A method and device for correcting the flight path of an LED display screen using a drone

Abstract

This application relates to the field of LED displays and discloses a method and apparatus for calibrating the flight path of an LED display screen using a drone. The method includes: controlling the drone's field of view to align with the center of a sign frame, controlling an LED module to display a module code, obtaining a module code image captured by the drone, identifying the module code image to determine a starting module, and controlling the drone to calibrate the LED display screen along two different preset flight paths, using the starting module as a starting point. By using any module position as the drone's initial takeoff position, the drone's takeoff position becomes more flexible. Furthermore, the drone operates fully automatically, eliminating the need to control the drone to fly to the upper left corner of the LED display screen each time, thereby improving the efficiency of LED display screen calibration.

Description

Technical Field

[0001] The present application relates to the field of LED displays, and in particular to a method and device for correcting the flight path of an LED display screen by a drone. Background Art

[0002] When using a drone to perform on-site calibration of an LED display, it is necessary to complete the calibration by taking a photo of each module. Traditional calibration methods include manual and semi-automatic methods.

[0003] Manual photo calibration involves manually controlling the drone to take off, manually flying the drone to the front of each module for photo calibration, and manually landing the drone after calibration. Semi-automatic photo calibration involves manually controlling the drone to take off, manually flying the drone to a specified starting point (such as the upper left corner), completing photo calibration for each module along a fixed path, and manually landing the drone after calibration. Due to the limited flight time of drones, manual and semi-automatic calibration methods are inefficient. Summary of the Invention

[0004] Based on this, it is necessary to provide a method and device for correcting the flight path of an LED display screen by a drone to address the above technical problems, which can improve the correction efficiency of the LED display screen.

[0005] In a first aspect, an embodiment of the present application provides a method for correcting the flight path of an LED display screen by a drone, the method comprising:

[0006] Control the drone's field of view to align with the center of the sign's border;

[0007] Control the LED module to display the module code;

[0008] Obtaining a module code image taken by the drone;

[0009] Identifying the module code image to determine the starting module;

[0010] Starting from the starting module, correct the next module with a smaller code than the current module in units of rows;

[0011] Record the offset of the current position of the drone relative to the starting module position until the module with the smallest module code is calibrated;

[0012] Get the total offset;

[0013] controlling the drone to return to the starting module based on the total offset;

[0014] Starting from the initial module again, calibrate the next module with a larger module code than the current module in units of rows, until the module with the largest module code is calibrated; or

[0015] Starting from the starting module, correct the next module with a larger code than the current module in units of rows;

[0016] Record the offset of the current position of the drone relative to the starting module position until the module with the largest module code is corrected;

[0017] Get the total offset;

[0018] controlling the drone to return to the starting module based on the total offset;

[0019] Taking the initial module as the starting point again, the next module with a smaller module code than the current module is corrected in order in rows until the module with the smallest module code is corrected.

[0020] In some embodiments, controlling the center of the drone's field of view to align with the center of the sign frame includes:

[0021] Get the pictures collected during the automatic takeoff of the drone;

[0022] Identify the image and determine a landmark border close to the center of the drone's field of view;

[0023] The center of the UAV's field of view is controlled to align with the center of the logo frame.

[0024] In some embodiments, identifying the module code image to determine the starting module includes:

[0025] The module encoding picture is identified by a pre-trained recognition model to determine the starting module.

[0026] In some embodiments, the method further comprises:

[0027] Control the drone to land automatically according to the preset landing path.

[0028] In a second aspect, an embodiment of the present application further provides a device for correcting the flight path of an LED display screen by a drone, the device comprising:

[0029] The first control module is used to control the center of the drone's field of view to align with the center of the sign frame;

[0030] The second control module is used to control the LED module to display the module code;

[0031] A first acquisition module is used to acquire a module code image taken by the drone;

[0032] An identification module, configured to identify the module code image and determine a starting module;

[0033] A first correction module is configured to correct the next module with a smaller code than the current module in units of rows, starting from the starting module;

[0034] A first recording module is used to record the offset of the current position of the drone relative to the position of the starting module until the module with the smallest module code is corrected;

[0035] The second acquisition module is used to obtain the total offset;

[0036] a third control module, configured to control the drone to return to the starting module based on the total offset;

[0037] The second correction module is configured to start again with the starting module and sequentially correct the next module with a larger module code than the current module in units of rows until the module with the largest module code is corrected; or

[0038] A third correction module is configured to correct the next module with a larger code than the current module in units of rows, starting from the starting module;

[0039] A second recording module is used to record the offset of the current position of the drone relative to the position of the starting module until the module with the largest module code is corrected;

[0040] The third acquisition module is used to obtain the total offset;

[0041] a fourth control module, configured to control the drone to return to the starting module based on the total offset;

[0042] The fourth correction module is configured to again use the initial module as a starting point and sequentially correct the next module with a smaller module code than the current module in units of rows until the module with the smallest module code is corrected.

