Unmanned aerial vehicle motion control method and device, electronic equipment and storage medium

Through the drone motion control method, the filtering processing and boundary recognition technology of image data are used to identify the target color characteristics, and accurate navigation is achieved when the GPS signal is weak or no signal is solved, solving the problem of search and rescue in mountainous environments and other environments , improves task efficiency and accuracy.

CN118897568APending Publication Date: 2024-11-05YUNNAN POWER GRID CO LTD NUJIANG POWER SUPPLY BUREAU
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410930546.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-11
Publication Date
2024-11-05

AI Technical Summary

Technical Problem

In places with large blockages such as mountainous areas and weak or no GPS signal, it makes it difficult to navigate the search and rescue drones, affecting the efficiency and accuracy of search and rescue.

Method used

Through the drone motion control method, image data is collected in response to the flight information input by the user and the color information of the target object, filtering and boundary recognition are performed, target image data is extracted, and target image data is identified according to the color characteristics, and the target will fly to the target location to avoid A situation where the signal is weak or no signal.

Benefits of technology

It reduces the difficulty of search and rescue, improves the accuracy and efficiency of drones' navigation in environments with large blockages, and ensures the successful completion of search and rescue tasks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118897568A_ABST
    Figure CN118897568A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses an unmanned aerial vehicle motion control method and device, electronic equipment and a storage medium, and the method comprises the steps: responding to flight information inputted by a user and color information of a target object, and flying to a target coordinate corresponding to the flight information; collecting image data corresponding to the target coordinates; filtering the acquired image data, and determining an image boundary in the filtered image data; extracting target image data from the filtered image data based on the image boundary, and identifying the target image data; and if the color corresponding to the color information is identified in the target image data, flying to a target location. According to the scheme, the search and rescue difficulty can be reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, electronic device and storage medium for controlling the motion of an unmanned aerial vehicle. Background Art

[0002] At present, the widespread application of drones is growing rapidly. Drones not only play an important role in the military field, but are also widely used in search and rescue (SAR), photography, agriculture, express delivery and other fields. In the past few years, the autonomous flight technology of drones has attracted a lot of research attention. In the field of search and rescue, concerns about human safety have always been the focus, and they need to be on standby at all times to respond to various disasters. The key to search and rescue is speed and accuracy, and some disaster sites are difficult for humans to enter due to environmental conditions and other factors. In this case, the application of drones becomes particularly important. Drones can easily enter areas that are difficult for humans to reach, providing strong support for search and rescue.

[0003] In current search and rescue drones, search and rescue are carried out through the Global Positioning System (GPS). However, GPS often has weak or no signal in places with large obstructions such as mountainous areas, which greatly increases the difficulty of search and rescue. Summary of the invention

[0004] The embodiments of the present application provide a drone motion control system, method, electronic device, and storage medium, which can reduce the difficulty of search and rescue.

[0005] In a first aspect, an embodiment of the present application provides a method for controlling the motion of a drone, comprising:

[0006] In response to the flight information input by the user and the color information of the target object, flying to the target coordinates corresponding to the flight information;

[0007] Acquiring image data corresponding to the target coordinates;

[0008] Performing filtering on the collected image data and determining the image boundary in the filtered image data;

[0009] extracting target image data from the filtered image data based on the image boundary, and identifying the target image data;

[0010] If a color corresponding to the color information is recognized in the target image data, the aircraft flies to the target location.

[0011] Optionally, in some embodiments of the present application, filtering the acquired image data and determining the image boundary in the filtered image data includes:

[0012] Converting the acquired image data from a first color space to a second color space;

[0013] Performing filtering processing on the collected image data in the second color space;

[0014] Image boundaries are determined in the filtered image data based on an edge detection algorithm.

[0015] Optionally, in some embodiments of the present application, the filtering process on the acquired image data in the second color space includes:

[0016] Determining a color threshold corresponding to the target object in the second color space according to the color information of the target object;

[0017] The collected image data is filtered based on the color threshold.

[0018] Optionally, in some embodiments of the present application, determining the image boundary in the filtered image data according to an edge detection algorithm includes:

[0019] Calculating the gradient magnitude and gradient direction corresponding to the image data according to an edge detection algorithm;

[0020] Based on the gradient magnitude and the gradient direction, image boundaries are determined in the filtered image data.

