Abnormal inspection methods, devices, equipment and storage media
By acquiring the location of abnormal objects in the target image and adjusting the drone's flight path to avoid collisions, the problem of drone collisions at the intersection of multiple areas has been solved, achieving safe and efficient inspection.
Patent Information
- Application Number
- CN202311774739.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-21
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-12-21
AI Technical Summary
In existing technologies, when a drone experiences equipment or facility malfunctions at the intersection of multiple regions, it can easily lead to the drone crossing regions to investigate abnormal information, resulting in collisions with drones in other regions.
By acquiring multiple target locations corresponding to abnormal objects in the target image, the flight path of the UAV is adjusted so that the target flight path does not intersect with the preset flight path of each area within the same time period, or the UAV does not cross areas for inspection, thus avoiding collisions.
This effectively avoids collisions between drones at the intersection of multiple areas, improving the safety and efficiency of inspections.
Smart Images

Figure CN117762158B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of communication technology, and in particular to an anomaly inspection method, apparatus, device, and storage medium. Background Technology
[0002] Unmanned aerial vehicle (UAV) inspection refers to the process by which UAVs inspect various equipment, buildings, roads, bridges, and pipelines along flight paths to identify potential problems and address them promptly, thereby ensuring the safety and normal operation of equipment and facilities. Current technologies typically simulate precise terrain conditions and determine flight paths based on the UAV's flight path length and altitude.
[0003] However, with existing technology, a single drone typically inspects one area. When equipment or facilities malfunction at the boundary of multiple areas, drones may cross areas to investigate abnormal information, potentially leading to collisions with drones from other areas. Summary of the Invention
[0004] This application provides an anomaly inspection method, apparatus, device, and storage medium to at least address the problem in existing technologies where, when equipment or facility anomalies occur at the boundaries of multiple areas, drones may cross regions to investigate anomalies, potentially leading to collisions with drones in other areas. The technical solution of this application is as follows:
[0005] Firstly, an anomaly inspection method is provided, comprising: acquiring multiple target locations corresponding to anomalies in a target image. The target image is obtained by a first inspection device inspecting a first region, which is the region inspected by the first inspection device according to a preset route corresponding to the first inspection device. The preset route corresponding to the first inspection device is adjusted according to the multiple target locations to obtain a first route of the first inspection device. At least one target inspection region to which the multiple target locations belong is determined. When there are multiple target inspection regions, a preset route corresponding to each second region is acquired in at least one second region. The second region is the target inspection region other than the first region among the multiple target inspection regions. Based on the preset route corresponding to each second region and the first route, a target route for inspecting the anomalies is determined. The target route does not intersect with the preset route corresponding to each second region within the same time period, or the inspection device corresponding to the target route does not perform inspections across regions.
[0006] In one possible implementation, determining the target route for inspecting the abnormal object based on the preset route and the first route corresponding to each second region includes: determining the first moment when the inspection equipment for each second region inspects the abnormal object according to the preset route corresponding to each second region, thus obtaining the first moment for each second region; determining the first position in each second region, where the first position is the target position; determining the second moment when the first inspection equipment inspects the first position in each second region, thus obtaining the second moment for each second region; determining the duration between the first moment and the second moment for each second region, thus obtaining the duration for each second region; and determining the target route for inspecting the abnormal object based on the duration for each second region.
[0007] In one possible implementation, determining the target route for inspecting abnormal objects based on the duration corresponding to each second region includes: if the duration corresponding to each second region is greater than a preset duration, determining a first route as the target route; if at least one second region has a duration less than or equal to a preset duration, determining a second route corresponding to each second region based on a first position within each second region; determining a third route based on target positions belonging to the first region from among multiple target positions; and finally determining the second and third routes corresponding to each second region as the target routes.
[0008] In one possible implementation, determining the first position in each second region includes: determining, based on multiple target positions and each second region, the target positions belonging to each second region as second positions in each second region. If there is only one second position in each second region, the second position in each second region is determined as the first position in each second region. If there are multiple second positions in each second region, any one of the multiple second positions is determined as the first position in each second region.
[0009] In one possible implementation, the above-mentioned acquisition of multiple target locations corresponding to abnormal objects in a target image includes: performing background removal processing on the target image according to a preset classification algorithm to obtain a first image; determining whether the object in the first image is in an abnormal state based on the first image and multiple preset images; the preset images include: images of objects in a normal state, and / or images of objects in an abnormal state; if the object in the first image is in an abnormal state, the object in the first image is identified as an abnormal object; performing coordinate transformation processing on the first image to obtain multiple third locations corresponding to the abnormal object; and performing edge extraction processing on the multiple third locations to obtain multiple target locations corresponding to the abnormal object.
[0010] In one possible implementation, the method further includes: when the number of target inspection areas is one, determining the first route as the target route.
[0011] Secondly, an anomaly inspection device is provided, comprising: an acquisition unit, a processing unit, and a determination unit. The acquisition unit is used to acquire multiple target locations corresponding to anomalies in a target image. The target image is obtained by a first inspection device inspecting a first region, which is the region inspected by the first inspection device according to a preset route corresponding to the first inspection device. The processing unit is used to adjust the preset route corresponding to the first inspection device based on the multiple target locations to obtain a first route of the first inspection device. The determination unit is used to determine at least one target inspection region to which the multiple target locations belong. The acquisition unit is further used to acquire a preset route corresponding to each of at least one second region when there are multiple target inspection regions. The second region is the target inspection region other than the first region among the multiple target inspection regions. The determination unit is further used to determine a target route for inspecting the anomaly based on the preset route corresponding to each second region and the first route. The target route does not intersect with the preset route corresponding to each second region within the same time period, or the inspection device corresponding to the target route does not perform inspections across regions.
[0012] In one possible implementation, the determining unit is specifically configured to: determine, based on a preset route corresponding to each second area, the first moment when the inspection equipment in each second area inspects the abnormal object according to the preset route corresponding to each second area, thus obtaining the first moment corresponding to each second area; determine the first position in each second area. The first position is the target position in each second area; based on the first route, determine the second moment when the first inspection equipment inspects the first position in each second area, thus obtaining the second moment corresponding to each second area; determine the duration between the first moment and the second moment in each second area, thus obtaining the duration corresponding to each second area; and based on the duration corresponding to each second area, determine the target route for inspecting the abnormal object.
