Region marking method and device, storage medium and electronic equipment

Abstract

The embodiment of the invention provides a region marking method and device, a storage medium and electronic equipment, and the method comprises the steps: obtaining image data obtained by an image collection module in an unmanned plane; identifying the image data through an edge calculation module in the unmanned aerial vehicle to determine an identification result of the image data; and when it is determined that a target area meeting a preset condition exists in the image data according to the identification result, marking the target area, and through the embodiment of the invention, the problem of low efficiency caused by intensively uploading a large amount of image data to an unmanned aerial vehicle nest end for defect identification analysis in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of image recognition, and more specifically, to a method and device for marking a region, a storage medium, and an electronic device. Background Art

[0002] At present, the inspection work of new energy stations mainly uses drones and other intelligent devices to inspect a large number of infrared or visible light images every day, and then transmits the inspection image data to the server for defect fault identification, and finally generates a defect report. However, as the installed capacity of new energy stations increases, the amount of image data collected during inspection increases sharply. According to the current processing method, all inspection data is uploaded and analyzed uniformly, then the cycle of fault defect identification will be lengthened, resulting in a decrease in inspection efficiency and affecting the subsequent defect elimination work. Therefore, how to realize the real-time identification and analysis of new energy station inspection data is imminent.

[0003] At present, the real-time identification and analysis of new energy station data on the market is mainly achieved through fixed machine nests, and the image analysis software is deployed on the drone nest end. When the drone completes a single inspection and returns to the machine nest to charge, the inspection image is screened, and only the images with defects are transmitted back to the control center using a dedicated network. Although this batch defect identification and transmission avoids uploading all data together and reduces the pressure of unified uploading, it does not achieve real-time defect identification and analysis in the true sense. During the inspection process, the drone cannot adjust the inspection strategy and path in time according to the results of real-time identification and analysis, and cannot provide immediate feedback and processing of the problems found, thereby improving the efficiency and effectiveness of the inspection. At the same time, there are many new energy stations, and not all stations have the conditions to build fixed drone nests for inspection and data analysis.

[0004] There is currently no effective solution to the problem of inefficiency caused by uploading a large amount of image data to the drone nest for defect identification and analysis in the existing technology.

[0005] Therefore, it is necessary to improve the related technology to overcome the above-mentioned defects in the related technology. Summary of the invention

[0006] The embodiments of the present application provide a method and device for marking an area, a storage medium, and an electronic device to at least solve the problem of low efficiency in the prior art caused by uploading a large amount of image data to a drone nest for defect identification and analysis.

[0007] According to one embodiment of the present application, a method for marking an area is provided, which is applied to a drone, including: acquiring image data acquired by an image acquisition module in the drone; identifying the image data through an edge computing module in the drone to determine a recognition result of the image data; and marking the target area when it is determined according to the recognition result that there is a target area in the image data that meets preset conditions.

[0008] In an exemplary embodiment, marking the target area includes: identifying a defect type and a location of the target area; and marking the target area based on the defect type and the location.

[0009] In an exemplary embodiment, after the image data is identified by the edge computing module in the drone to determine the identification result of the image data, the method further includes: determining the number of target areas in the image data that meet the preset conditions based on the identification result; determining the size relationship between the number and a preset number; and determining an adjustment strategy for the driving speed of the drone based on the size relationship.

[0010] In an exemplary embodiment, an adjustment strategy for the driving speed of the UAV is determined based on the size relationship, including: when the size relationship indicates that the number is greater than or equal to the preset number, determining the adjustment strategy as a first adjustment strategy, wherein the first adjustment strategy is used to indicate a reduction in the driving speed of the UAV; when the size relationship indicates that the number is less than the preset number, determining the adjustment strategy as a second adjustment strategy, wherein the second adjustment strategy is used to indicate prohibiting adjustment of the driving speed of the UAV.

[0011] In an exemplary embodiment, after determining that the adjustment strategy is the first adjustment strategy, the method further includes: determining a difference between the number and the preset number; determining a target speed according to the difference, and controlling the drone to reduce the target speed.

[0012] In an exemplary embodiment, after marking the target area, the method further includes: performing a lossless compression operation on the image data and storing the compressed image data in a first file; and storing the marked image data in a second file.

