Intelligent river patrol method and system, electronic device, and computer-readable storage medium

Abstract

The present invention discloses an intelligent river patrol method and system, an electronic device, and a computer-readable storage medium, comprising: obtaining a high-resolution satellite remote sensing image river map, marking the position of a camera on the high-resolution satellite remote sensing image river map; setting the patrol range of each camera respectively, and marking points according to a grid; sequentially calling the data of the camera to obtain a video stream and perform abnormal event recognition processing, and recording abnormal events and position coordinates; using a drone to patrol the river according to a preset patrol route, transmitting the acquired video back to a monitoring center and performing recognition processing, recording the recognized abnormal events and position coordinates; sorting the abnormal events at the patrol points according to the number of occurrences, and saving them if the number of occurrences is greater than a first threshold; merging adjacent patrol points whose distance calculated according to longitude and latitude is less than a second threshold; generating a new patrol route in combination with patrol points that must be patrolled, and updating the patrol route.

Description

Technical Field

[0001] The present application relates to the field of river and lake management technology, and in particular to an intelligent river patrol method and system, electronic equipment, and computer-readable storage medium. Background Art

[0002] Rivers, lakes and reservoirs have important resource functions, ecological functions and economic functions. In recent years, various regions have actively taken measures to strengthen the governance, management and protection of rivers and lakes, and have achieved remarkable comprehensive benefits in flood control, water supply, power generation, shipping, aquaculture, etc. However, with the rapid development of the economy and society, some new problems have emerged in the management and protection of rivers and lakes, such as the high level of pollutant emissions into rivers and lakes, the frequent occupation of river courses, reclamation of lakes and illegal sand mining.

[0003] River and lake management is an important means to test whether the river chief system and lake chief system are "famous" and "real". However, the current river and lake management still relies on regular manual inspections or public reports. This method has shortcomings such as incomplete inspection coverage, relatively fixed inspection routes, safety risks for inspectors in extreme weather, random problem discovery, and poor timeliness. It also consumes a lot of manpower, so an intelligent inspection method is particularly important. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide an intelligent river patrol method and system, an electronic device, and a computer-readable storage medium to solve the technical problems in the related art that river and lake management relies on regular manual inspections or public reports, which have the shortcomings of random problem discovery, untimely offline processing, lack of rectification feedback, poor timeliness, and consumes a lot of manpower.

[0005] According to a first aspect of an embodiment of the present application, there is provided an intelligent river patrol method, which is applied to a monitoring center and includes:

[0006] Obtain high-resolution satellite remote sensing imagery river maps;

[0007] Marking the position of the camera on the high-resolution satellite remote sensing image river map to obtain the coordinates of the camera;

[0008] The inspection range of each camera is set respectively, and the marking points are marked in the field of view of each camera according to the grid. Combined with the coordinates of the camera, the coordinate position of the marking point on the high-resolution satellite remote sensing image river map and the current corresponding viewing angle parameters of the camera are determined and saved in the camera preset position, and the preset position number is recorded;

[0009] The viewing angle of the camera is adjusted to the preset position, the camera is called in sequence and the video stream of the camera is pulled, and the video stream is processed for abnormal event recognition. When an abnormal event is recognized, the abnormal event and the abnormal event position are recorded. The abnormal event position is the coordinate position of the mark point closest to the abnormal event, and the abnormal event position is recorded as a patrol point;

[0010] Importing inspection routes into the drone so that the drone conducts inspections along the inspection routes, and after arriving at the inspection points, performs all-round video shooting and transmits the shot videos to the monitoring center. The inspection routes are composed of various inspection points.

[0011] Identify abnormal events in the video sent by the drone. When an abnormal event is identified, record the abnormal event and its location.

[0012] Statistics of abnormal events at each inspection point;

[0013] If the frequency of abnormal events at a certain inspection point is higher than the first threshold, the abnormal event location is added to the inspection route, and the distance between adjacent inspection points is calculated. If the distance is less than the second threshold, the inspection points are merged, and the inspection route is updated in combination with the inspection points that must be inspected;

[0014] The updated inspection route is sent to the drone.