[0043] In some embodiments, the first control module is specifically configured to:

[0044] Get the pictures collected during the automatic takeoff of the drone;

[0045] Identify the image and determine a landmark border close to the center of the drone's field of view;

[0046] The center of the UAV's field of view is controlled to align with the center of the logo frame.

[0047] In some embodiments, the identification module is specifically configured to:

[0048] The module encoding picture is identified by a pre-trained recognition model to determine the starting module.

[0049] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0050] at least one processor; and,

[0051] a memory communicatively connected to the at least one processor; wherein,

[0052] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the method according to the first aspect.

[0053] In a fourth aspect, an embodiment of the present application further provides a system for determining a drone flight path based on an LED module, comprising:

[0054] The electronic device, the drone and the LED display screen of the third aspect, wherein the electronic device is connected to the drone and the LED display screen respectively.

[0055] In a fifth aspect, an embodiment of the present application further provides a non-volatile computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor executes the method described in the first aspect.

[0056] Compared with the prior art, the beneficial effects of the present application are: different from the prior art, a method for correcting the flight path of an LED display screen by a drone in an embodiment of the present application controls the center of the drone's field of view to align with the center of the sign frame, then controls the LED module to display the module code, and obtains the module code picture taken by the drone, and then identifies the module code picture to determine the starting module, and finally uses the starting module as the starting point to control the drone to correct the LED display screen according to two different preset flight paths. By using any position of the module as the initial position for the drone to take off, the drone's take-off position is more flexible, and the drone operates fully automatically, and there is no need to control the drone to fly to the upper left corner of the LED display screen every time, which can improve the efficiency of LED display screen correction. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] One or more embodiments are exemplarily illustrated by pictures in the corresponding drawings. These exemplifications do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are represented as similar elements. Unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0058] Figure 1 This is a schematic diagram of an application scenario of the method for correcting the flight path of an LED display screen by a drone of the present application;

[0059] Figure 2 This is a flow chart of a method for correcting the flight path of an LED display screen by a drone provided in one embodiment of the present application;

[0060] Figure 2a This is a schematic diagram of a process for automatically correcting an LED display screen through a first preset flight path provided by an embodiment of the present application;

[0061] Figure 2b This is a schematic diagram of a process for automatically correcting an LED display screen through a second preset flight path provided by another embodiment of the present application;

[0062] Figure 3 This is a schematic diagram of module coding provided by an embodiment of the present application;

[0063] Figure 4 This is a schematic diagram of a process for determining a marker frame at the center of a drone's field of view, provided by one embodiment of the present application;

[0064] Figure 5 This is a schematic diagram of a specific logo of an LED display screen provided by an embodiment of the present application;

[0065] Figure 6a This is a schematic diagram of the structure of a device for correcting the flight path of an LED display screen by a drone, provided by one embodiment of the present application;

[0066] Figure 6b This is a schematic diagram of the structure of a device for correcting the flight path of an LED display screen by a drone, provided in another embodiment of the present application;

[0067] Figure 7 This is a schematic diagram of the hardware structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0068] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0069] It should be noted that, if there is no conflict, the various features in the embodiments of the present application can be combined with each other and are all within the scope of protection of the present application. In addition, although the functional modules are divided in the device schematic and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order than the module division in the device or the order in the flow chart. Furthermore, the words "first", "second", "third", etc. used in this application do not limit the data and execution order, but only distinguish between the same items or similar items with basically the same functions and effects.

[0070] The method provided in this application for correcting the flight path of an LED display screen by a drone is applicable to Figure 1 The application scenario shown in this embodiment is a system 1 for determining the flight path of a drone based on an LED module, including an electronic device 10, a drone 20 and an LED display screen 30, and the electronic device 10 is connected to the drone 20 and the LED display screen 30 respectively.