[0013] According to another embodiment of the present application, a region marking device is provided, which is applied to a drone, and includes: an image acquisition module, used to acquire image data; an edge computing module, used to identify the image data to determine an identification result of the image data; when it is determined according to the identification result that there is a target region in the image data that meets preset conditions, the target region is marked.

[0014] According to another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0015] According to another embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0016] According to another embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0017] Through the present application, image data acquired by the image acquisition module in the drone is obtained; the image data is identified by the edge computing module in the drone to determine the identification result of the image data; when it is determined according to the identification result that there is a target area that meets the preset conditions in the image data, the target area is marked; in the embodiment of the present application, real-time identification and marking of the target area are realized through the image acquisition module and edge computing module carried by the drone, thereby improving the detection efficiency. Therefore, it can solve the problem of inefficiency caused by a large amount of image data being uploaded to the drone nest for defect identification and analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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.

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] Figure 1 It is a hardware structure block diagram of a drone of a method for marking an area in an embodiment of the present application;

[0021] Figure 2 is a flow chart of a method for marking a region according to an embodiment of the present application;

[0022] Figure 3 is a structural block diagram of a region marking device according to an optional embodiment of the present application;

[0023] Figure 4 is a flow chart of a method for marking a region according to an optional embodiment of the present application;

[0024] Figure 5 It is a structural block diagram of a region marking device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0027] The method embodiments provided in the embodiments of the present application can be executed in a drone or a similar computing device. Taking running on a drone as an example, Figure 1 FIG. 1 is a hardware structure diagram of a drone of a method for marking an area in an embodiment of the present application. Figure 1 As shown, the drone may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the above-mentioned drone may also include a transmission device 106 for communication functions and an input and output device 108. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above-mentioned drone. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0028] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for marking the area in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the drone via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0029] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by the communication provider of the drone. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0030] In this embodiment, a method for marking an area is provided, which is applied to the above-mentioned drone. Figure 2 is a flow chart of a method for marking a region according to an embodiment of the present application. Figure 2 As shown, the process includes the following steps:

[0031] Step S202, acquiring image data acquired by the image acquisition module in the drone;

[0032] In this step, the image acquisition module (such as an infrared or visible light camera) carried by the drone captures the inspection image and transmits it to the edge computing module, where the image acquisition module can be a high-resolution image sensor that can capture the image data of the drone during the inspection process in real time. Data transmission can use high-speed internal bus or wireless communication technology to ensure that the image data is delivered to the edge computing module in a timely and complete manner.

[0033] Step S204, identifying the image data through an edge computing module in the drone to determine an identification result of the image data;

[0034] After receiving the image data, the edge computing module runs the preset AI algorithm model to analyze the image, identify possible defects or abnormal areas, and generate recognition results.

[0035] The edge computing module is equipped with high-performance processors and memory, which can carry complex computing tasks. Model algorithms may include but are not limited to deep learning, convolutional neural networks (CNN), etc., which are used for image feature extraction and pattern recognition. At the same time, considering the resource limitations of edge devices, the model needs to be optimized to adapt to the computing environment of the edge to ensure real-time and accuracy.

[0036] Step S206: When it is determined according to the recognition result that there is a target area meeting a preset condition in the image data, the target area is marked.

[0037] If the recognition results indicate that there are target areas in the image that meet the preset conditions (such as suspected defects, abnormal equipment, etc.), these areas are marked for subsequent analysis or human review.

[0038] Among them, marking can be done by drawing a box on the image, adding a label inside the box, highlighting, etc. to visually highlight the target area. These markings can be visual or data recorded, such as recording the coordinates and identification type of the target area in the image metadata. After marking, the image data can be further processed or stored for subsequent analysis.

[0039] Through the above steps, the image data acquired by the image acquisition module in the drone is obtained; the image data is identified by the edge computing module in the drone to determine the identification result of the image data; when it is determined according to the identification result that there is a target area that meets the preset conditions in the image data, the target area is marked; in the embodiment of the present application, the image acquisition module and the edge computing module carried by the drone are used to realize real-time identification and marking of the target area, thereby improving the detection efficiency. Therefore, it can solve the problem of inefficiency caused by a large amount of image data being uploaded to the drone nest for defect identification and analysis.

[0040] The execution subject of the above steps may be a drone, etc., but is not limited thereto.

[0041] Optionally, marking the target area includes: identifying a defect type and a position of the target area; and marking the target area based on the defect type and the position.