[0015] According to a second aspect of an embodiment of the present application, there is provided an intelligent river patrol system, which is applied to a monitoring center and includes:

[0016] Acquisition module, used to obtain high-resolution satellite remote sensing image river maps;

[0017] A marking module, used to mark the position of the camera on the high-resolution satellite remote sensing image river map to obtain the coordinates of the camera;

[0018] A position determination module is used to set the inspection range of each camera respectively, and mark the marking points according to the grid within the field of view of each camera, and determine the coordinate position of the marking point on the high-resolution satellite remote sensing image river map and the current corresponding viewing angle parameters of the camera in combination with the coordinates of the camera;

[0019] A first event recognition module is used to adjust the viewing angle of the camera to the position corresponding to the viewing angle parameter, call the camera in sequence and pull the video stream of the camera, perform recognition processing on the video stream, and when an abnormal event is recognized, record the abnormal event and the abnormal event position, the abnormal event position is the coordinate position of the mark point closest to the abnormal event, and the abnormal event position is recorded as a patrol point;

[0020] The route import module is used to import the inspection route into the drone so that the drone can inspect according to the inspection route, take all-round video after arriving at the inspection point, and transmit the video to the monitoring center. The inspection route is composed of various inspection points.

[0021] The second event recognition module is used to recognize abnormal events in the video sent by the drone, and when an abnormal event is recognized, the abnormal event and the abnormal event location are recorded;

[0022] Statistics module, used to count abnormal events at each inspection point;

[0023] The route update module is used to add the abnormal event location to the inspection route if the frequency of abnormal events at a certain inspection point in the original inspection route is higher than the first threshold, calculate the distance between adjacent inspection points, merge the inspection points if the distance is less than the second threshold, and update the inspection route in combination with the inspection points that must be inspected;

[0024] The sending module is used to send the updated inspection route to the drone.

[0025] According to a third aspect of an embodiment of the present application, there is provided an electronic device, including:

[0026] one or more processors;

[0027] A memory for storing one or more programs;

[0028] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in the first aspect.

[0029] According to a third aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in the first aspect are implemented.

[0030] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0031] It can be seen from the above embodiments that the present application adopts a combination of video and drones, defines the camera recognition area and formulates the initial drone inspection route, identifies and processes abnormal events in the camera video and the video transmitted back by the drone, performs statistical analysis and calculation on abnormal events, optimizes the inspection route and automatically generates new drone inspection routes, thereby overcoming technical problems such as incomplete inspection coverage, relatively fixed inspection routes, safety risks for inspectors in extreme weather, random problem discovery, and poor timeliness, and thus achieves the technical effect of intelligent river patrol. By identifying abnormal events, classifying and counting them, and optimizing river patrol routes, it not only improves the work efficiency of inspectors, but also improves the real-time nature of abnormal event discovery, truly realizing intelligent river patrol.

[0032] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0034] Figure 1 The present invention is a flow chart of an intelligent river patrol method according to an exemplary embodiment.

[0035] Figure 2 It is a schematic diagram showing an isosceles trapezoid formed by any four points on the earth according to an exemplary embodiment.

[0036] Figure 3 It is a schematic diagram showing the installation of cameras on both sides of a river according to an exemplary embodiment.

[0037] Figure 4 It is a schematic diagram showing an abnormal event - illegal sewage discharge according to an exemplary embodiment.

[0038] Figure 5 It is a block diagram of an intelligent river patrol system according to an exemplary embodiment.

[0039] Figure 6 The diagram is a schematic structural diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0040] Here, exemplary embodiments will be described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are only examples of systems and methods consistent with some aspects of the present application.

[0041] The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to and includes any or all possible combinations of one or more associated listed items.