[0071] The electronic device 10 can be any device with image processing and control capabilities, such as a smart terminal or computer. The drone 20 is equipped with an RGB camera and a binocular ranging camera. The LED display screen 30 is composed of multiple modules, each of which is provided with a continuous and unique module code, including but not limited to numbers, symbols, images, or text. The LED display screen 30 is also provided with a logo pattern.

[0072] The drone 20 is used to receive control instructions and collect pictures, and then send the pictures to the electronic device 10. The electronic device 10 is used to process the pictures sent by the drone 20 and send the processing results to the LED display screen 30, so that the control card of the LED display screen 30 can calibrate the LED display screen 30 according to the processing results.

[0073] like Figure 2 As shown, an embodiment of the present application provides a method for a drone to correct the flight path of an LED display screen, the method comprising:

[0074] Step 210: Control the drone's field of view to align with the center of the sign frame.

[0075] During the take-off phase, the drone needs to find the LED display screen during the upward flight and ensure that the drone can capture a larger local area of ​​the LED display screen. Therefore, it is necessary to set a logo on the LED display screen in advance. In the embodiment of the present application, the logo on the LED display screen can be, for example, any si gn logo, and the width and height of the si gn logo are set to one-sixth of the actual width of the LED display screen and one-twelfth of the actual height of the LED display screen, respectively. In other embodiments, the width and height of the logo on the LED display screen can be set according to the actual size of the LED display screen, without being bound by the limitations in this embodiment. Specifically, the electronic device controls the center of the drone's field of view to align with the center of the logo frame on the LED display screen.

[0076] In some embodiments, as a specific implementation of step 210, such as Figure 4 As shown, the method includes:

[0077] Step 410: Acquire images collected during the automatic takeoff of the drone.

[0078] Step 420: Identify the image and determine the marker frame close to the center of the drone's field of view.

[0079] Step 430: Control the drone's field of view to align with the center of the logo frame.

[0080] Before controlling the center of the drone's field of view to align with the center of the sign frame, it is first necessary to control the drone to take off and find the LED display. In the embodiment of the present application, the drone is placed directly below the LED display. The placement distance is adjustable, but it is necessary to ensure that the drone faces the LED display when it is on the ground. Specifically, the drone's camera is directed toward the LED display, and the drone is placed at a distance of more than 0.5 times the actual width of the LED display. After the drone takes off to the minimum height, it flies upwards to one-third of the height of the LED display several times. Each flight stop will capture a picture, and then send the picture to the electronic device.

[0081] After acquiring images captured by the drone, the electronic device identifies them to determine whether there is a takeoff sign in the drone's field of view. If the drone fails to locate the LED display after repeatedly ascending to a preset maximum altitude, it controls the drone to return to its original route. If the electronic device detects a sign on the LED display based on the image recognition results, it corrects the drone's deviation, aligning the drone's field of view with the center of the sign's border.

[0082] The specific process of identifying and calculating the center of the logo frame on the LED display is as follows: first, the electronic device obtains the picture collected during the automatic takeoff of the drone, and then recognizes the picture through the built-in YOLO recognition model to determine the target and the target frame close to the center of the drone's field of view. Then, the center coordinates of multiple target frames are calculated, and their distances from the center coordinates of the picture are calculated at the same time, and the target frame corresponding to the closest center coordinate is found. Specifically, the electronic device uses the known information of the LED display and the target frame information to obtain the conversion coefficient between the image space of the target image and the actual physical space. Figure 5 As shown, for example, the logo on the LED display is AOTO, and the physical length and width of the AOTO logo are a fixed ratio of the physical width of the LED screen. The algorithm calculates the physical width RW of the AOTO logo obj (unit: m), and the pixel width PW of the central target box is obtained through the results of the YOLO recognition model obj , the ratio of these two values ​​is the conversion coefficient RW pixel The conversion coefficient can be used to calculate the actual physical length corresponding to one pixel width, and the reciprocal of the conversion coefficient can be used to calculate how many pixels correspond to a physical length of 1m.