[0021] Optionally, in some embodiments of the present application, extracting target image data from the filtered image data based on the image boundary and identifying the target image data includes:

[0022] Determine a color extraction area based on the image boundary, and extract image data corresponding to the color extraction area from the filtered image data to obtain target image data;

[0023] Performing feature calculation on the target image data to obtain color features corresponding to the target image data;

[0024] The target image data is identified according to the color feature.

[0025] Optionally, in some embodiments of the present application, if a color corresponding to the color information is identified in the target image data, flying to the target location includes:

[0026] If a color corresponding to the color information is identified in the target image data, determining a position of the target object according to the target image data;

[0027] Planning a moving path to a first target location according to a preset error range and the position of the target object;

[0028] After moving to the first target location according to the moving path, move to the second target location.

[0029] Optionally, in some embodiments of the present application, the collecting the image data corresponding to the target coordinates includes:

[0030] Detect whether the current working mode is the preset working mode;

[0031] If the current working mode is a preset working mode, then collecting image data corresponding to the target coordinates;

[0032] If the current working mode is not the preset working mode, motion control is performed according to the control information input by the user.

[0033] In a second aspect, an embodiment of the present application provides a drone motion control device, comprising:

[0034] A response module, used for responding to the flight information input by the user and the color information of the target object, and flying to the target coordinates corresponding to the flight information;

[0035] An acquisition module, used for acquiring image data corresponding to the target coordinates;

[0036] A processing module, used for filtering the collected image data and determining the image boundary in the filtered image data;

[0037] A recognition module, used for extracting target image data from the filtered image data based on the image boundary, and identifying the target image data;

[0038] The flying module is used to fly to a target location if a color corresponding to the color information is recognized in the target image data.

[0039] Correspondingly, the present application also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the steps of any of the above methods when executing the program.

[0040] The present application also provides a storage medium, wherein the storage medium stores a computer program, and the computer program implements any of the above methods when the computer program is executed by a processor.

[0041] The present application provides a method, device, electronic device and storage medium for controlling the motion of a drone. In response to the flight information and color information of the target object input by the user, after flying to the target coordinates corresponding to the flight information, the image data corresponding to the target coordinates is collected, and then the collected image data is filtered and processed, and the image boundary is determined in the filtered image data. Finally, the target image data is extracted from the filtered image data based on the image boundary, and the target image data is identified. If the color corresponding to the color information is identified in the target image data, the drone flies to the target location. In the solution for controlling the motion of a drone provided by the present application, the collected image data is filtered and processed, and the image boundary is determined in the filtered image data, and the target image data is extracted from the filtered image data based on the image boundary, and the target image data is identified. If the color corresponding to the color information is identified in the target image data, the drone flies to the target location, avoiding places with large obstructions such as mountainous areas, which may cause weak or no signals, thereby affecting search and rescue, thereby reducing the difficulty of search and rescue. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 It is a flow chart of the UAV motion control method provided in the embodiment of the present application;

[0044] Figure 2 is a schematic diagram of the structure of the UAV motion control device provided in an embodiment of the present application;

[0045] Figure 3 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are merely examples of systems and methods consistent with the examples detailed in the attached claims, or with some aspects of the present application.

[0047] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover descriptions such as non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0048] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0049] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0050] Embodiments of the present application provide a method, device, electronic device, and storage medium for controlling the motion of a drone.

[0051] The UAV motion control device can be deployed in a UAV. A UAV (Unmanned Aerial Vehicle, UAV), also known as a remote-controlled aircraft or an Unmanned Aircraft System (UAS), is an aircraft that does not require a pilot to operate in the cabin. The UAV can communicate with a server via wired or wireless means. The server can include an independently operated server or a distributed server, or a server cluster composed of multiple servers. The terminal can include a mobile phone, a tablet computer or a personal computer (PC, Personal Computer).

[0052] It should be noted that the order of description of the following embodiments is not intended to limit the priority order of the embodiments.

[0053] The present application provides a method for controlling the motion of an unmanned aerial vehicle, including: in response to flight information input by a user and color information of a target object, flying to target coordinates corresponding to the flight information; collecting image data corresponding to the target coordinates; filtering the collected image data and determining image boundaries in the filtered image data; extracting target image data from the filtered image data based on the image boundaries and identifying the target image data; and flying to the target location if a color corresponding to the color information is identified in the target image data.