[0042] In the embodiment of the present application, an AI algorithm model is used to analyze the inspection image. Through deep learning and other technologies, the algorithm model can identify various types of defects that may exist in the image. For example, for the inspection of new energy stations, it may include but is not limited to: photovoltaic panel cracks, hot spots, occlusions, bracket rust, wire damage, etc. At the same time, the algorithm also needs to accurately locate the position of these defects in the image (for example, object detection technology), and can give the boundary box of the defect, that is, the specific coordinate range where the defect is located.

[0043] After identifying the defect type and location, the algorithm will mark the image based on this information. Marking can be done in a variety of ways, such as using different colored boxes to distinguish different types of defects, or annotating the image with text to describe the specific type of defect and possible causes. This marking can be directly displayed on the drone's real-time monitoring interface, allowing operators to instantly understand the defect status, or it can be stored in the image file for later viewing and analysis.

[0044] For example, suppose a drone is inspecting a large photovoltaic power station, and an abnormality appears in the image of a photovoltaic panel, which may be a hot spot phenomenon. The AI ​​model on the edge computing device first identifies that the photovoltaic panel has a hot spot defect and determines the specific location of the defect in the image. For example, the hot spot is located in the upper left corner of the photovoltaic panel, and the coordinate range of the bounding box is (x1, y1) to (x2, y2). Next, the model will mark the location of the hot spot on this image with a red box, and add a text description in or near the box, such as "hot spot defect", and may also mark the severity of the defect, such as "medium". Finally, this marked image will be stored in a specific folder, which is dedicated to storing all images marked as defective, for later analysis and maintenance. At the same time, if the storage space is insufficient, the image lossless compression module will be started to losslessly compress the inspected image to save storage space and ensure that the inspection process is not affected by storage limitations.

[0045] The embodiments of the present application can greatly improve inspection efficiency and reduce data transmission delays through real-time marking and analysis functions, ensure that operators can obtain key information in real time, respond quickly, reduce fault downtime, and improve the operation and maintenance level of the station.

[0046] Optionally, after the image data is identified by the edge computing module in the drone to determine the identification result of the image data, the method further includes: determining the number of target areas in the image data that meet the preset conditions based on the identification result; determining the size relationship between the number and a preset number; and determining an adjustment strategy for the driving speed of the drone based on the size relationship.

[0047] The embodiment of the present application defines a method of using the edge computing module in the drone to perform real-time recognition of image data, and dynamically adjust the driving speed of the drone based on the recognition result to optimize the inspection efficiency and data processing effect. Specifically:

[0048] Based on the recognition results, the number of target areas in the image that meet preset conditions, such as certain types of defects or faults, is determined. The preset conditions can be the type, size or location of the defect, and the number of target areas is an indicator of the density of defects.

[0049] The relationship between the number of target areas and the preset number determines whether the drone's speed needs to be adjusted. If the number of target areas exceeds the preset number, it means that there are many defects in the current area or the current identification is incomplete and requires a more detailed inspection. At this time, the drone's flight speed will be slowed down to ensure that all defects can be fully identified and recorded.

[0050] The strategy of dynamically adjusting the flight speed in the embodiment of the present application, combined with the real-time processing capability of edge computing, significantly improves the efficiency and effectiveness of new energy station inspections, while also reflecting the intelligence and automation level of the technology.

[0051] Optionally, determining an adjustment strategy for the driving speed of the UAV based on the size relationship includes: when the size relationship indicates that the number is greater than or equal to the preset number, determining the adjustment strategy as a first adjustment strategy, wherein the first adjustment strategy is used to indicate a reduction in the driving speed of the UAV; when the size relationship indicates that the number is less than the preset number, determining the adjustment strategy as a second adjustment strategy, wherein the second adjustment strategy is used to indicate prohibiting adjustment of the driving speed of the UAV.

[0052] The "size relationship" in the embodiment of the present application refers to the comparison between the number of identified defects and a preset number. The preset number is a threshold used to determine whether the identified defects require the drone to slow down for a more detailed inspection.

[0053] If the number of defects identified is greater than or equal to the preset number, it means that there may be more faults or abnormalities in the current area and a closer inspection is required. At this time, the drone's driving speed will be reduced to give the image recognition algorithm more time to process and analyze the image, ensuring that important information is not missed due to excessive speed.