[0083] The coordinates of the center of the logo pattern frame in the image (Cx obj ,Cy obj ) and the image center coordinates (Cx image ,Cy image ) can estimate the actual distance Dx between the current lens center and the target frame center on the x-axis and y-axis in the spatial coordinate system (obj,camera) , Dy (obj,camera) :

[0084] Dx (obj,camera) =(Cx obj -Cx image )×RW pixel

[0085] Dy (obj,camera) =(Cy obj -Cy image )×RW pixel

[0086] After the electronic device calculates the result, it sends the result to the drone's flight controller. Based on the result, the drone flight controller controls the drone to move a corresponding distance in the direction of the corresponding coordinate axis to fine-tune the drone's position so that the center of the drone's field of view is aligned with the center of the target frame, that is, the center of the marker frame.

[0087] Step 220: Control the LED module to display the module code.

[0088] When the center of the drone's field of view is aligned with the center of the logo frame, the logo pattern on the LED display screen is switched and the LED module is controlled to display the module code, such as Figure 3 As shown, each LED module is encoded in binary format. The module code is continuous and unique and includes, but is not limited to, numbers, symbols, images, or text. Furthermore, the module code frame is a square, and the number of LEDs on each side of the square is min(number of LEDs on the module's high side - 30, number of LEDs on the module's long side - 30).

[0089] Step 230: Obtain the module code image taken by the drone.

[0090] Step 240: Identify the module code image to determine the starting module.

[0091] After the LED module displays the module code, the drone captures a picture of the module code and sends it to the electronic device, which then identifies the module code picture and determines the starting module. Specifically, the electronic device uses a pre-trained YOLO recognition model to identify the coded area of ​​the coded picture, i.e., to identify the module code and determine the starting module and the exact center of the starting module. The starting module is the module directly opposite the center of the drone's field of view; in other words, the starting module is the module closest to the center of the drone's field of view.

[0092] In other embodiments, to facilitate a wider range of choices for the starting module, the starting module can also be any module of the module-coded image taken by the drone, that is, the starting module does not need to be the module facing the center of the drone's field of view.

[0093] The method for identifying the coding area is the same as that for finding the center of the landmark frame mentioned above. Please refer to the above identification method and will not be repeated here. The only difference is that the data used for training has more coding areas, and multiple coding data are required for training.

[0094] Step 250 , starting from the starting module, controls the drone to calibrate the LED display screen according to a preset flight path.

[0095] Traditionally, when calibrating an LED display, the drone must be controlled to fly to the upper left corner of the display each time, starting the subsequent calibration process from the upper left corner of the display. This results in low calibration efficiency. In the embodiments of the present application, the drone is controlled to automatically calibrate the LED display according to two different preset flight paths, which improves efficiency.

[0096] The first method of automatically correcting the LED display screen by presetting the flight path is as follows Figure 2a As shown:

[0097] Step 250 , starting from the initial module, calibrate the next module with a smaller code than the current module in units of rows.

[0098] Step 260 , recording the offset of the current position of the drone relative to the starting module position until the module with the smallest module code is calibrated;

[0099] Step 270, record and obtain the total offset;

[0100] Step 280 , recording and controlling the drone to return to the starting module based on the total offset;

[0101] Step 290 , record again starting from the initial module and sequentially calibrate the next module with a larger module code than the current module in units of rows until the module with the largest module code is calibrated.

[0102] Specifically, the drone takes the starting module as the starting point and sequentially corrects the next module with a smaller module code than the current module in units of behavior; records the offset of the drone's current position relative to the starting module's position until the module with the smallest module code is corrected; obtains a total offset; controls the drone to return to the starting module based on the total offset; and again takes the starting module as the starting point and sequentially corrects the next module with a larger module code than the current module in units of behavior until the module with the largest module code is corrected.

[0103] The second method of automatically correcting the LED display screen by presetting the flight path is as follows Figure 2b As shown:

[0104] Step 350 , starting from the initial module, calibrate the next module with a larger code than the current module in units of rows;

[0105] Step 360: Record the offset of the current position of the drone relative to the starting module position until the module with the largest module code is calibrated.

[0106] Step 370, obtaining the total offset;

[0107] Step 380: Control the drone to return to the starting module based on the total offset;

[0108] Step 390 , starting from the initial module again, calibrate the next module with a smaller module code than the current module in units of rows, until the module with the smallest module code is calibrated.