[0042] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0043] The monitoring center can be a computing recognition and analysis system. It is mainly used to pull the camera video stream and perform abnormal event recognition processing on the video stream, perform abnormal event recognition processing on the video transmitted back by the drone, and automatically generate inspection routes according to abnormal events at the inspection points. The abnormal event recognition algorithm (AI recognition algorithm) can adopt the general algorithm on the market. For example, companies such as Hikvision and Dahua provide relevant technologies and integrate them.

[0044] Figure 1 is a flow chart of an intelligent river patrol method according to an exemplary embodiment. Figure 1 As shown, the method is applied to a monitoring center and may include the following steps:

[0045] S1: Obtain high-resolution satellite remote sensing image river map;

[0046] Specifically, determine the scope of the river to be supervised, and obtain high-resolution satellite remote sensing image river maps from local natural resources bureaus or surveying and mapping institutes. This map contains coordinate information of all locations within the river range. The main purpose of this step is to provide coordinate information for subsequent operations.

[0047] S2: Marking the position of the camera on the high-resolution satellite remote sensing image river map to obtain the coordinates of the camera;

[0048] Specifically, since all areas on the high-resolution satellite remote sensing image river map are visible, the camera position along the river on the high-resolution satellite remote sensing image river map is combined with the on-site card drawing to find the camera and record the coordinates of the camera. The main purpose of this step is to provide a position reference for the next step of marking point marking.

[0049] S3: respectively set the inspection range of each camera, and mark the marking points in the field of view of each camera according to the grid, and determine the coordinate position of the marking point on the high-resolution satellite remote sensing image river map and the current corresponding viewing angle parameters of the camera in combination with the coordinates of the camera, and save them to the camera preset position; this step may include the following sub-steps:

[0050] S31: Adjust the viewing angle and focal length of the camera to ensure that the river to be monitored can be covered;

[0051] Specifically, adjust the viewing angle and focal length of the camera until the river surface and the opposite bank can be clearly monitored. If it is a gun camera, you only need to adjust the focal length. If it is a ball camera, you need to adjust the viewing angle and focal length (the ball camera can rotate). The main purpose of this step is to define the video AI recognition range in the subsequent steps.

[0052] S32: Obtain a photo taken by the camera;

[0053] Specifically, a photo is taken by the camera, and the main purpose of this step is to provide an original template for defining the recognition area in the next step.

[0054] S33: Delineating the area to be inspected and identified on the photo;

[0055] Specifically, the area to be inspected and identified is delineated on the photo, such as Figure 3 As shown in the figure, because the cameras are installed too close or the ball camera can rotate, the recognition areas may overlap, which may cause abnormal events to be recognized multiple times at the same location, affecting the automatic planning of subsequent inspection routes. By delineating the areas that need to be inspected and identified, overlapping locations can be avoided and recognition efficiency can be improved.

[0056] S34: marking points on the photo according to a grid, and determining the coordinate positions of the marking points on the high-resolution satellite remote sensing image river map in combination with the coordinates of the camera;

[0057] Specifically, marking points are marked on the photo according to a grid. Since the camera has a relatively high resolution and an adjustable focal length, the irradiation range is generally about 100-200 meters. The designated identification area is marked on the photo according to a 3*3 grid. Based on the coordinate position of the camera as a reference point, combined with the high-resolution satellite remote sensing image river map, the coordinate positions of a total of 9 center points in the 3*3 grid are obtained. The main purpose of this step is to map the identified event area to the grid after identifying the abnormal event, so as to obtain the specific coordinate position of the abnormal event. This method will have coordinate errors, but because the irradiation range of the video is large, the error can be ignored. Generally speaking, the denser the grid marking points, the more accurate the specific coordinate position of the abnormal event. Considering the large irradiation range of the video, it is generally recommended to use 3*3. According to the range of 100 meters, the coordinate interval of adjacent points is about 33 meters, which is in line with the irradiation range of the video.