[0054] See also Figure 1 , Figure 1 : is a flow chart of the UAV motion control method provided by the present application, and the UAV motion control method specifically includes the following process:

[0055] 101. In response to flight information input by a user and color information of a target object, fly to target coordinates corresponding to the flight information.

[0056] The UAV system receives flight information input by the user, including target coordinates (longitude, latitude, and possible altitude). The user also provides color information of the target object, which may include HSV values ​​or RGB values ​​of the color.

[0057] For example, the user inputs flight information including target coordinates (longitude, latitude, altitude) through the ground control station. The user can also input color information of the target object at the same time. For example, the target may be a rescue object wearing red clothes, and the user inputs the specific value of red in the HSV color space into the system.

[0058] 102. Collect image data corresponding to the target coordinates.

[0059] When the drone arrives near the target coordinates, the target area is identified using onboard sensors and cameras. The drone camera collects image data of the target coordinate area. This may include visible light images, infrared images, or other types of image data. Image stabilization technology, such as optical image stabilization or electronic image stabilization, is used to ensure that the collected images are clear and stable. The collected images are pre-processed, including denoising, contrast adjustment, and color correction, to improve image quality.

[0060] For example, when the drone approaches the target coordinate area, it starts the onboard vision system, which includes a Raspberry Pi 3 as a single-board computer and a Logitech C920 Pro HD as a high-definition camera. The camera points downward and starts collecting image data of the target area. The camera is connected to the Raspberry Pi via a USB port, which runs the OpenCV library and Python program for image processing0.

[0061] 103. Perform filtering processing on the collected image data, and determine the image boundary in the filtered image data.

[0062] For example, the image data of the target area is collected using the Logitech C920 Pro HD camera carried by the drone. The collected raw image is preprocessed, including adjusting the brightness, contrast, and possible denoising to improve the image quality. Then, the image is converted from the RGB color space to the HSV color space to facilitate color recognition and processing. According to the color characteristics of the target object, the thresholds of hue (H), saturation (S), and brightness (V) are set in the HSV color space. The image is filtered by applying the color threshold to generate a binary image, in which the area of ​​the target color is retained and the other areas are set as the background. The edge is identified on the filtered binary image using an edge detection algorithm (such as the Canny edge detector). Non-maximum suppression is performed on the edge detection results to refine the edge so that it is closer to a continuous line with a single pixel width. The refined edge is tracked, starting from the point with the highest edge intensity and moving along the edge until the edge ends. Morphological operations such as dilation or erosion are applied to smooth the edge, fill small gaps, or remove small protrusions. The boundaries in the edge tracking results are determined, which represent the outline of the target object. Extract contours from the refined edges, which can be represented as a series of continuous points or line segments. Mark the determined boundaries on the original image, usually represented by different colors or lines. Post-process the detected boundaries to improve accuracy. This may include removing falsely detected boundaries, or merging boundaries that are too close.

[0063] Optionally, in some embodiments of the present application, the step of “filtering the acquired image data and determining the image boundary in the filtered image data” may specifically include:

[0064] Converting the acquired image data from a first color space to a second color space;

[0065] Performing filtering processing on the collected image data in a second color space;

[0066] Image boundaries are determined in the filtered image data based on an edge detection algorithm.

[0067] For example, specifically, an image acquisition device (such as a camera) captures an image in an RGB color space. The RGB image is converted to a second color space, and a common choice is an HSV or HSL (hue, saturation, brightness) color space, because these color spaces are more suitable for color recognition and analysis. In the HSV color space, thresholds for hue (H), saturation (S), and brightness (V) are set according to the color characteristics of the target object. These thresholds are applied to filter the image to generate a binary image, highlight the target color, and suppress other colors. Then, a suitable edge detection algorithm is selected, such as a Canny edge detector, a Sobel operator, or a Laplacian operator. The edge detection algorithm is applied to the filtered binary image to identify edges in the image. Non-maximum suppression is performed on the edge detection results to refine the edges so that they are closer to continuous lines with a single pixel width. The refined edges are tracked, starting from the point with the highest edge strength and moving along the edge until the edge ends. Morphological operations, such as dilation or erosion, are applied to smooth the edges, fill small gaps, or remove small protrusions. Boundaries in the edge tracking results are determined, which represent the contours of the target object. Extract contours from the refined edges, which can be represented as a series of continuous points or line segments. Mark the determined boundaries on the original image, usually represented by different colors or lines. Post-process the detected boundaries to improve accuracy. This may include removing falsely detected boundaries, or merging boundaries that are too close.