[0013] In one possible implementation, the determining unit is specifically configured to: determine a first route as a target route when the duration corresponding to each second region is greater than a preset duration; determine a second route corresponding to each second region based on a first position within each second region when at least one second region has a duration less than or equal to a preset duration; determine a third route based on a target position belonging to the first region from among multiple target positions; and determine the second and third routes corresponding to each second region as the target routes.
[0014] In one possible implementation, the determining unit is specifically configured to: determine, based on multiple target locations and each second region, a target location belonging to each second region as a second location within each second region. If there is only one second location in each second region, determine the second location in each second region as a first location within each second region. If there are multiple second locations in each second region, determine any one of the multiple second locations as a first location within each second region.
[0015] In one possible implementation, the acquisition unit is specifically used for: performing background removal processing on the target image according to a preset classification algorithm to obtain a first image; determining whether an object in the first image is in an abnormal state based on the first image and multiple preset images; the preset images include: images of objects in a normal state, and / or images of objects in an abnormal state; if the object in the first image is in an abnormal state, the object in the first image is identified as an abnormal object; performing coordinate transformation processing on the first image to obtain multiple third positions corresponding to the abnormal object; and performing edge extraction processing on the multiple third positions to obtain multiple target positions corresponding to the abnormal object.
[0016] In one possible implementation, the determining unit is further configured to: determine the first route as the target route when the number of target inspection areas is one.
[0017] Thirdly, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions. The processor is configured to execute instructions to implement the methods described in the first aspect and any possible implementation thereof.
[0018] Fourthly, a computer-readable storage medium is provided, wherein when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the methods described in the first aspect and any possible implementation thereof.
[0019] Fifthly, a computer program product is provided, comprising computer instructions that, when executed on an electronic device, cause the electronic device to perform the method described in the first aspect and any possible implementation thereof.
[0020] The technical solution of the first aspect provided by this application brings at least the following beneficial effects: In the prior art, when equipment or facility malfunctions occur at the boundary of multiple areas, drones may cross regions to investigate abnormal information, leading to collisions with drones in other areas. This application obtains multiple target locations corresponding to abnormal objects in a target image. The target image is obtained by a first inspection device inspecting a first area, which is the area inspected by the first inspection device according to a preset flight path. Then, the preset flight path corresponding to the first inspection device is adjusted based on the multiple target locations to obtain the first flight path of the first inspection device.
[0021] Next, at least one target inspection area is identified to which multiple target locations belong. Then, when there are multiple target inspection areas, a preset route corresponding to each of the at least one second area is obtained. The second area refers to the target inspection areas other than the first area among the multiple target inspection areas. This allows us to determine that the target object is located at the boundary of multiple inspection areas. Further, based on the preset route corresponding to each second area and the first route, a target route for inspecting the abnormal object is determined. The target route does not intersect with the preset route corresponding to each second area within the same time period, or the inspection equipment corresponding to the target route does not cross areas for inspection. This ensures that the determined target route effectively avoids collisions between inspection equipment.
[0022] It should be noted that the technical effects of any of the implementation methods in aspects two through five can be found in the technical effects of the corresponding implementation methods in aspect one, and will not be repeated here.
[0023] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description
[0024] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application, and do not constitute an undue limitation of this application.
[0025] Figure 1 This is a schematic diagram of the structure of an unmanned aerial vehicle (UAV) inspection system according to an exemplary embodiment;
[0026] Figure 2 This is a schematic diagram of the structure of an abnormal inspection system according to an exemplary embodiment;
[0027] Figure 3 This is a flowchart illustrating an abnormal inspection method according to an exemplary embodiment;
[0028] Figure 4 This is a flowchart illustrating yet another abnormal inspection method according to an exemplary embodiment;
[0029] Figure 5 This is a flowchart illustrating yet another abnormal inspection method according to an exemplary embodiment;
[0030] Figure 6 This is a flowchart illustrating yet another abnormal inspection method according to an exemplary embodiment;
[0031] Figure 7 This is a flowchart illustrating yet another abnormal inspection method according to an exemplary embodiment;
[0032] Figure 8 This is a flowchart illustrating yet another abnormal inspection method according to an exemplary embodiment;
[0033] Figure 9 This is a flowchart illustrating yet another abnormal inspection method according to an exemplary embodiment;
[0034] Figure 10 This is a block diagram illustrating an abnormality inspection device according to an exemplary embodiment;
[0035] Figure 11 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation
[0036] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.
[0037] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.
[0038] Before providing a detailed introduction to the abnormal inspection method provided in this application, let me briefly introduce the technical background involved in this application.
[0039] Unmanned aerial vehicle (UAV) inspection refers to the use of UAV technology to inspect and patrol various facilities such as equipment, buildings, roads, bridges, and pipelines to identify potential problems and address them promptly, thereby ensuring the safety and normal operation of these facilities. Sensor-integrated UAVs combine multiple sensing methods (such as vision, hearing, and touch) with UAV technology to achieve multimodal perception and intelligent control of the environment and targets. Specifically, sensor-integrated UAVs can acquire environmental information through various sensors, including images, sound, temperature, and humidity, and process and analyze this information using artificial intelligence algorithms to achieve intelligent control and autonomous decision-making for the UAV.
[0040] Currently, existing methods for determining drone flight paths include the following: 1. Obtaining map information of the area to be predicted based on existing map data and establishing a target mathematical model. Then, constructing a cost function based on the target mathematical model, the drone's flight environment, and drone information, and planning the drone flight path using the artificial bee colony algorithm and the cost function. 2. Simulating an accurate terrain environment by performing cubic interpolation on terrain data, and establishing a drone trajectory planning model in conjunction with the inspection task. This method comprehensively considers parameters such as drone path length, flight altitude, obstacle avoidance flight costs, and smoothing costs, reducing the drone's flight costs.
