematic diagram of the area to be inspected. In the figure, 1 is the security area. The edge of the security area is generally a building or a wall. A camera can be fixedly installed on the edge of the security area. A plane coordinate system can be established based on the edge of the security area. Figure 2 is the camera, 3 is the inspected area corresponding to the camera, and 4 is the area to be inspected obtained by excluding the inspected area in the security area. Figure 3 The schematic diagram of the area to be inspected is a security area excluding the inspected area. The area to be inspected is the area that cannot be captured by the surveillance video of the fixed camera. In the prior art, the area to be inspected requires manual inspection.

[0019] S200, obtaining drone camera data, and constructing the size of the drone inspection area based on the drone camera data; traversing the drone inspection area on the area to be inspected to construct an optimal inspection route; It should be noted that the parameters of the camera configured on the drone can determine the size of the area that can be photographed during the drone inspection. For example, the drone inspection area of ​​the fisheye aerial lens should be circular, and the size of the circular area is set according to the resolution of the camera. The general high-definition camera can set the drone inspection area to a rectangle. In this embodiment, only the coverage relationship between planar areas is considered, and the spatial relationship is not considered; the drone inspection area needs to traverse the area to be inspected, which is equivalent to the drone aerial photography inspecting the area that cannot be photographed by the fixed camera. By traversing the area to be inspected with the drone inspection area, several drone inspection areas of the same size and shape are used to cover the area to be inspected during the traversal process. During the traversal process, multiple drone inspection areas need to completely cover the area to be inspected, and the coverage plan that requires the least number of drone inspection areas is selected. The coverage plan can reflect how many drones need to reach at least to complete a full inspection of the area to be inspected. Points; when constructing the inspection route, a shortest path through each drone inspection area can be identified under the coverage scheme composed of several drone inspection areas. In each drone inspection area, a must-pass point of the inspection route can be set according to the camera type. For example, the center of the circular drone inspection area under the fisheye aerial lens should be the must-pass point, that is, the inspection route is considered to be able to reach the inspection area when it passes through the center of the circular drone inspection area; some parts of the area to be inspected require multiple drone inspection areas to overlap to achieve coverage, and when constructing the shortest inspection route, the position of the must-pass point of the drone inspection area can be changed by changing the overlapping relationship, making the inspection route shorter, and when the edge of the security area is a building wall and the drone cannot pass through, the inspection route cannot pass through the edge of the security area; the drone inspection route finally constructed needs to enable the drone camera to capture the area to be inspected that the fixed camera cannot capture during the flight inspection, and the shortest inspection route is the best; S300, sending the inspection route to the drone, obtaining real-time drone inspection images, and identifying risk behaviors based on the drone inspection images.

[0020] It should be noted that the inspection route can be represented as the plane coordinates of multiple turning points, and each turning point has a passing order. After the coordinates of each turning point of the inspection route and the passing order are sent to the drone, the drone will fly to each coordinate point in the inspection route in sequence to realize the inspection; during the inspection process, the drone inspection image will be taken to monitor the areas that cannot be photographed by fixed cameras, and the inspection images will be analyzed and processed in real time to identify risky behaviors. According to the characteristics of the specific inspection location, the corresponding risky behavior features are selected for identification. For example, in the construction site area, the risky behavior of workers is detected for illegal activities, and after identifying the human body in the drone inspection image, it is determined whether the person is wearing a safety helmet to identify the risky behavior and complete the automatic security inspection of the drone.

[0021] In this embodiment, the area to be inspected that requires drone inspection is constructed through security area data and fixed camera data, and then the drone inspection area is set with the drone data, and the area to be inspected is traversed. The best inspection route for drone inspection is constructed based on the traversal results. The drone flies on the inspection route to obtain real-time inspection images, and then identifies risk behaviors in the images to realize automatic security inspection by drones, so that the security area can be fully covered by the inspection, and the areas that cannot be monitored by fixed cameras are inspected in the most efficient way, thereby improving the safety and inspection efficiency in the security area.

[0022] The above is a detailed description of the first embodiment of an automatic security patrol method based on a drone provided by the present application. The following is a detailed description of the second embodiment of an automatic security patrol method based on a drone provided by the present application.

[0023] In this embodiment, an automatic security inspection method based on drones is further provided. In the aforementioned step S200, after traversing the inspection area with a drone on the area to be inspected, the method further includes: obtaining historical inspection data, determining areas with high incidence of inspection risk behaviors, obtaining the necessary points of the drone inspection area corresponding to the traversal plan according to the area coordinates, and adaptively increasing the number of times the corresponding necessary points pass when constructing the optimal inspection route; It should be noted that risky behaviors will be identified during the drone inspection process. Based on the coordinates of the drones that have identified risky behaviors in the historical inspection data, the coordinates of the occurrence of the inspection risky behaviors can be determined, and the total number of wind direction behaviors that fall into each drone inspection area under the drone inspection area traversal method in the inspection route can be identified. The necessary points in the inspection area where the total number of risky behaviors exceeds the preset number of thresholds are identified, and when replanning the best inspection route, it is set that the necessary points in the areas with high incidence of inspection risk behaviors need to be passed multiple times. Multiple number thresholds can be set to increase the number of times the necessary points are passed, and when planning the inspection route, the same necessary points need to be separated by several other necessary points to avoid the continuous passing of necessary points in high-incidence areas due to the logic of the shortest route when planning the inspection route, which affects the effect of increasing the inspection and monitoring intensity in areas with high incidence of risky behaviors.

[0024] Furthermore, after the risk behavior is identified based on the drone inspection image, it also includes: identifying the risk behavior in the drone inspection image, obtaining the corresponding drone inspection coordinates based on the image frame where the risk behavior appears, and sending the corresponding risk coordinates to the drone for key inspection.