[0054] If the number of defects identified is less than the preset number, it means that the inspection situation in the current area is good and no additional detailed inspection is required. In this case, the drone's driving speed will not be adjusted and the original speed will be maintained to continue the inspection, thereby improving the overall efficiency of the inspection.

[0055] Through the embodiments of the present application, drone inspections can adapt to different inspection environments more intelligently, ensuring the accuracy of inspections while taking into account efficiency. This is an effective application of edge computing technology in new energy inspection scenarios.

[0056] For example, the AI ​​algorithm on the edge computing module immediately processes the image, identifies defects on the blade and marks them out. Assume that the preset condition is that the defect area on the blade exceeds a certain threshold, and the preset number is 10 (that is, the number of defects exceeding this threshold in each frame of the image). If the number of defects identified in a frame of image is less than 10, the drone continues to fly at the current speed; if the number of defects identified is more than 10, indicating that the current area requires a more detailed inspection, the drone will automatically slow down, for example, from 5 meters / second to 3 meters / second to ensure that all defects are fully recorded. After the speed is adjusted, the drone continues to patrol, and the edge computing module continues to perform image recognition and analysis until the entire inspection task is completed.

[0057] Optionally, after determining that the adjustment strategy is the first adjustment strategy, the method further includes: determining a difference between the number and the preset number; determining a target speed according to the difference, and controlling the drone to reduce the target speed.

[0058] During the inspection process, if the number of defects in the image identified by the drone through the edge computing device exceeds the preset threshold, the "first adjustment strategy" will be triggered. The system will dynamically calculate a "target speed" based on the difference between the number of defects and the preset threshold. The calculation formula for the target speed may be based on the size of the difference. The larger the difference, the higher the target speed, and vice versa. The system will then control the drone to fly at this target speed to ensure that there is enough time to identify and analyze the defects.

[0059] For example, suppose that during the inspection process, the preset defect number threshold is set to 10 defects (i.e., the "preset number" is 10). In a certain inspection screen, the edge computing device identified 15 defects (i.e., the "number" is 15). In this case, the system will trigger the "first adjustment strategy" because the number of defects identified exceeds the preset threshold.

[0060] Next, the system calculates the difference, which is 15-10=5. Based on this difference, the system determines a target speed. For example, if the difference is 5, the system may decide to reduce the drone's flight speed by 20%. This means that if the drone is originally flying at 10 meters per second, it will slow down to 8 meters per second when too many defects are identified.

[0061] Through the embodiments of the present application, the drone can automatically adjust its flight speed during the inspection process according to the number of defects identified, ensuring the quality and efficiency of the inspection. For example, if the edge computing device continuously identifies a large number of defects in a certain area, the drone will automatically slow down and inspect the area more carefully until the defects are fully identified and recorded. This not only improves the accuracy of the inspection, but also effectively utilizes the inspection time of the drone and avoids waste of resources.

[0062] Optionally, after marking the target area, the method further includes: performing a lossless compression operation on the image data, and storing the compressed image data in a first file; and storing the marked image data in a second file.

[0063] During the inspection process, once the algorithm model of the edge computing device identifies the target area in the image (usually defects or abnormalities), the system will mark these areas. Marking can be done by drawing a frame, drawing a circle, adding a text label, etc. to highlight them for subsequent analysis or manual review.

[0064] Lossless compression means that no details or information will be lost in the process of compressing image data, and the image data will be completely restored after decompression. Due to the huge amount of image data generated by drone inspections, lossless compression can effectively reduce the storage space requirements of data while maintaining the integrity of the data.

[0065] The compressed image data and the marked image data are stored in two different files or folders. The compressed image data is stored in the "first file", which is usually a storage area dedicated to storing compressed images to save storage space. The marked image data is stored in the "second file", which is usually used to store images that have been analyzed and marked for subsequent query, analysis and report generation.

[0066] For example, after the algorithm model detects a crack, it automatically adds a red rectangular box to the image area where the crack is located, and may annotate the text information "blade crack" to highlight the defect. After the marking operation is completed, the system performs lossless compression on all collected image data (including marked and unmarked). For example, the compression algorithm in JPEG2000 or PNG format can be used.

[0067] All compressed image data (both marked and unmarked) are stored in the device's internal memory card as a "first file" (e.g., a folder named "Compressed_Images"). Marked image data are stored in another folder, called a "second file" (e.g., "Analyzed_Images"), which is specifically used to store analyzed and marked image data for subsequent processing and report generation.