[0041] III. An objective function is constructed based on environmental threat costs and UAV flight fuel costs. The area to be planned is divided into grids, and an immune cloning algorithm is used to calculate and update antibody populations for the node sets corresponding to the grids, obtaining the optimal trajectory corresponding to the optimal antibody. IV. For the problem of UAV cooperative trajectory planning in dynamic obstacle environments, a feedback strategy is proposed based on the Q-learning algorithm to ensure that UAVs master guidance information and risk awareness during training, achieving low-cost and risk-free cooperative trajectory planning for multiple UAVs. V. For UAV trajectory planning in urban low-altitude environments, a three-dimensional tangent graph method is used to generate three obstacle avoidance sub-paths for the obstacle space. Combined with heuristic rules, this assists UAVs in bypassing obstacles from the sides or above, ensuring that UAVs successfully reach the inspection endpoint.
[0042] While the above methods can inspect target items, drones will directly inspect abnormal information when they encounter it. If the abnormal information is located at the boundary of different areas, it is easy for drones in different areas to conduct cross-area inspections, which may lead to drone collisions and repeated inspections of the same abnormal information.
[0043] The existing technology, "A Method and System for Safety Detection of Inspection Paths for Close-Range UAV Flight," is a method for determining inspection paths. This method includes: collecting vector data of obstacles in an industrial park and storing it in a database; setting a bottom buffer zone based on a safety radius r; obtaining the UAV's inspection path R and projecting it onto the ground plane to obtain a polyline L; extracting the bottom buffer zones that intersect with L to form a set of potential obstacles and corresponding obstacle buffer zones; sequentially judging the safety of road segments formed by two adjacent path points in the inspection path R to detect the safety of the entire inspection path R; if the inspection path R is unsafe, calculating the areas of each obstacle that affect the safety of the inspection path R and highlighting them in the corresponding 3D scene. This method can pre-determine the safety of the entire inspection path and can also determine the collision risk between the inspection path and multiple obstacles simultaneously, making it applicable to scenarios where UAV inspections in factories need to navigate between equipment and pipelines.
[0044] Before providing a detailed introduction to the anomaly inspection method provided in this application, let's first briefly introduce the implementation environment (implementation architecture) involved in this application.
[0045] The anomaly inspection equipment provided in this application embodiment can be applied to unmanned aerial vehicle (UAV) inspection systems. Figure 1 This is a schematic diagram of the structure of a drone inspection system. Figure 1 As shown, the UAV inspection system 10 includes: a UAV device 11 and a processing platform 12. The UAV device 11 includes a first image receiving module 111, a first transmitting module 112, and a first data receiving module 113. The processing platform 12 includes: a second image receiving module 121, a processing module 122, a second transmitting module 123, a storage module 124, and a display module 125.
[0046] The first image receiving module 111 is used to receive the target image sent by the camera.
[0047] The first sending module 112 is used to send the target image to the second image receiving module 121 in the processing platform 12.
[0048] The first data receiving module 113 is used to receive the target route sent by the processing platform 12.
[0049] The second image receiving module 121 is used to receive the target image sent by the first sending module 112.
[0050] The processing module 122 is used to process the target image to obtain the target flight path.
[0051] The second sending module 123 is used to send the target route to the first data receiving module 113 in the UAV device 11.
[0052] Storage module 124 is used to store target images and target flight paths.
[0053] Display module 125 is used to display the space model and UAV parameters.
[0054] The abnormal inspection method provided in this application embodiment can also be applied to an abnormal inspection system. Figure 2 A schematic diagram of one structure of this anomaly inspection system is shown. For example... Figure 2 As shown, the anomaly inspection system 20 includes an anomaly inspection device 21 and an electronic device 22. The anomaly inspection device 21 is connected to the electronic device 22. The anomaly inspection device 21 and the electronic device 22 can be connected by wired or wireless means, and this embodiment does not limit the connection.
[0055] The anomaly inspection device 21 can be used to interact with the electronic device 22, for example, to receive target images sent by the electronic device 22, and to send target routes for inspecting anomalies to the electronic device 22.
[0056] The anomaly inspection device 21 can also be used to process the acquired target image. For example, it can remove the background of the target image according to a preset classification algorithm to obtain a first image. Based on the first image and multiple preset images, it can determine whether the object in the first image is in an abnormal state. The preset images include: images where the object is in a normal state, and / or images where the object is in an abnormal state. If the object in the first image is in an abnormal state, the object in the first image is identified as an abnormal object. The first image is subjected to coordinate transformation processing to obtain multiple third positions corresponding to the abnormal object. Edge extraction processing is performed on the multiple third positions to obtain multiple target positions corresponding to the abnormal object.
[0057] The anomaly inspection device 21 can also be used to acquire multiple target locations corresponding to anomalies in a target image. The target image is obtained by a first inspection device inspecting a first region, which is the region inspected by the first inspection device according to a preset route. The preset route corresponding to the first inspection device is adjusted based on the multiple target locations to obtain the first route of the first inspection device. At least one target inspection region to which the multiple target locations belong is determined. When there are multiple target inspection regions, a preset route corresponding to each of at least one second region is acquired. The second region is the target inspection region other than the first region among the multiple target inspection regions. Based on the preset route corresponding to each second region and the first route, a target route for inspecting the anomaly is determined. The target route does not intersect with the preset route corresponding to each second region within the same time period, or the inspection device corresponding to the target route does not perform inspections across regions.
[0058] Electronic device 22 can be used to interact with anomaly inspection device 21, for example, to send target images to anomaly inspection device 21 and to receive target routes for inspecting abnormal objects sent by anomaly inspection device 21.
[0059] Optionally, the electronic device can be a physical machine, such as a desktop computer, mobile phone, tablet computer, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), and other terminal devices. The electronic device can also be a server or a server cluster composed of multiple servers.
[0060] Optionally, the above-mentioned anomaly inspection device 21 can also achieve the functions to be performed by a virtual machine (VM) deployed on a physical machine.
[0061] It should be noted that the abnormal inspection device 21 and the electronic device 22 can be independent devices or integrated into the same device. This application does not make specific limitations in this regard.