[0068] Optionally, in some embodiments of the present application, the step of “filtering the acquired image data in the second color space” may specifically include:

[0069] Determine, according to the color information of the target object, a color threshold corresponding to the target object in a second color space;

[0070] The collected image data is filtered based on the color threshold.

[0071] For example, analyze the color characteristics of the target object and determine its typical performance in the HSV color space. The HSV color space consists of three dimensions: hue, saturation, and value, and is more suitable for describing and processing color information. According to the color characteristics of the target object, set the threshold range of hue (H), saturation (S), and brightness (V) in the HSV color space. For example, if the target is red rescue equipment, you might choose a specific hue range to match the red color, and set the range of saturation and brightness to exclude non-target colors. Use the Logitech C920 ProHD camera on the drone to collect image data of the target area. Convert the collected RGB image data to the HSV color space in preparation for color-based filtering. Using the determined color threshold, create a color mask in the HSV color space. This mask will be used to filter out pixels that do not belong to the target color range. Apply the color mask to the converted HSV image for color filtering. This step will highlight pixels of the target color while suppressing pixels of other colors. After color filtering, a binary image is generated, where the target color area is white (or 255) and other areas are black (or 0). Post-processing is performed on the filtered binary image, such as removing noise, filling holes, or smoothing boundaries to improve the image quality. Edge detection algorithms, such as the Canny algorithm, are applied to the filtered binary image to determine the boundaries of the target color area.

[0072] Optionally, in some embodiments of the present application, the step of “determining the image boundary in the filtered image data according to the edge detection algorithm” may specifically include:

[0073] According to the edge detection algorithm, the gradient amplitude and gradient direction corresponding to the image data are calculated;

[0074] Based on the gradient magnitude and gradient direction, image boundaries are determined in the filtered image data.

[0075] First, make sure that the image has been filtered in the HSV color space according to the color information of the target object to obtain a binary image. Apply Sobel, Prewitt or other gradient operators to calculate the gradient magnitude and gradient direction of each pixel in the image.

[0076] For each pixel, the gradient magnitude can be found by calculating the square root of the sum of the squares of the horizontal and vertical gradient components:

[0077] Among them, Gx and Gy are the horizontal and vertical gradient components obtained after applying the gradient operator, respectively.

[0078] The gradient direction can be obtained by calculating the inverse tangent of the gradient components: direction = artan (Gy, Gx). Non-maximum suppression is performed in the gradient direction. This step helps to refine the edge and make it closer to a continuous line with a single pixel width. Starting from the point with the largest gradient magnitude, the edge is tracked along the gradient direction until the magnitude is below a certain threshold. The detected edges are refined to remove noise and discontinuous edge fragments. Morphological operations such as dilation or erosion are applied to smooth edges, fill small gaps, or remove small protrusions. Boundaries in the edge tracing results are determined, which represent the outline of the target object.

[0079] 104. Extract target image data from the filtered image data based on the image boundary, and identify the target image data.

[0080] For example, based on the extracted contours, a bounding box of the target color region is determined in the filtered image, and the image data within this region is extracted as the target image data. The extracted target image data is enhanced to improve the image quality, such as adjusting the contrast, brightness, or applying a filter to remove noise. Features are extracted from the target image data, which may include color histograms, texture features, shape descriptors, etc. The extracted features are analyzed using machine learning or pattern recognition algorithms to identify and confirm the target object. This may involve matching with a known target template or judgment by a classifier. The recognition results are verified to ensure that the extracted image data does belong to the target object.

[0081] Optionally, in some embodiments of the present application, the step of “extracting target image data from the filtered image data based on the image boundary, and identifying the target image data” may specifically include:

[0082] Determine a color extraction area based on an image boundary, and extract image data corresponding to the color extraction area from the filtered image data to obtain target image data;

[0083] Perform feature calculation on the target image data to obtain color features corresponding to the target image data;

[0084] The target image data is identified according to color features.

[0085] For example, specifically, the color filtering results in the visual system are used to determine the areas containing the target color. The boundaries of these areas are obtained through filtering and edge detection algorithms. In the filtered binary image, the corresponding image data blocks are extracted according to the areas determined by the image boundaries, and these data blocks contain the target color information. The extracted image data is enhanced to improve the image quality, which may include adjusting the brightness, contrast or using filters to remove noise. The extracted image data is feature calculated to obtain the color features of the target image data. These features may specifically include:

[0086] Color histogram: Statistics of the distribution of each color in the image.