[0109] Specifically, the drone takes the starting module as the starting point and sequentially corrects the next module with a smaller module code than the current module in units of behavior; records the offset of the drone's current position relative to the starting module's position until the module with the smallest module code is corrected; obtains a total offset; controls the drone to return to the starting module based on the total offset; and again takes the starting module as the starting point and sequentially corrects the next module with a larger module code than the current module in units of behavior until the module with the largest module code is corrected.

[0110] In the specific implementation method, after reaching the new position through the preset flight path, that is, after the next module, flight error correction and distance maintenance are required. Flight error correction is to align the center of the drone's field of view with the center of the module to be corrected. First, it is necessary to calculate the pixel width and physical width of this coding frame, and obtain the conversion coefficient through the ratio of the two. Since the coding frame is a square, and the number of lamp beads on the side of the square = min (the number of lamp beads on the high side of the module - 30, the number of lamp beads on the long side of the module - 30), after obtaining the number of lamp beads corresponding to the side, the number of lamp beads is multiplied by the point spacing to obtain the physical length of the coding frame. The pixel length of the coding frame is obtained by combining the YOLO recognition model with post-processing, and then the pixel width of the fitted recognition frame is calculated, and the conversion coefficient is obtained by comparing it with the actual physical width of the corresponding coding frame.

[0111] After obtaining the conversion coefficient, the need for correction and the required displacement distance can be calculated using the horizontal and vertical coordinate differences between the center coordinates of the encoding frame and the image. This calculation and judgment method is consistent with the aforementioned method for finding the center of the marker frame. In other embodiments, after the drone reaches a new location via a preset flight path, i.e., after the next module, flight error correction is not required. Specifically, there is no need to align the center of the drone's field of view with the center of the module to be corrected, thereby improving correction efficiency.

[0112] In addition to flight error correction, it is also necessary to ensure that the drone and the LED module maintain a suitable distance during the correction process. Maintaining a suitable distance can ensure that the captured image is clear enough. The appropriate distance can be maintained by calculating the ratio of the module's pixel length to the entire image length. Specifically, the pixel length of the module needs to be calculated first. Since the module's physical length and width {RW module ,RH module}、The physical side length RW of the encoding frame codeBox , pixel side length PW of the coding frame codeBox It is known information, and the pixel length is proportional to the actual length, so the pixel length and width of the module {PW module ,PH module}Calculation is as follows,

[0113]

[0114]

[0115] Then calculate the ratio R between the length and width of the module and the length and width of the image in the picture using the following formula:

[0116]

[0117] Judge R moduleIs it within the threshold range? If it is greater than the upper threshold, it means that the distance to the screen is too close and needs to be moved back a certain distance. If it is less than the lower threshold, it means that the distance to the screen is too far and needs to be moved forward a certain distance. In this embodiment of the present application, the upper and lower limits of the threshold are set to 0.55 and 0.7 respectively.

[0118] In other embodiments, when the initial module is the upper left, lower left, upper right, or lower right corner of the LED display, the LED display can be calibrated using a traditional flight path. For example, the drone uses the leftmost module in the top row of modules on the LED display as the flight origin. The drone then flies rightward along the top row of modules to the rightmost module, then moves down one row, flies leftward from the rightmost module to the leftmost module, then moves down one row, and repeats the above steps until it reaches the last module.

[0119] In some embodiments, the method further includes: controlling the drone to automatically land according to a preset landing path.

[0120] Specifically, once the drone completes LED display calibration according to the preset flight path, it automatically returns from the current module to the LED module in the center of the screen, activates obstacle avoidance mode, and then retreats to a preset distance from the screen before descending. It should be noted that since the current module is the last one calibrated, its number is accumulated during the calibration phase. This number corresponds one-to-one with the module. The center module's code is calculated from the rows and columns of the LEDs. These two codes are used to calculate the flight path, thereby controlling the drone to automatically return from the current module to the LED module in the center of the screen.

[0121] An embodiment of the present application provides a method for correcting the flight path of an LED display screen by using a drone. By using any position of a module as the initial position for the drone to take off, the take-off position is made more flexible, and there is no need to control the drone to fly to the upper left corner of the LED display screen every time, which can improve the efficiency of LED display screen correction.