[0062] When the anomaly inspection device 21 and the electronic device 22 are integrated into the same device, the communication method between the anomaly inspection device 21 and the electronic device 22 is the same as the communication between modules within the device. In this case, the communication process between the two is the same as the communication process between the anomaly inspection device 21 and the electronic device 22 when they are independent of each other.
[0063] In the following embodiments provided in this application, the abnormal inspection device 21 and the electronic device 22 are described as being set up independently of each other.
[0064] For ease of understanding, the abnormal inspection method provided in this application will be described in detail below with reference to the accompanying drawings.
[0065] Figure 3 This is a flowchart illustrating an anomaly inspection method according to an exemplary embodiment. This method can be applied to electronic devices or anomaly inspection devices connected to electronic devices. Furthermore, this method can also be applied to devices similar to electronic devices or anomaly inspection devices. The following description uses the application of this method to an electronic device as an example to illustrate the method. Figure 3 As shown, this anomaly inspection method includes the following steps:
[0066] S301. The electronic device acquires multiple target locations corresponding to abnormal objects in the target image.
[0067] The target image is obtained by the first inspection device inspecting the first area, which is the area inspected by the first inspection device according to the preset route corresponding to the first inspection device.
[0068] One possible implementation is that the electronic device divides a preset inspection area into multiple inspection sub-areas and equips each sub-area with an inspection device. Then, the electronic device determines a preset route for each inspection device, enabling the inspection device to inspect the sub-area according to the preset route and send the acquired images to the electronic device in real time.
[0069] Then, the electronic device acquires the target image of the first inspection area inspected by the first inspection device. Next, the electronic device performs background removal processing on the target image according to a preset classification algorithm to obtain the first image. Further, the electronic device processes the first image to obtain multiple target locations corresponding to abnormal objects in the target image.
[0070] For example, the inspection equipment could be a drone.
[0071] For example, the electronic device divides the preset inspection area into multiple inspection sub-regions based on the drone's power parameters, energy parameters, and image clarity parameters, and constructs a spatial coordinate model based on the multiple inspection sub-regions.
[0072] For example, multiple target locations can be edge points of the abnormal object, or multiple target locations can be points within the edge of the abnormal object.
[0073] The specific implementation of this step can be found in the subsequent description of the embodiments of this application, and will not be repeated here.
[0074] Understandably, by acquiring the images collected by the inspection equipment in real time, real-time image information of the inspection area can be obtained, which facilitates the supervision of the inspection area.
[0075] S302. The electronic equipment adjusts the preset route corresponding to the first inspection equipment according to multiple target locations to obtain the first route of the first inspection equipment.
[0076] As one possible implementation, the electronic device determines the first route of the first inspection device based on multiple target locations and the preset route corresponding to the first inspection device.
[0077] It should be noted that the preset route corresponding to the first inspection equipment is pre-set. The preset route corresponding to the first inspection equipment can be determined based on the inspection items, the take-off point of the first inspection equipment, the landing point of the first inspection equipment, and the first area.
[0078] S303. The electronic device determines at least one target inspection region to which a plurality of target positions belong.
[0079] As an example, the electronic device determines the inspection sub-regions to which the target positions belong as the target inspection regions according to the plurality of target positions and a plurality of inspection sub-regions.
[0080] As an example, the electronic device constructs a spatial coordinate model according to the plurality of inspection sub-regions. The electronic device determines coordinates of the plurality of target positions in the spatial coordinate model, and determines at least one target inspection region to which the plurality of target positions belong according to the region range of each inspection sub-region in the plurality of inspection sub-regions in the spatial coordinate model.
[0081] As an example, the electronic device divides a preset region into 4 inspection sub-regions with the same region range, and constructs a spatial coordinate model according to the 4 inspection sub-regions, where the first region is (0-5, 0-5, 0-5), the second region is (5-10, 0-5, 0-5), the third region is (0-5, 5-10, 0-5), and the fourth region is (5-10, 5-10, 0-5). Taking a plurality of target positions which are respectively target position 1 (x1, y1, z1) where 0<x1<5, 0<y1<5, 0<z1<5, and target position 2 (x2, y2, z2) where 5<x2<10, 0<y2<5, 0<z2<5 as an example, the electronic device determines that the region to which target position 1 belongs is the first region, and the region to which target position 2 belongs is the second region, and determines the first region and the second region as target inspection regions, so as to obtain at least one target inspection region to which the plurality of target positions belong.
[0082] S304. When the number of the target inspection regions is multiple, the electronic device obtains a preset route corresponding to each of the at least one second region.
[0083] The second regions are target inspection regions other than the first region in the plurality of target inspection regions.
[0084] As a possible implementation, the electronic device determines target inspection regions other than the first region in the plurality of target inspection regions as second regions, to obtain at least one second region. After that, the electronic device obtains the preset route corresponding to each of the at least one second region.
[0085] It should be noted that, in the embodiments of the present application, the electronic device needs to execute S303 first and then execute S304. Meanwhile, the present application does not limit the execution order of S302 and S303. For example, the electronic device may execute S302 and S303 at the same time, the electronic device may also execute S302 first and then execute S303, and the electronic device may further execute S303 first and then execute S302.
[0086] S305. The electronic equipment determines the target route for inspecting abnormal objects based on the preset route and the first route corresponding to each second area.
[0087] Among these conditions, the target route does not intersect with the preset route corresponding to each second area within the same time period, or the inspection equipment corresponding to the target route does not conduct inspections across areas.
[0088] As one possible implementation, the electronic device determines the first moment when the inspection device in each second area inspects the abnormal object according to the preset route corresponding to each second area, thus obtaining the first moment for each second area. Then, the electronic device determines the first position in each second area. Next, based on the first route, the electronic device determines the second moment when the first inspection device inspects the first position in each second area, thus obtaining the second moment for each second area. Then, the electronic device determines the duration between the first moment and the second moment for each second area, thus obtaining the duration for each second area. Further, based on the duration for each second area, the electronic device determines the target route for inspecting the abnormal object.
[0089] The specific implementation of this step can be found in the subsequent description of the embodiments of this application, and will not be repeated here.