[0087] Color moment: Calculates statistics such as the mean and variance of color distribution.

[0088] Texture features: describe the roughness or directionality of image texture.

[0089] Shape features: If the object has a specific shape, a shape descriptor can be computed.

[0090] The calculated color signature is analyzed to determine its similarity or difference to a known target signature.

[0091] Use feature matching or machine learning classifiers to identify target image data, such as comparing the extracted features with predefined target templates, or using trained classifiers to classify targets based on features.

[0092] Verify the recognition results to ensure that the extracted image data does belong to the target object. This can be done by comparing with known target features. Optionally, in some embodiments of the present application, the recognition results can also be further verified and refined by combining the contextual information of the target object, such as location, size, environment, etc. The recognition results are fed back to the control system of the drone to adjust the flight path or perform other tasks as needed.

[0093] 105. If a color corresponding to the color information is recognized in the target image data, fly to the target location.

[0094] For example, specifically, the existence of color features matching the preset color information in the target image data can be confirmed through image processing and feature calculation. Then, the position of the target in the image is determined by using the image boundaries and features in the target image data, and converted into the physical coordinate system of the drone. Then, an optimal flight path is calculated based on the current position of the drone and the target coordinates. Based on the calculated path, a flight control instruction is generated, including parameters such as speed, direction, and altitude. After receiving the flight control instruction, the flight mission is executed to fly to the target location. During the flight, the target image data is continuously monitored to ensure that the target is stably tracked. When the drone approaches the target location, the flight speed and attitude are adjusted to prepare for target confirmation and precise positioning. In the process of approaching the target location, the color information in the image data is continuously verified to ensure that the target is correct. Use machine vision or sensor fusion to achieve precise positioning of the target. Once the drone reaches the target location and confirms the target, it performs corresponding operations according to the mission requirements, such as delivering relief supplies and taking pictures.

[0095] Through this process, the drone can automatically navigate to the target location and perform the predetermined mission. This is very useful in a variety of application scenarios such as search and rescue, target monitoring, and cargo delivery.

[0096] Optionally, in some embodiments of the present application, the step of “flying to the target location if a color corresponding to the color information is identified in the target image data” may specifically include:

[0097] If a color corresponding to the color information is identified in the target image data, a position of the target object is determined according to the target image data;

[0098] Planning a moving path to a first target location according to a preset error range and the position of the target object;

[0099] After moving to the first target location according to the moving path, move to the second target location.

[0100] The drone's vision system uses the OpenCV library and Python programming to identify areas in the image that match the preset color information through filtering in the HSV color space. Once the target color is identified, the vision system determines the hue saturation value (HSV) of the target in the image through image processing technology, and uses these values ​​to determine the coordinate position of the target. The vision system evaluates the error between the current position and the target position. If the error is less than the preset error range (for example, 5 units), the target is considered to be close enough. If the target object is located at the first target location, the drone's flight control system (such as Pixhawk) will use a path planning algorithm (such as A* algorithm or Dijkstra algorithm) to plan the movement path based on the target coordinates and the current position. The drone executes the flight control instructions according to the planned path and moves to the first target location. After arriving at the first target location, the drone performs the corresponding task, such as delivering relief supplies or collecting data. After the task is completed, the drone plans a path from the current position to the second target location based on the new preset target or the operator's instructions. If the vision system detects the movement of the target object or new environmental conditions during the movement, the drone will adjust the path in real time to adapt to the changes. After arriving at the second target location, the drone will perform the scheduled mission again. During the entire process, the drone will continuously feed back image data and mission execution status to the ground control station for the operator to monitor and make decisions. After all tasks are completed, the drone will return to the base or wait for new instructions according to the preset program.

[0101] For example, a drone is conducting a search mission in a disaster area, and its preset color information is to look for victims wearing orange life jackets. The drone identifies the orange area in the image data, and the visual system determines the location of the orange area and evaluates the error with the current GPS coordinates. If the error is within an acceptable range, the drone plans a path to fly to the victim and automatically flies over the victim to locate and deliver relief supplies. Subsequently, the drone plans a new path based on new instructions or search areas, and flies to another location where there may be victims to continue the search and rescue mission.