[0058] S35: Record the viewing angle parameters of the camera, save them in the camera preset position, and record the preset position number;

[0059] Specifically, the viewing angle parameters of the camera, including rotation position, angle, focal length and other parameters, are recorded, the position is set as the preset position parameters of the camera, and the number of the preset position is recorded, then the camera will automatically store the rotation position, angle, focal length and other parameters. The preset position is a function that allows the user to pre-set and save the position, angle and focal length of the camera so that it can be quickly called when needed. The main purpose of this step is to ensure that the illumination range is consistent with that when the recognition area is demarcated. If any one or more parameters such as the inclination angle, rotation position, focal length, etc. change, it will cause changes in the recognition area, and ultimately lead to repeated recognition or recognition errors. The camera is also returned to the position when it was set by means of the preset position. It is worth noting that only the ball camera has a preset position. The gun camera has no preset position because it is fixedly installed, the focal length cannot be adjusted, and the position cannot be rotated.

[0060] S4: adjusting the viewing angle of the camera to the preset position, calling the camera in sequence and pulling the video stream of the camera, performing abnormal event recognition processing on the video stream, and when an abnormal event is recognized, recording the abnormal event and the abnormal event position, the abnormal event position is the coordinate position of the mark point closest to the abnormal event, and the abnormal event position is recorded as the inspection point;

[0061] Specifically, the cameras on both sides of the river are processed in sequence. If each camera is a ball camera, it is necessary to set the ball camera to the preset position. Note that each ball camera may have more than one preset position. The cameras are called in sequence and the video streams of the cameras are pulled to identify and process abnormal events. When abnormal events are identified, including random stacking and occupation of water areas, illegal sewage discharge, floating garbage in rivers, wild fishing and swimming, and stranger invasion of key areas, the abnormal events and their locations are recorded. The location of the abnormal event is determined according to the location of the marking point described in S34. The location of the abnormal event is determined by judging the specific location of the abnormal event in the 3*3 grid. If the abnormal event occupies multiple grids at the same time, the one with the largest occupied area is taken, and finally the location of the abnormal event is set as the inspection point. The main purpose of this step is to identify abnormal events in the river, and to classify, locate and generate inspection points for the identified abnormal events. This step provides data support for the automatic generation of inspection routes in subsequent operations.

[0062] S5: importing the inspection route into the drone so that the drone performs inspections according to the inspection route, and after arriving at the inspection point, performs all-round video shooting and transmits the shot video to the monitoring center, wherein the inspection route is composed of various inspection points;

[0063] Specifically, the inspection route is imported into the drone. The first inspection route includes the coordinates of the blind spot position and the initially set inspection points. The coordinates of the blind spot position are obtained in the following way: after defining the water area recognition range of the camera, the blind spot position identified by the video is marked on the high-resolution satellite remote sensing image river map in combination with the range that the camera can illuminate, and the coordinates of the blind spot position are recorded. The blind spot is inspected on site to determine the inspection points and inspection routes that must be inspected. The principle of determining the points that must be inspected is key areas, such as water quality monitoring equipment installation points, water and rainfall monitoring station installation points, easy dumping of garbage, sewage outlets, wild fishing and swimming spots, etc. Figure 4 The figure shows abnormal sewage discharge from the sewage outlet. The drone conducts inspections according to the inspection route. After arriving at the inspection point, it takes all-round video shots and transmits the captured video and the coordinates of the inspection point to the monitoring center. The main purpose of this step is that the drone inspects and shoots videos to provide video materials for subsequent abnormal event identification. In addition, the route of the first inspection is determined by manual inspection to ensure that the initial inspection route is accurate and to determine the points that must be inspected, providing a basis for the subsequent automatic generation of the inspection route.

[0064] S6: Identify abnormal events in the video sent by the drone, and when an abnormal event is identified, record the abnormal event and the location of the abnormal event;

[0065] Specifically, the video sent by the drone is used to identify abnormal events. When an abnormal event is detected, the abnormal event and the coordinates of the inspection point are recorded. The main purpose of this step is to identify abnormal events and record the location of abnormal events to provide data support for the subsequent automatic generation of inspection routes.