[0090] It is understandable that when equipment or facilities malfunction at the boundary of multiple areas using existing technology, drones may cross areas to investigate abnormal information, potentially leading to collisions with drones in other areas. This application obtains multiple target locations corresponding to abnormal objects in a target image. The target image is obtained by a first inspection device inspecting a first area, which is the area inspected by the first inspection device according to a preset flight path. Subsequently, the preset flight path corresponding to the first inspection device is adjusted based on the multiple target locations to obtain the first flight path of the first inspection device.
[0091] Next, at least one target inspection area is identified to which multiple target locations belong. Then, when there are multiple target inspection areas, a preset route corresponding to each of the at least one second area is obtained. The second area refers to the target inspection areas other than the first area among the multiple target inspection areas. This allows us to determine that the target object is located at the boundary of multiple inspection areas. Further, based on the preset route corresponding to each second area and the first route, a target route for inspecting the abnormal object is determined. The target route does not intersect with the preset route corresponding to each second area within the same time period, or the inspection equipment corresponding to the target route does not cross areas for inspection. This ensures that the determined target route effectively avoids collisions between inspection equipment.
[0092] In some embodiments, during the inspection of abnormal objects, to avoid collisions between inspection devices, such as... Figure 4 As shown, the above S305 can be implemented in the following manner:
[0093] S401. The electronic equipment determines the first moment when the inspection equipment in each second area inspects the abnormal object according to the preset route corresponding to each second area, based on the preset route corresponding to each second area, and obtains the first moment corresponding to each second area.
[0094] S402, The electronic device determines the first position in each second area.
[0095] The first position is the target position in each of the second regions.
[0096] As one possible implementation, the electronic device determines a second position within each second region based on multiple target locations and each second region. Then, the electronic device determines a first position within each second region based on the second position within each second region.
[0097] The specific implementation method of this step can be referred to in the subsequent description of the embodiments of this application, and will not be repeated here.
[0098] S403. The electronic equipment determines the second time when the first inspection equipment inspects the first position in each second area according to the first route, and obtains the second time corresponding to each second area.
[0099] S404. The electronic device determines the duration between the first time corresponding to each second region and the second time corresponding to each second region, and obtains the duration corresponding to each second region.
[0100] S405. The electronic equipment determines the target route for inspecting abnormal objects based on the duration corresponding to each second zone.
[0101] As one possible implementation, if the duration corresponding to each second region is greater than a preset duration, the electronic device determines the first route as the target route. Then, if in at least one second region the duration corresponding to a second region is less than or equal to the preset duration, the electronic device determines the second route corresponding to each second region based on the first position within each second region. Next, the electronic device determines the third route based on the target position belonging to the first region from among multiple target positions. Further, the electronic device determines the second and third routes corresponding to each second region as the target routes.
[0102] The specific implementation method of this step can be referred to in the subsequent description of the embodiments of this application, and will not be repeated here.
[0103] Understandably, the first moment is the time when the inspection equipment corresponding to each second area inspects abnormal objects according to the preset route for each second area, and the second moment is the time when the first inspection equipment inspects the first position in each second area according to the first route. This allows for an accurate determination of the time between the time when the first inspection equipment inspects abnormal objects across areas according to the first route and the time when the inspection equipment corresponding to the second area inspects abnormal objects within the second area according to the preset route. This improves the efficiency of subsequently determining the target route based on the time between the first and second moments.
[0104] In some embodiments, during the inspection of abnormal objects, to avoid collisions between inspection devices, such as... Figure 5 As shown, the above S405 can be implemented in the following manner:
[0105] S501. If the duration of each second area is longer than the preset duration, the electronic device will determine the first route as the target route.
[0106] S502, if the electronic device has a second route corresponding to at least one second region whose duration is less than or equal to a preset duration, it determines the second route corresponding to each second region based on the first position in each second region.
[0107] S503, the electronic equipment determines the third route based on the target location belonging to the first area among multiple target locations.
[0108] S504. The electronic equipment determines the second and third routes corresponding to each second area as the target routes.
[0109] For example, the electronic device sends a second route corresponding to each second area to the inspection device corresponding to that second area, so that the inspection device in each second area can inspect the abnormal objects located in each second area. The inspection device in each second area sends the images collected after inspection to the electronic device. Then, the electronic device sends a third route to the first inspection device, so that the first inspection device can inspect the abnormal objects according to the third route. The first inspection device sends the images collected after inspection to the electronic device. The electronic device receives the images collected after inspection from the inspection devices in each second area and the images collected after inspection from the first inspection device, and stitches the images collected by the inspection devices in each second area and the images collected by the first inspection device together to obtain a complete image of the abnormal object.
[0110] For example, an electronic device employs a pre-trained deep learning model. This pre-trained deep learning model is used to stitch multiple images together to obtain a complete image. The pre-trained deep learning model can automatically learn stitching rules and is suitable for complex scenarios.
[0111] It is understandable that if the duration corresponding to each second region is longer than the preset duration, it indicates that the time between the first inspection device inspecting the abnormal object according to the first route and the time between the second region's inspection device inspecting the second region according to the preset route is longer than the preset duration. This effectively avoids collisions between the first inspection device and the second region's inspection device when inspecting across regions. It also reduces the number of times abnormal objects are inspected, improving the efficiency of abnormal object inspection. Furthermore, if the duration corresponding to each second region is less than or equal to the preset duration, a second route is determined for each second region based on the first position within that region, ensuring that the determined second route does not cross regions. Then, a third route is determined based on the target positions belonging to the first region from among multiple target positions. This ensures that the determined third route does not cross regions. Therefore, by defining the second and third routes corresponding to each second area as target routes, the inspection equipment in the second area can inspect abnormal objects in the second area according to the second route, and the first inspection equipment can inspect abnormal objects in the first area according to the third route. This effectively avoids the problem of collision caused by inspection equipment in different areas inspecting the same abnormal object.
[0112] In some embodiments, to improve the efficiency of determining the target route, such as Figure 6 As shown, the above S402 can be implemented in the following way:
[0113] S601, the electronic device determines the target location belonging to each second region as the second location in each second region based on multiple target locations and each second region.
[0114] S602. When the number of second positions in each second region of the electronic device is one, the second position in each second region is determined as the first position in each second region.