[0102] As can be seen from the above, the embodiment of the present application provides a method for controlling the motion of a drone. In response to the flight information input by the user and the color information of the target object, after flying to the target coordinates corresponding to the flight information, the image data corresponding to the target coordinates is collected, and then the collected image data is filtered and processed, and the image boundary is determined in the filtered image data. Finally, the target image data is extracted from the filtered image data based on the image boundary, and the target image data is identified. If the color corresponding to the color information is identified in the target image data, the drone flies to the target location. In the solution for controlling the motion of a drone provided in the present application, the collected image data is filtered and processed, and the image boundary is determined in the filtered image data, and the target image data is extracted from the filtered image data based on the image boundary, and the target image data is identified. If the color corresponding to the color information is identified in the target image data, the drone flies to the target location, avoiding places with large obstructions such as mountainous areas, which may cause weak or no signals, thereby affecting search and rescue, thereby reducing the difficulty of search and rescue.

[0103] In order to better implement the UAV motion control method of the embodiment of the present application, the embodiment of the present application also provides a UAV motion control device. The meanings of the terms are the same as those in the above-mentioned UAV motion control system, and the specific implementation details can refer to the description in the system embodiment.

[0104] See also Figure 2 , Figure 2 The schematic diagram of the structure of the UAV motion control device provided in the embodiment of the present application, wherein the UAV motion control device may specifically include a response module 201, a collection module 202, a processing module 203, an identification module 204 and a flight module 205, which may be specifically as follows:

[0105] The response module 201 is used to respond to the flight information input by the user and the color information of the target object and fly to the target coordinates corresponding to the flight information.

[0106] The acquisition module 202 is used to acquire image data corresponding to the target coordinates.

[0107] The processing module 203 is used to perform filtering processing on the collected image data and determine the image boundary in the filtered image data.

[0108] The recognition module 204 is used to extract target image data from the filtered image data based on the image boundary and recognize the target image data.

[0109] The flying module 205 is used to fly to the target location if a color corresponding to the color information is recognized in the target image data.

[0110] The embodiment of the present application provides a UAV motion control device. After the response module 201 flies to the target coordinates corresponding to the flight information in response to the flight information input by the user and the color information of the target object, the acquisition module 202 acquires the image data corresponding to the target coordinates. Then, the processing module 203 performs filtering processing on the acquired image data and confirms the image boundary in the filtered image data. Finally, the recognition module 204 extracts the target image data from the filtered image data based on the image boundary and identifies the target image data. If the flight module 205 identifies the color corresponding to the color information in the target image data, it flies to the target location. In the UAV motion control scheme provided in the present application, the acquired image data is filtered, the image boundary is confirmed in the filtered image data, and the target image data is extracted from the filtered image data based on the image boundary, and the target image data is identified. If the color corresponding to the color information is identified in the target image data, it flies to the target location, avoiding places with large obstructions such as mountainous areas, resulting in weak or no signal, thereby affecting the search and rescue situation, thereby reducing the difficulty of search and rescue.

[0111] In addition, the present application also provides an electronic device, such as Figure 3 As shown, it shows a schematic diagram of the structure of the electronic device involved in the embodiment of the present application, specifically:

[0112] The electronic device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, a power supply 303, and an input unit 304. Those skilled in the art will appreciate that Figure 3 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0113] The processor 301 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 302, and calling data stored in the memory 302, it executes various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 301.

[0114] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and drone motion control methods by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0115] The electronic device also includes a power supply 303 for supplying power to each component. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions. The power supply 303 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0116] The electronic device may further include an input unit 304, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0117] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 301 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302, thereby realizing various functions, as follows:

[0118] In response to the flight information input by the user and the color information of the target object, the aircraft flies to the target coordinates corresponding to the flight information; collects image data corresponding to the target coordinates; filters the collected image data and determines the image boundary in the filtered image data; extracts the target image data from the filtered image data based on the image boundary and identifies the target image data; if a color corresponding to the color information is identified in the target image data, the aircraft flies to the target location.