[0068] The embodiment of the present application adopts a separate storage method, which can not only effectively manage the storage space, but also facilitate the classification and retrieval of data, improve the efficiency of data processing and the continuity of inspection work. For example, maintenance personnel can directly access the marked images in the "second file" and quickly locate the problem points without decompressing all the image data, thereby saving time and improving work efficiency.

[0069] In order to better understand the process of the marking method of the above-mentioned area, the implementation method flow of the marking of the above-mentioned area is described below in combination with an optional embodiment, but it is not used to limit the technical solution of the embodiment of the present application.

[0070] In this embodiment, a device for marking an area is provided. Figure 3 is a structural block diagram of a region marking device according to an optional embodiment of the present application, such as Figure 3 As shown, it includes an inspection image recognition and marking module, a flight speed control module, a defect image storage module, and an image lossless compression module, wherein:

[0071] The inspection image recognition and marking module is used to call the algorithm model during the inspection process through the edge computing box with an embedded algorithm model, to perform real-time recognition and analysis of the inspection images, and to mark the images immediately if defects are found.

[0072] The flight speed control module is used to calculate and count the number of defects in the picture during the inspection process. When there are too many defects in the picture and the recognition is incomplete during the inspection process, the flight speed of the drone is automatically adjusted to reserve enough time for the image recognition module to identify and mark them.

[0073] The defect image storage module is used to store images with real-time identification and defect marking during the inspection process in special folders to ensure clear data classification.

[0074] The image lossless compression module is used to accumulate massive amounts of data during the inspection process. These data are temporarily stored in the device's built-in storage card to avoid interruptions in the inspection process due to storage problems. The inspection images are losslessly compressed with an ultra-high compression ratio to ensure the smooth progress of the inspection.

[0075] In this embodiment, a method for marking a region is provided. Figure 4 is a flow chart of a method for marking a region according to an optional embodiment of the present application. Figure 4 As shown, the following steps are included:

[0076] Step S401: The drone is equipped with an edge computing module to conduct field inspections;

[0077] Step S402: During the inspection process, the edge computing box identifies and marks defects in the inspection image;

[0078] Step S403: The UAV adjusts the flight speed according to the recognition result;

[0079] Step S404: classify and store the inspection identification mark images;

[0080] Step S405: compress the inspection image losslessly with a high compression ratio.

[0081] In the embodiments of the present application, by transferring data processing from the cloud to the edge, the amount of data that needs to be transmitted to the cloud can be reduced, network resource utilization can be optimized, bandwidth utilization can be improved, and network congestion can be reduced. The data collected by the drone can be processed in real time by edge computing devices, combined with pre-trained models, to achieve fast and accurate data analysis and pattern recognition, and improve the efficiency and accuracy of recognition and analysis. During the inspection process, the drone adjusts the inspection strategy and path in a timely manner based on the results of real-time recognition and analysis, and provides immediate feedback and processing for problems found, thereby improving the efficiency and effectiveness of the inspection.

[0082] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0083] In this embodiment, a device for marking an area is also provided, which is used to implement the above embodiments and preferred implementations, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0084] Figure 5 is a structural block diagram of a region marking device according to an embodiment of the present application, such as Figure 5 As shown, the device comprises:

[0085] An image acquisition module 52, used to acquire image data;

[0086] The edge computing module 54 is used to identify the image data to determine the recognition result of the image data; when it is determined according to the recognition result that there is a target area in the image data that meets the preset conditions, the target area is marked.

[0087] Through the above-mentioned device, the image data acquired by the image acquisition module in the drone is obtained; the image data is identified by the edge computing module in the drone to determine the identification result of the image data; when it is determined according to the identification result that there is a target area that meets the preset conditions in the image data, the target area is marked; in the embodiment of the present application, the image acquisition module and the edge computing module carried by the drone are used to realize real-time identification and marking of the target area, thereby improving the detection efficiency. Therefore, it can solve the problem of inefficiency caused by uploading a large amount of image data to the drone nest for defect identification and analysis.

[0088] In an exemplary embodiment, the edge computing module is used to identify the defect type and location of the target area; and mark the target area based on the defect type and the location.