[0115] S603. When the number of second positions in each second region of the electronic device is multiple, any one of the multiple second positions shall be determined as the first position in each second region.
[0116] Understandably, the target location belonging to the second region is designated as the second location within the second region. Subsequently, when there are multiple second locations, designating any one of them as the first location within the second region can improve the efficiency of determining the target route based on the first location within the second region.
[0117] In some embodiments, to improve the efficiency of identifying abnormal objects, such as Figure 7As shown, the above S502 can be implemented in the following manner:
[0118] S701. The electronic device performs background removal processing on the target image according to a preset classification algorithm to obtain the first image.
[0119] As one possible implementation, the electronic device acquires the target image and performs background removal processing on the target image according to a preset classification algorithm to obtain the first image.
[0120] For example, the background can be the environmental portion of the target image, and the first image can be the image corresponding to the abnormal object. The abnormal object can be an inspected item.
[0121] S702. The electronic device determines whether the object in the first image is in an abnormal state based on the first image and multiple preset images.
[0122] The preset images include: images of objects in a normal state, and / or images of objects in an abnormal state.
[0123] As one possible implementation, the electronic device acquires multiple preset images corresponding to each preset object among multiple preset objects. Then, based on the first image and the multiple preset images corresponding to the objects in the first image, the electronic device determines whether the object in the first image is in an abnormal state.
[0124] S703. If an object in the first image is in an abnormal state, the electronic device determines the object in the first image as an abnormal object.
[0125] It should be noted that when the object in the first image is not in an abnormal state, the electronic device sends a preset inspection message to the first inspection device so that the first inspection device can inspect the first area according to the preset route corresponding to the first area.
[0126] S704. The electronic device performs coordinate transformation on the first image to obtain multiple third positions corresponding to the abnormal object.
[0127] As one possible implementation, the electronic device acquires the internal and external parameters of the inspection equipment. The internal parameters include the camera's focal length, principal point position, and distortion coefficients, while the external parameters include the camera position and camera pose. Then, based on the internal and external parameters, the electronic device performs coordinate transformation on the first image to obtain multiple third locations corresponding to the abnormal objects.
[0128] S705 The electronic device performs edge extraction processing on multiple third locations to obtain multiple target locations corresponding to the abnormal object.
[0129] It is understandable that the background part in the first object can be removed through a preset classification algorithm to obtain a first image. Afterwards, it can be determined whether the object in the first image is an abnormal object according to a plurality of preset images. In this way, by removing the background, the inaccuracy of object state recognition caused by the background can be avoided, and the accuracy of determining the abnormal object is further improved. Afterwards, edge extraction is performed on a plurality of third positions corresponding to the abnormal object to obtain a plurality of target positions corresponding to the abnormal object. In this way, the obtained target positions are the edges of the abnormal object, which can improve the efficiency of subsequently determining the target route according to the plurality of target positions.
[0130] In some embodiments, when the number of target inspection areas is one, in order to determine the target route, as Figure 8 shown, the abnormal inspection method provided in the embodiments of the present application further includes:
[0131] S801. When the number of target inspection areas is one, the electronic device determines the first route as the target route.
[0132] For example, taking a plurality of target positions respectively as target position 3 (x3, y3, z3) where 0<x3<5, 0<y3<5, 0<z3<5, and target position 4 (x4, y4, z4) where 0<x4<5, 0<y4<5, 0<z4<5 as an example, the electronic device determines that the area to which target position 3 belongs is the first area, and the area to which target position 4 belongs is the first area, so as to obtain that the target inspection area to which the plurality of target positions belong is the first area.
[0133] It is understandable that when the number of target inspection areas is one, it indicates that all the plurality of target positions corresponding to the abnormal object belong to the first area. In this way, the first route determined according to the plurality of target positions is located within the first area, and the abnormal object can be inspected according to the target route determined from the first route.
[0134] Figure 9 is a flowchart of an abnormal inspection method provided in the embodiments of the present application. As Figure 9 shown, the abnormal inspection method includes:
[0135] S901. The electronic device divides the inspection area into a plurality of inspection sub-areas, and constructs a spatial coordinate model.
[0136] S902. The electronic device acquires a target image of the first inspection sub-area.
[0137] S903. The electronic device determines whether the target image of the first inspection sub-area includes an abnormal object.
[0138] S904. If the target image of the first inspection sub-area includes an abnormal object, the electronic device processes the abnormal object to obtain the target route and inspects the abnormal object according to the target route.
[0139] S905. If the target image of the first inspection sub-region does not contain any abnormal objects, the electronic device shall inspect the first inspection sub-region according to the preset route corresponding to the first inspection sub-region.
[0140] The anomaly inspection method of this application will be described below with reference to specific embodiments. For example, when the electronic device is located in multiple second areas, namely a first area, a second area 1, and a third area 2, the electronic device determines route 1 based on multiple target locations. Then, the electronic device determines whether the drone corresponding to the first area can return to the first area before the drones in the second areas 1 and 2 inspect the anomaly when inspecting the anomaly according to route 1. If the electronic device can return to the first area before the drones in the second areas 1 and 2 inspect the anomaly according to the preset route when inspecting the anomaly according to route 1, route 1 is determined as the target route. If the electronic device cannot return to the first area before the drones in the second areas 1 and 2 inspect the anomaly when inspecting the anomaly according to route 1, route 2 is determined based on the target location within the first area and the target location within the second area 1, and route 3 is determined based on the target location within the second area 2.
[0141] Then, the electronic device determines whether the drone in the first area can return to the first area before the drone in the second area 1, which is inspecting the abnormal object according to route 2, can return to the first area before the drone in the second area 1, which is inspecting the abnormal object according to the preset route. Next, if the drone in the first area can return to the first area before the drone in the second area 1, route 2 and route 3 are designated as target routes. If the drone in the first area cannot return to the first area before the drone in the second area 1, route 4 is determined based on the target location in the first area, and route 5 is determined based on the target location in the second area 1. Route 3, route 4, and route 5 are then designated as target routes.