[0025] It should be noted that when the drone is performing automatic security inspection tasks, the data of time and the coordinates of the drone will be recorded. Based on real-time risk behavior recognition, when risky behavior is identified, the corresponding time point is obtained according to the video frame time of the identified risk, and the coordinates corresponding to the time point are sent to the drone to conduct key inspections at the risk location. For example, if a traffic accident occurs on a road, the drone can fly to the coordinates and hover to obtain more video images, which is conducive to subsequent supervision and processing.

[0026] The above is a detailed description of an automatic security inspection method based on a drone provided in the first aspect of the present application. The following is a detailed description of an embodiment of an automatic security inspection system based on a drone provided in the second aspect of the present application.

[0027] See also Figure 4 , Figure 4 This embodiment provides an automatic security inspection system based on a drone, including: The module 10 for constructing the area to be inspected is used to obtain the security area data and the fixed camera data, construct the security area coordinates according to the security area data, and construct the inspected area coordinates according to the fixed camera data; and obtain the coordinates of the area to be inspected by removing the inspected area coordinates from the security area coordinates; The inspection route planning module 20 is used to obtain drone camera data, build the size of the drone inspection area based on the drone camera data; traverse the drone inspection area on the area to be inspected to build the best inspection route; The automatic inspection control module 30 is used to send the inspection route to the drone, obtain real-time drone inspection images, and identify risk behaviors based on the drone inspection images.

[0028] Furthermore, in the inspection route planning module 20, after traversing the area to be inspected with the drone, the following steps are further included: Obtain historical inspection data, determine areas with high incidence of inspection risk behaviors, obtain the necessary points in the drone inspection area corresponding to the traversal plan based on the regional coordinates, and adaptively increase the number of times the corresponding necessary points are passed when constructing the optimal inspection route.

[0029] Furthermore, in the automatic inspection control module 30, after identifying risk behaviors according to the drone inspection images, the automatic inspection control module 30 further includes: Identify risky behaviors in drone inspection images, obtain corresponding drone inspection coordinates based on the image frames where risky behaviors appear, and send the corresponding risk coordinates to the drone for key inspections.

[0030] The third aspect of the present application also provides an automatic security inspection method device based on a drone, including a processor and a memory: the memory is used to store program code and transmit the program code to the processor; the processor is used to execute the above-mentioned automatic security inspection method based on a drone according to the instructions in the program code.

[0031] A fourth aspect of the present application provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program code, and the program code is used to execute the above-mentioned automatic security inspection method based on a drone.

[0032] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0033] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0034] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0035] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0036] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0037] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automatic security inspection method based on drones, characterized in that include: Obtain security area data and fixed camera data, construct security area coordinates based on security area data, and construct inspected area coordinates based on fixed camera data; remove inspected area coordinates from security area coordinates to obtain the coordinates of the area to be inspected; Obtain drone camera data and construct the size of the drone inspection area based on the drone camera data; Use drones to traverse the area to be inspected and build the best inspection route; The inspection route is sent to the drone, real-time drone inspection images are obtained, and risk behavior identification is performed based on the drone inspection images.

2. The automatic security inspection method based on drone according to claim 1 is characterized in that: After the unmanned aerial vehicle is used to traverse the area to be inspected, the method further includes: Obtain historical inspection data, determine areas with high incidence of inspection risk behaviors, obtain the necessary points in the drone inspection area corresponding to the traversal plan based on the regional coordinates, and adaptively increase the number of times the corresponding necessary points are passed when constructing the optimal inspection route.

3. The automatic security inspection method based on drone according to claim 1 is characterized in that: After the risk behavior identification is performed based on the drone inspection image, the following steps are also included: Identify risky behaviors in drone inspection images, obtain corresponding drone inspection coordinates based on the image frames where risky behaviors appear, and send the corresponding risk coordinates to the drone for key inspections.

4. An automatic security inspection system based on drones, characterized in that: include: The module for constructing the area to be inspected is used to obtain the security area data and the fixed camera data, construct the security area coordinates according to the security area data, and construct the inspected area coordinates according to the fixed camera data; the coordinates of the area to be inspected are obtained by removing the coordinates of the inspected area from the coordinates of the security area; Inspection route planning module, used to obtain drone camera data and build the size of the drone inspection area based on the drone camera data; Use drones to traverse the area to be inspected and build the best inspection route; The automatic inspection control module is used to send the inspection route to the drone, obtain real-time drone inspection images, and identify risky behaviors based on the drone inspection images.

5. The automatic security inspection system based on drone according to claim 4 is characterized in that: In the inspection route planning module, after traversing the area to be inspected by the drone, the following steps are also included: Obtain historical inspection data, determine areas with high incidence of inspection risk behaviors, obtain the necessary points in the drone inspection area corresponding to the traversal plan based on the regional coordinates, and adaptively increase the number of times the corresponding necessary points are passed when constructing the optimal inspection route.

6. The automatic security inspection system based on drone according to claim 4 is characterized in that: In the automatic inspection control module, after identifying risk behaviors according to the inspection images of the drone, the module further includes: Identify risky behaviors in drone inspection images, obtain corresponding drone inspection coordinates based on the image frames where risky behaviors appear, and send the corresponding risk coordinates to the drone for key inspections.

7. An automatic security inspection device based on drones, characterized in that: The device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the automatic security inspection method based on a drone as described in any one of claims 1-3 according to the instructions in the program code.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program code, and the program code is used to execute the automatic security inspection method based on a drone as described in any one of claims 1-3.

Images