[0119] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0120] In the embodiment of the present application, after flying to the target coordinates corresponding to the flight information in response to the flight information input by the user and the color information of the target object, the image data corresponding to the target coordinates is collected, and then the collected image data is filtered and processed, and the image boundary is determined in the filtered image data. Finally, the target image data is extracted from the filtered image data based on the image boundary, and the target image data is identified. If the color corresponding to the color information is identified in the target image data, the flight is to the target location. In the solution of the UAV motion control provided by the present application, the collected image data is filtered and processed, and the image boundary is determined in the filtered image data, and the target image data is extracted from the filtered image data based on the image boundary, and the target image data is identified. If the color corresponding to the color information is identified in the target image data, the flight is to the target location, avoiding places with large obstructions such as mountainous areas, resulting in weak or no signals, thereby affecting search and rescue, thereby reducing the difficulty of search and rescue.

[0121] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0122] To this end, an embodiment of the present application provides a storage medium in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any of the drone motion control methods provided in the embodiments of the present application. For example, the instructions can execute the following steps:

[0123] In response to the flight information input by the user and the color information of the target object, the aircraft flies to the target coordinates corresponding to the flight information; collects image data corresponding to the target coordinates; filters the collected image data and determines the image boundary in the filtered image data; extracts the target image data from the filtered image data based on the image boundary and identifies the target image data; if a color corresponding to the color information is identified in the target image data, the aircraft flies to the target location.

[0124] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0125] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0126] Since the instructions stored in the storage medium can execute the steps in any one of the UAV motion control methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any one of the UAV motion control methods provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0127] The above is a detailed introduction to a drone motion control method, device, electronic device and storage medium provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for controlling the motion of an unmanned aerial vehicle, characterized in that: include: In response to the flight information input by the user and the color information of the target object, flying to the target coordinates corresponding to the flight information; Acquiring image data corresponding to the target coordinates; Performing filtering on the collected image data and determining the image boundary in the filtered image data; extracting target image data from the filtered image data based on the image boundary, and identifying the target image data; If a color corresponding to the color information is recognized in the target image data, the aircraft flies to the target location.

2. The UAV motion control method according to claim 1, characterized in that: The filtering process is performed on the collected image data, and the image boundary is determined in the filtered image data, including: Converting the acquired image data from a first color space to a second color space; Performing filtering processing on the collected image data in the second color space; Image boundaries are determined in the filtered image data based on an edge detection algorithm.

3. The UAV motion control method according to claim 2, characterized in that: The filtering process of the collected image data in the second color space includes: Determining a color threshold corresponding to the target object in the second color space according to the color information of the target object; The collected image data is filtered based on the color threshold.

4. The UAV motion control method according to claim 2, characterized in that: Determining the image boundary in the filtered image data according to the edge detection algorithm includes: Calculating the gradient magnitude and gradient direction corresponding to the image data according to an edge detection algorithm; Based on the gradient magnitude and the gradient direction, image boundaries are determined in the filtered image data.

5. The UAV motion control method according to claim 1, characterized in that: The step of extracting target image data from the filtered image data based on the image boundary and identifying the target image data comprises: Determine a color extraction area based on the image boundary, and extract image data corresponding to the color extraction area from the filtered image data to obtain target image data; Performing feature calculation on the target image data to obtain color features corresponding to the target image data; The target image data is identified according to the color feature.

6. The UAV motion control method according to claim 1, characterized in that: If a color corresponding to the color information is identified in the target image data, flying to the target location includes: If a color corresponding to the color information is identified in the target image data, determining a position of the target object according to the target image data; Planning a moving path to a first target location according to a preset error range and the position of the target object; After moving to the first target location according to the moving path, move to the second target location.

7. The UAV motion control method according to claim 1, characterized in that: The collecting of image data corresponding to the target coordinates includes: Detect whether the current working mode is the preset working mode; If the current working mode is a preset working mode, then collecting image data corresponding to the target coordinates; If the current working mode is not the preset working mode, motion control is performed according to the control information input by the user.

8. A UAV motion control device, characterized in that: include: A response module, used for responding to the flight information input by the user and the color information of the target object, and flying to the target coordinates corresponding to the flight information; An acquisition module, used for acquiring image data corresponding to the target coordinates; A processing module, used for filtering the collected image data and determining the image boundary in the filtered image data; A recognition module, used for extracting target image data from the filtered image data based on the image boundary, and identifying the target image data; The flying module is used to fly to a target location if a color corresponding to the color information is recognized in the target image data.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program according to the steps of the drone motion control method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method for controlling the motion of a drone as claimed in any one of claims 1 to 7.