[0142] The above primarily describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, the anomaly inspection device or electronic device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0143] This application embodiment can, based on the above method, exemplarily divide anomaly inspection devices or electronic devices into functional modules. For example, the anomaly inspection device or electronic device may include functional modules corresponding to each functional division, or two or more functions may be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division; in actual implementation, there may be other division methods.
[0144] Figure 10 This is a block diagram illustrating an abnormality inspection device 1000 according to an exemplary embodiment. Figure 10 As shown, the abnormal inspection device 1000 includes an acquisition unit 1001, a processing unit 1002, and a determination unit 1003.
[0145] The acquisition unit 1001 is used to acquire multiple target locations corresponding to abnormal objects in the target image. The target image is obtained by the first inspection device inspecting a first area, which is the area inspected by the first inspection device according to a preset route corresponding to the first inspection device.
[0146] The processing unit 1002 is used to adjust the preset route corresponding to the first inspection equipment according to multiple target locations to obtain the first route of the first inspection equipment.
[0147] The determining unit 1003 is used to determine at least one target inspection area to which multiple target locations belong.
[0148] The acquisition unit 1001 is further configured to acquire, when there are multiple target inspection areas, at least one preset route corresponding to each second area in a second area. The second area is the target inspection area other than the first area among the multiple target inspection areas.
[0149] The determining unit 1003 is also used to determine the target route for inspecting abnormal objects based on the preset route and the first route corresponding to each second area. The target route does not intersect with the preset route corresponding to each second area within the same time period, or the inspection equipment corresponding to the target route does not perform inspections across areas.
[0150] Optionally, during the inspection of abnormal objects, to avoid collisions between inspection equipment, such as... Figure 10 As shown, the aforementioned determining unit 1003 is specifically used for:
[0151] Based on the preset route corresponding to each second area, determine the first moment when the inspection equipment in each second area inspects the abnormal object according to the preset route corresponding to each second area, and obtain the first moment corresponding to each second area.
[0152] Determine the first location within each second region. The first location is the target location within each second region.
[0153] Based on the first route, determine the second time when the first inspection equipment inspects the first position in each second region, and obtain the second time corresponding to each second region.
[0154] Determine the duration between the first time point corresponding to each second region and the second time point corresponding to each second region to obtain the duration corresponding to each second region.
[0155] Based on the duration corresponding to each second zone, determine the target route for inspecting abnormal objects.
[0156] Optionally, during the inspection of abnormal objects, to avoid collisions between inspection equipment, such as... Figure 10 As shown, the aforementioned determining unit 1003 is specifically used for:
[0157] If the duration of each second zone exceeds the preset duration, the first route will be designated as the target route.
[0158] If, in at least one second region, the duration corresponding to the second region is less than or equal to the preset duration, the second route corresponding to each second region is determined based on the first position in each second region.
[0159] The third route is determined based on the target locations belonging to the first region among multiple target locations.
[0160] The second and third routes corresponding to each second region are determined as the target routes.
[0161] Optionally, to improve the efficiency of determining the target route, such as Figure 10 As shown, the aforementioned determining unit 1003 is specifically used for:
[0162] Based on multiple target locations and each second region, the target locations belonging to each second region are determined as the second locations within each second region.
[0163] If there is one second position in each second region, then the second position in each second region is determined as the first position in each second region.
[0164] When there are multiple second positions in each second region, any one of the multiple second positions is determined as the first position in each second region.
[0165] Optionally, to improve the efficiency of identifying abnormal objects, such as Figure 10 As shown, the aforementioned acquisition unit 1001 is specifically used for:
[0166] The target image is processed by background removal according to a preset classification algorithm to obtain the first image.
[0167] Based on a first image and multiple preset images, determine whether the object in the first image is in an abnormal state. The preset images include: images of objects in a normal state, and / or images of objects in an abnormal state.
[0168] If an object in the first image is in an abnormal state, the object in the first image will be identified as an abnormal object.
[0169] The first image is transformed to obtain multiple third locations corresponding to the abnormal object.
[0170] Edge extraction is performed on multiple third locations to obtain multiple target locations corresponding to the abnormal object.
[0171] Optionally, if there is only one target inspection area, in order to determine the target route, such as... Figure 10 As shown, the aforementioned determining unit 1003 is further configured to:
[0172] If there is only one target inspection area, the first route will be designated as the target route.
[0173] Figure 11 A block diagram of an electronic device is shown according to an exemplary embodiment. (See diagram below.) Figure 11 As shown, the electronic device 1100 includes, but is not limited to, a processor 1101 and a memory 1102.
[0174] The memory 1102 described above is used to store the executable instructions of the processor 1101. It is understood that the processor 1101 is configured to execute instructions to implement the anomaly detection method in the above embodiments.
[0175] It should be noted that those skilled in the art will understand that Figure 11 The electronic device structure shown does not constitute a limitation on the electronic device; the electronic device may include, but is not limited to, other electronic devices. Figure 11 This may indicate more or fewer components, or combinations of certain components, or different component arrangements.
[0176] Processor 1101 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in memory 1102, and by calling data stored in memory 1102, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. Processor 1101 may include one or more processing units. Optionally, processor 1101 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into processor 1101.
[0177] The memory 1102 can be used to store software programs and various data. The memory 1102 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required by at least one functional module (such as an acquisition unit, processing unit, and determination unit). Furthermore, the memory 1102 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.
[0178] In an exemplary embodiment, a computer-readable storage medium including instructions, such as a memory including instructions, is also provided, which can be executed by a processor of an electronic device to implement the anomaly inspection method in the above embodiments.
[0179] In actual implementation, the functions of the acquisition unit 1001, the processing unit 1002, and the determination unit 1003 can all be provided by [the relevant entity / component]. Figure 11 The processor 1101 calls the computer program stored in the memory 1102 to implement the process. The specific execution process can be found in the description of the anomaly inspection method section in the above embodiments, and will not be repeated here.
[0180] Optionally, the computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.
[0181] In an exemplary embodiment, this application also provides a computer program product including one or more instructions, which can be executed by a processor of an electronic device to perform the methods described above.