[0066] S7: count abnormal events at each inspection point;

[0067] Specifically, statistics are collected for abnormal events at each inspection point. For example, at inspection point 1, the number of abnormal events such as illegal dumping and occupation of water areas, illegal sewage discharge, floating garbage in rivers, wild fishing and swimming, and intrusion of strangers in key areas is counted. The main purpose of this step is to count the abnormal events and provide data support for the subsequent automatic generation of inspection routes.

[0068] S8: If the frequency of abnormal events at a certain inspection point is higher than the first threshold, the abnormal event location is added to the inspection route, and the distance between adjacent inspection points is calculated. If the distance is less than the second threshold, the inspection points are merged, and the inspection route is updated in combination with the inspection points that must be inspected. This step may include the following sub-steps:

[0069] S81: retaining inspection points where the number of abnormal events occurring is higher than a first threshold;

[0070] Specifically, mobility abnormal events such as floating objects are eliminated, and the number of non-mobility abnormal events is counted. If the number of abnormal events at the inspection point is higher than the first threshold, generally speaking, the video is inspected at a fixed frequency during a fixed time period every day, and the drone is inspected on a weekly basis. Considering that the inspection frequency of drones is low, if an abnormal event occurs, it may be sporadic. If abnormal events occur in more than half of the inspection times, it can be considered that the frequency of the abnormal event is high. Therefore, it is more appropriate to use half of the drone inspection times as the first threshold.

[0071] S82: According to the coordinates of the inspection points, if the adjacent longitude or latitude is less than a second threshold, merge the inspection points and generate an inspection point list;

[0072] Specifically, the inspection points recorded after an abnormal event occurs during the inspection process may be close to each other, because the video exposure distance is relatively far. If the distance is close, it means that the distance setting of the inspection point is unreasonable and the video wastes inspection time. Therefore, the inspection points with similar distances need to be merged. The calculation formula for converting the longitude and latitude of two points to distance is as follows:

[0073] Assuming that the radius of the earth is R, for any point on the ground, assuming that its latitude and longitude are θ and φ respectively, then the conversion to the three-dimensional rectangular coordinate system is

[0074] ;

[0075] like Figure 2 As shown in the figure, assume that A, B, C, and D are four points on the earth's surface, and the latitude and longitude of point A are and ; The latitude and longitude of point B are and ; The coordinates of point C are and ; The coordinates of point D are and ; then quadrilateral ABCD is an isosceles trapezoid. Now we need to calculate the distance S between points A and C. Obviously

[0076] ;

[0077] By the law of cosines in ∆ABC we have:

[0078] ;

[0079] Similarly, in ∆ACD:

[0080] ;

[0081] Combining the above two equations to eliminate We can get:

[0082] ;

[0083] but:

[0084] ;

[0085] ;

[0086] but:

[0087] ;

[0088] So we have:

[0089] ;

[0090] ;

[0091] ;

[0092] S is the calculated distance between the two points. The distance between the two points is calculated based on the adjacent points. If the distance is less than the second threshold, the two coordinate points are merged. After merging, the average value of the coordinates of the two inspection points is used to take both inspection points into account. Generally speaking, the camera coverage distance is 100-200 meters, so the distance between the two points should be at least greater than 100 meters to be effective. The second threshold is recommended to be 100.

[0093] S83: adding the inspection points that must be inspected to the inspection point list;

[0094] Specifically, the inspection points that must be inspected are added to the inspection point list. The main purpose of this step is to ensure the rationality of the inspection route. Due to the existence of blind spots in surveillance videos, the areas with key monitoring need to be added as inspection points in the blind spots. The selection principle of the inspection points that must be inspected is the existence of key areas, such as water quality monitoring equipment installation points, water and rainfall monitoring station installation points, garbage dumping sites, sewage outlets, wild fishing and swimming spots, etc.