[0089] In an exemplary embodiment, the above-mentioned device also includes: a control module, which is used to determine the number of target areas in the image data that meet the preset conditions based on the recognition results; determine the size relationship between the number and the preset number; and determine an adjustment strategy for the driving speed of the drone based on the size relationship.

[0090] In an exemplary embodiment, the control module is used to determine that the adjustment strategy is a first adjustment strategy when the size relationship indicates that the number is greater than or equal to the preset number, wherein the first adjustment strategy is used to indicate that the driving speed of the UAV is reduced; and to determine that the adjustment strategy is a second adjustment strategy when the size relationship indicates that the number is less than the preset number, wherein the second adjustment strategy is used to indicate that the adjustment of the driving speed of the UAV is prohibited.

[0091] In an exemplary embodiment, the control module is used to determine the difference between the number and the preset number; determine the target speed according to the difference, and control the drone to reduce the target speed.

[0092] In an exemplary embodiment, the above-mentioned device includes: a storage module, which is used to perform a lossless compression operation on the image data and store the compressed image data in a first file; and store the marked image data in a second file.

[0093] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0094] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0095] Optionally, in this embodiment, the storage medium may be configured to store program codes for executing the following steps:

[0096] S1, obtaining image data acquired by an image acquisition module in the drone;

[0097] S2, identifying the image data through an edge computing module in the drone to determine an identification result of the image data;

[0098] S3, when it is determined according to the recognition result that there is a target area meeting a preset condition in the image data, marking the target area.

[0099] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0100] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0101] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0102] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0103] S1, obtaining image data acquired by an image acquisition module in the drone;

[0104] S2, identifying the image data through an edge computing module in the drone to determine an identification result of the image data;

[0105] S3, when it is determined according to the recognition result that there is a target area meeting a preset condition in the image data, marking the target area.

[0106] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.

[0107] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0108] An embodiment of the present application also provides a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in any one of the above method embodiments.

[0109] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0110] S1, obtaining image data acquired by an image acquisition module in the drone;

[0111] S2, identifying the image data through an edge computing module in the drone to determine an identification result of the image data;

[0112] S3, when it is determined according to the recognition result that there is a target area meeting a preset condition in the image data, marking the target area.

[0113] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0114] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0115] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for marking a region, characterized in that: Applications in drones include: Acquire image data acquired by an image acquisition module in the drone; Recognize the image data by an edge computing module in the drone to determine a recognition result of the image data; When it is determined according to the recognition result that there is a target area meeting a preset condition in the image data, the target area is marked.

2. The method according to claim 1, characterized in that Marking the target area includes: identifying defect types and locations in the target area; The target area is marked based on the defect type and the location.

3. The method according to claim 1, characterized in that After identifying the image data by the edge computing module in the drone to determine the identification result of the image data, the method further includes: Determine the number of target areas in the image data that meet the preset conditions according to the recognition result; Determining the magnitude relationship between the quantity and a preset quantity; The adjustment strategy for the driving speed of the UAV is determined according to the size relationship.

4. The method according to claim 3, characterized in that Determining a strategy for adjusting the travel speed of the drone according to the magnitude relationship includes: When the magnitude relationship indicates that the number is greater than or equal to the preset number, determining that the adjustment strategy is a first adjustment strategy, wherein the first adjustment strategy is used to instruct to reduce the driving speed of the drone; When the size relationship indicates that the number is less than the preset number, the adjustment strategy is determined to be a second adjustment strategy, wherein the second adjustment strategy is used to indicate that adjustment of the driving speed of the drone is prohibited.

5. The method according to claim 4, characterized in that After determining that the adjustment strategy is the first adjustment strategy, the method further includes: determining a difference between the quantity and the predetermined quantity; A target speed is determined according to the difference, and the UAV is controlled to reduce the target speed.

6. The method according to claim 1, characterized in that After marking the target area, the method further includes: Performing a lossless compression operation on the image data, and storing the compressed image data in a first file; The labeled image data is stored in a second file.

7. A device for marking an area, characterized in that: Applications in drones include: An image acquisition module, used for acquiring image data; The edge computing module is used to identify the image data to determine the recognition result of the image data; when it is determined according to the recognition result that there is a target area in the image data that meets the preset conditions, the target area is marked.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the method according to any one of claims 1 to 6 is executed when the program is executed.

9. An electronic device, comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 6 through the computer program.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images