[0182] It should be noted that when one or more instructions in the computer-readable storage medium or computer program product are executed by the processor of an electronic device, they implement the various processes of the above method embodiments and achieve the same technical effect as the above method. To avoid repetition, they will not be described again here.
[0183] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.
[0184] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.
[0185] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0186] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0187] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.
[0188] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. An abnormal inspection method, characterized in that, The method includes: Obtain multiple target locations corresponding to abnormal objects in the target image; the target image is obtained by the first inspection device inspecting a first area, and the first area is the area inspected by the first inspection device according to the preset route corresponding to the first inspection device; The preset route corresponding to the first inspection equipment is adjusted according to the multiple target locations to obtain the first route of the first inspection equipment. Determine at least one target inspection area to which the plurality of target locations belong; When there are multiple target inspection areas, a preset route corresponding to each second area in at least one second area is obtained; the second area is the target inspection area other than the first area among the multiple target inspection areas; Based on the preset route corresponding to each second region and the first route, determine the target route for inspecting the abnormal object, including: Based on the preset route corresponding to each second area, determine the first moment when the inspection equipment corresponding to each second area inspects the abnormal object according to the preset route corresponding to each second area, and obtain the first moment corresponding to each second area. Determine a first location within each of the second regions; the first location is the target location within each of the second regions. Based on the first route, determine the second time when the first inspection equipment inspects the first position in each second region, and obtain the second time corresponding to each second region; Determine the duration between the first time point corresponding to each second region and the second time point corresponding to each second region to obtain the duration corresponding to each second region; If the duration corresponding to each second region is greater than a preset duration, the first route is determined as the target route; If there is a second region in the at least one second region whose corresponding duration is less than or equal to the preset duration, the second route corresponding to each second region is determined based on the first position in each second region. The third route is determined based on the target locations belonging to the first region among the multiple target locations; The second route and the third route corresponding to each second region are determined as the target route.
2. The method according to claim 1, characterized in that, Determining the first location in each of the second regions includes: Based on the plurality of target locations and each second region, the target location belonging to each second region is determined as the second location in each second region; If there is one second position in each second region, then the second position in each second region is determined as the first position in each second region. When there are multiple second positions in each second region, any one of the multiple second positions is determined as the first position in each second region.
3. The method according to claim 2, characterized in that, The step of obtaining multiple target locations corresponding to abnormal objects in the target image includes: The target image is processed by background removal according to a preset classification algorithm to obtain a first image; Based on the first image and multiple preset images, it is determined whether the object in the first image is in an abnormal state; the preset images include: an image in which the object is in a normal state, and / or an image in which the object is in an abnormal state; If an object in the first image is in the abnormal state, the object in the first image is identified as the abnormal object. The first image is subjected to coordinate transformation to obtain multiple third locations corresponding to the abnormal object; Edge extraction processing is performed on the multiple third locations to obtain multiple target locations corresponding to the abnormal object.
4. The method according to any one of claims 1-3, characterized in that, The method further includes: If there is only one target inspection area, the first route is determined as the target route.
5. An abnormal inspection device, characterized in that, The device includes: an acquisition unit, a processing unit, and a determination unit; The acquisition unit is used to acquire multiple target locations corresponding to abnormal objects in the target image; the target image is obtained by the first inspection device inspecting a first area, and the first area is the area inspected by the first inspection device according to the preset route corresponding to the first inspection device; The processing unit is used to adjust the preset route corresponding to the first inspection equipment according to the multiple target locations to obtain the first route of the first inspection equipment. The determining unit is used to determine at least one target inspection area to which the plurality of target locations belong; The acquisition unit is further configured to acquire, when there are multiple target inspection areas, a preset route corresponding to each of at least one second area in a second area; the second area is a target inspection area other than the first area among the multiple target inspection areas. The determining unit is further configured to determine the target route for inspecting the abnormal object based on the preset route corresponding to each second area and the first route. The determining unit is specifically used for: Based on the preset route corresponding to each second area, determine the first moment when the inspection equipment corresponding to each second area inspects the abnormal object according to the preset route corresponding to each second area, and obtain the first moment corresponding to each second area. Determine a first location within each of the second regions; the first location is the target location within each of the second regions. Based on the first route, determine the second time when the first inspection equipment inspects the first position in each second region, and obtain the second time corresponding to each second region; Determine the duration between the first time point corresponding to each second region and the second time point corresponding to each second region to obtain the duration corresponding to each second region; If the duration corresponding to each second region is greater than a preset duration, the first route is determined as the target route; If there is a second region in the at least one second region whose corresponding duration is less than or equal to the preset duration, the second route corresponding to each second region is determined based on the first position in each second region. The third route is determined based on the target locations belonging to the first region among the multiple target locations; The second route and the third route corresponding to each second region are determined as the target route.
6. The apparatus according to claim 5, characterized in that, The determining unit is specifically used for: Based on the plurality of target locations and each second region, the target location belonging to each second region is determined as the second location in each second region; If there is one second position in each second region, then the second position in each second region is determined as the first position in each second region. When there are multiple second positions in each second region, any one of the multiple second positions is determined as the first position in each second region.
7. The apparatus according to claim 6, characterized in that, The acquisition unit is specifically used for: The target image is processed by background removal according to a preset classification algorithm to obtain a first image; Based on the first image and multiple preset images, determine whether the object in the first image is in an abnormal state; The preset image includes: an image of the object in a normal state, and / or an image of the object in an abnormal state; If an object in the first image is in the abnormal state, the object in the first image is identified as the abnormal object. The first image is subjected to coordinate transformation to obtain multiple third locations corresponding to the abnormal object; Edge extraction processing is performed on the multiple third locations to obtain multiple target locations corresponding to the abnormal object.
8. The apparatus according to any one of claims 5-7, characterized in that, The determining unit is further configured to: If there is only one target inspection area, the first route is determined as the target route.
9. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the method as described in any one of claims 1-4.
10. A computer-readable storage medium, characterized in that, When the computer-executable instructions stored in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is capable of performing the method as described in any one of claims 1-4.
Citation Information
Patent Citations
Task cooperation and path planning method of inmanned aerial vehicle system
CN111006669A
Inspection route determination method and device, computer equipment and storage medium thereof
CN115062880A