[0095] S84: generating a new inspection route by combining the longitude and latitude coordinates of the inspection points in the inspection point list and the coordinates of the starting point;

[0096] Specifically, the longitude and latitude of the inspection points in the inspection point list and the coordinates of the starting point are used to generate a new inspection route.

[0097] S85: Use the new inspection route to update the old inspection route.

[0098] Specifically, the old inspection route is replaced with a new optional route. Since the inspection route is generally stored in the monitoring center, the latest inspection route needs to be downloaded from the monitoring center every time the drone inspects. If it is not updated, the drone may still use the old route during the next inspection.

[0099] S9: Send the updated inspection route to the drone.

[0100] Specifically, the updated inspection route is sent to the drone. The main purpose of this step is to update the drone inspection route to ensure that the drone can perform inspections according to the predetermined route.

[0101] It can be seen from the above embodiments that the present application adopts a combination of video and drones, defines the camera recognition area and formulates the initial drone inspection route, identifies and processes abnormal events in the camera video and the video transmitted back by the drone, performs statistical analysis and calculation on abnormal events, optimizes the inspection route and automatically generates new drone inspection routes, thereby overcoming technical problems such as incomplete inspection coverage, relatively fixed inspection routes, safety risks for inspectors in extreme weather, random problem discovery, and poor timeliness, and thus achieves the technical effect of intelligent river patrol. By identifying abnormal events, classifying and counting them, and optimizing river patrol routes, it not only improves the work efficiency of inspectors, but also improves the real-time nature of abnormal event discovery, truly realizing intelligent river patrol.

[0102] Corresponding to the aforementioned embodiment of the intelligent river patrol method, the present application also provides an embodiment of an intelligent river patrol system.

[0103] Figure 5 is a block diagram of an intelligent river patrol system according to an exemplary embodiment. Figure 5 , applied to the monitoring center, the system includes:

[0104] Acquisition module 1, used to obtain high-resolution satellite remote sensing image river map;

[0105] Marking module 2, used to mark the position of the camera on the high-resolution satellite remote sensing image river map to obtain the coordinates of the camera;

[0106] Position determination module 3, used to set the inspection range of each camera respectively, and mark the marking points according to the grid in the field of view of each camera, and determine the coordinate position of the marking point on the high-resolution satellite remote sensing image river map and the current corresponding viewing angle parameters of the camera in combination with the coordinates of the camera, and save them to the camera preset position;

[0107] The first event recognition module 4 is used to adjust the viewing angle of the camera to the position corresponding to the viewing angle parameter, call the camera in sequence and pull the video stream of the camera, perform recognition processing on the video stream, and when an abnormal event is recognized, record the abnormal event and the abnormal event position, the abnormal event position is the coordinate position of the mark point closest to the abnormal event, and the abnormal event position is recorded as a patrol point;

[0108] Route import module 5, used to import the inspection route into the drone, so that the drone can inspect according to the inspection route, take all-round video after arriving at the inspection point, and transmit the video to the monitoring center. The inspection route is composed of various inspection points;

[0109] The second event recognition module 6 is used to recognize abnormal events in the video sent by the drone, and when an abnormal event is recognized, record the abnormal event and the abnormal event location;

[0110] Statistics module 7, used to count abnormal events at each inspection point;

[0111] The route updating module 8 is used to add the abnormal event location to the inspection route if the frequency of abnormal events at a certain inspection point in the original inspection route is higher than a first threshold, calculate the distance between adjacent inspection points, merge the inspection points if the distance is less than a second threshold, and update the inspection route in combination with the inspection points that must be inspected;

[0112] The sending module 9 is used to send the updated inspection route to the drone.

[0113] Regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0114] For the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The system embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application. A person of ordinary skill in the art can understand and implement it without creative work.

[0115] Accordingly, the present application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned intelligent river patrol method. Figure 6 As shown in FIG. 1 , a hardware structure diagram of an intelligent river patrol system provided by an embodiment of the present invention is provided for any device with data processing capability, except Figure 6 In addition to the processor, memory, DMA controller, disk, and non-volatile memory shown, any device with data processing capabilities in the system in the embodiment may also include other hardware based on the actual functions of the device with data processing capabilities, which will not be described in detail.

[0116] Accordingly, the present application also provides a computer-readable storage medium on which computer instructions are stored, and when the instructions are executed by a processor, the intelligent river patrol method as described above is implemented. The computer-readable storage medium can be an internal storage unit of any device with data processing capabilities described in any of the aforementioned embodiments, such as a hard disk or a memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), an SD card, a flash card (Flash Card), etc. equipped on the device. Furthermore, the computer-readable storage medium can also include both an internal storage unit and an external storage device of any device with data processing capabilities. The computer-readable storage medium is used to store the computer program and other programs and data required by any device with data processing capabilities, and can also be used to temporarily store data that has been output or is to be output.

[0117] Those skilled in the art will readily appreciate other embodiments of the present application after considering the description and practicing the contents disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application. The description and examples are intended to be exemplary only.

[0118] It should be understood that the present application is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. An intelligent river patrol method, characterized in that: Applied to monitoring centers, including: Obtain high-resolution satellite remote sensing imagery river maps; Marking the position of the camera on the high-resolution satellite remote sensing image river map to obtain the coordinates of the camera; The inspection range of each camera is set respectively, and the marking points are marked in the field of view of each camera according to the grid. Combined with the coordinates of the camera, the coordinate position of the marking point on the high-resolution satellite remote sensing image river map and the current corresponding viewing angle parameters of the camera are determined and saved in the camera preset position, and the preset position number is recorded; The viewing angle of the camera is adjusted to the preset position, the camera is called in sequence and the video stream of the camera is pulled, and the video stream is processed for abnormal event recognition. When an abnormal event is recognized, the abnormal event and the abnormal event position are recorded. The abnormal event position is the coordinate position of the mark point closest to the abnormal event, and the abnormal event position is recorded as a patrol point; Importing inspection routes into the drone so that the drone conducts inspections along the inspection routes, and after arriving at the inspection points, performs all-round video shooting and transmits the shot videos to the monitoring center. The inspection routes are composed of various inspection points. Identify abnormal events in the video sent by the drone. When an abnormal event is identified, record the abnormal event and its location. Statistics of abnormal events at each inspection point; If the frequency of abnormal events at a certain inspection point is higher than the first threshold, the abnormal event location is added to the inspection route, and the distance between adjacent inspection points is calculated. If the distance is less than the second threshold, the inspection points are merged, and the inspection route is updated in combination with the inspection points that must be inspected; Sending the updated inspection route to the drone; Among them, the inspection range of each camera is set respectively, and the marking points are marked according to the grid in the field of view of each camera. Combined with the coordinates of the camera, the coordinate position of the marking point on the high-resolution satellite remote sensing image river map and the current corresponding viewing angle parameters of the camera are determined and saved in the camera preset position, and the preset position number is recorded, including: Adjust the camera's viewing angle and focal length to ensure that the river to be monitored is covered; Obtain a photo taken by the camera; Delineate the area to be inspected and identified on the photo; Marking points on the photo according to a grid, and determining the coordinate positions of the marked points on the high-resolution satellite remote sensing image river map in combination with the coordinates of the camera; Record the viewing angle parameters of the camera, save them in the camera preset position, and record the preset position number; Among them, if the frequency of abnormal events at a certain inspection point is higher than the first threshold, the abnormal event location is added to the inspection route, and the distance between adjacent inspection points is calculated. If the distance is less than the second threshold, the inspection points are merged, and the inspection route is updated in combination with the inspection points that must be inspected, including: Keep the inspection points where the number of abnormal events is higher than the first threshold; According to the coordinates of the inspection points, the distance between adjacent inspection points is calculated, and if the distance is less than a second threshold, the inspection points are merged and an inspection point list is generated; Add the inspection points that must be inspected to the inspection point list; Combining the longitude and latitude of the inspection point in the inspection point list with the coordinates of the starting point, a new inspection route is generated; Update old inspection routes with new inspection routes.

2. The intelligent river patrol method according to claim 1, characterized in that: The first inspection route includes the coordinates of the blind spot location and the initial set inspection points.

3. The intelligent river patrol method according to claim 2, characterized in that: The coordinates of the blind spot position are obtained by: Define the water area recognition range of the camera, mark the blind spot position of video recognition on the high-resolution satellite remote sensing image river map, and record the coordinates of the blind spot position.

4. An intelligent river patrol system, characterized in that: Applied to monitoring centers, including: Acquisition module, used to obtain high-resolution satellite remote sensing image river maps; A marking module, used to mark the position of the camera on the high-resolution satellite remote sensing image river map to obtain the coordinates of the camera; A position determination module is used to set the inspection range of each camera respectively, and mark the marking points according to the grid within the field of view of each camera, and determine the coordinate position of the marking point on the high-resolution satellite remote sensing image river map and the current corresponding viewing angle parameters of the camera in combination with the coordinates of the camera; A first event recognition module is used to adjust the viewing angle of the camera to the position corresponding to the viewing angle parameter, call the camera in sequence and pull the video stream of the camera, perform recognition processing on the video stream, and when an abnormal event is recognized, record the abnormal event and the abnormal event position, the abnormal event position is the coordinate position of the mark point closest to the abnormal event, and the abnormal event position is recorded as a patrol point; The route import module is used to import the inspection route into the drone so that the drone can inspect according to the inspection route, take all-round video after arriving at the inspection point, and transmit the video to the monitoring center. The inspection route is composed of various inspection points. The second event recognition module is used to recognize abnormal events in the video sent by the drone, and when an abnormal event is recognized, the abnormal event and the abnormal event location are recorded; Statistics module, used to count abnormal events at each inspection point; The route update module is used to add the abnormal event location to the inspection route if the frequency of abnormal events at a certain inspection point in the original inspection route is higher than the first threshold, calculate the distance between adjacent inspection points, merge the inspection points if the distance is less than the second threshold, and update the inspection route in combination with the inspection points that must be inspected; A sending module, used for sending the updated inspection route to the drone; Among them, the inspection range of each camera is set respectively, and the marking points are marked according to the grid in the field of view of each camera. Combined with the coordinates of the camera, the coordinate position of the marking point on the high-resolution satellite remote sensing image river map and the current corresponding viewing angle parameters of the camera are determined and saved in the camera preset position, and the preset position number is recorded, including: Adjust the camera's viewing angle and focal length to ensure that the river to be monitored is covered; Obtain a photo taken by the camera; Delineate the area to be inspected and identified on the photo; Marking points on the photo according to a grid, and determining the coordinate positions of the marked points on the high-resolution satellite remote sensing image river map in combination with the coordinates of the camera; Record the viewing angle parameters of the camera, save them in the camera preset position, and record the preset position number; Among them, if the frequency of abnormal events at a certain inspection point is higher than the first threshold, the abnormal event location is added to the inspection route, and the distance between adjacent inspection points is calculated. If the distance is less than the second threshold, the inspection points are merged, and the inspection route is updated in combination with the inspection points that must be inspected, including: Keep the inspection points where the number of abnormal events is higher than the first threshold; According to the coordinates of the inspection points, the distance between adjacent inspection points is calculated, and if the distance is less than a second threshold, the inspection points are merged and an inspection point list is generated; Add the inspection points that must be inspected to the inspection point list; Combining the longitude and latitude of the inspection point in the inspection point list with the coordinates of the starting point, a new inspection route is generated; Update old inspection routes with new inspection routes.

5. An electronic device, characterized in that: include: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 3.

6. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images