[0122] Accordingly, the embodiment of the present application also provides a device 600 for correcting the flight path of an LED display screen by a drone, such as Figure 6a As shown, including:

[0123] The first control module 610 is used to control the center of the drone's field of view to align with the center of the sign frame;

[0124] The second control module 620 is used to control the LED module to display the module code;

[0125] A first acquisition module 630 is configured to acquire a module code image taken by the drone;

[0126] Identification module 640, used to identify the module code image and determine the starting module;

[0127] A first correction module 650 is configured to correct the next module with a smaller code than the current module, starting from the starting module and in units of rows;

[0128] A first recording module 660 is configured to record the offset of the current position of the drone relative to the position of the starting module until the module with the smallest module code is corrected;

[0129] A second obtaining module 670 is used to obtain a total offset;

[0130] A third control module 680 is configured to control the drone to return to the starting module based on the total offset;

[0131] The second correction module 690 is configured to start again with the initial module and sequentially correct the next module with a larger module code than the current module in units of rows until the module with the largest module code is corrected.

[0132] The embodiment of the present application also provides a device 600 for correcting the flight path of an LED display screen by a drone, such as Figure 6b As shown, including:

[0133] The first control module 610 is used to control the center of the drone's field of view to align with the center of the sign frame;

[0134] The second control module 620 is used to control the LED module to display the module code;

[0135] A first acquisition module 630 is configured to acquire a module code image taken by the drone;

[0136] Identification module 640, used to identify the module code image and determine the starting module;

[0137] A third correction module 650 is configured to correct the next module with a larger code than the current module, starting from the starting module and in units of rows;

[0138] The second recording module 660 is used to record the offset of the current position of the drone relative to the starting module position until the module with the largest module code is corrected;

[0139] The third acquisition module 670 is used to obtain the total offset;

[0140] A fourth control module 680 is configured to control the drone to return to the starting module based on the total offset;

[0141] The fourth correction module 690 is configured to again use the initial module as the starting point and sequentially correct the next module with a smaller module code than the current module in units of rows until the module with the smallest module code is corrected.

[0142] The embodiment of the present application provides a device for correcting the flight path of an LED display screen by a drone. The device controls the center of the drone's field of view to align with the center of the sign frame through a first control module, then controls the LED module to display the module code through a second control module, then obtains the module code image taken by the drone through an acquisition module, and identifies the module code image through an identification module to determine the starting module. Finally, the correction module uses the starting module as the starting point to control the drone to correct the LED display screen according to two different preset flight paths. By using any position of the module as the initial position for the drone to take off, the take-off position is made more flexible, and there is no need to control the drone to fly to the upper left corner of the LED display screen every time, which can improve the efficiency of LED display screen correction. Optionally, in other embodiments of the device, please refer to Figure 6, the device 600 also includes:

[0143] The landing module 700 is used to control the UAV to automatically land according to a preset landing path.

[0144] Optionally, in other embodiments of the device, the first control module 610 is specifically configured to:

[0145] Get the pictures collected during the automatic takeoff of the drone;

[0146] Identify the image and determine a landmark border close to the center of the drone's field of view;

[0147] The center of the UAV's field of view is controlled to align with the center of the logo frame.

[0148] Optionally, in other embodiments of the device, the identification module 640 is specifically configured to:

[0149] The module encoding picture is identified by a pre-trained recognition model to determine the starting module.

[0150] It should be noted that the aforementioned device for correcting the flight path of an LED display screen by a drone can implement the method for correcting the flight path of an LED display screen by a drone provided in the embodiments of this application, and possesses the corresponding functional modules and beneficial effects of the method. For technical details not fully described in the embodiment of the device for correcting the flight path of an LED display screen by a drone, please refer to the method for correcting the flight path of an LED display screen by a drone provided in the embodiments of this application.

[0151] Figure 7 FIG is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention, such as Figure 7As shown, the electronic device 700 includes:

[0152] One or more processors 710 and memory 720, Figure 7 A processor 710 is taken as an example.

[0153] The processor 710 and the memory 720 may be connected via a bus or other means. Figure 7 The bus connection is taken as an example.

[0154] Memory 720, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs, and modules, such as the program instructions / modules corresponding to the method for correcting the flight path of an LED display screen by a drone in an embodiment of the present application (for example, the first control module 610, the second control module 620, the acquisition module 630, the identification module 640, the correction module 650, and the landing module 660 shown in FIG. 6). By running the non-volatile software programs, instructions, and modules stored in memory 720, the processor 710 executes various functional applications and data processing of the electronic device, thereby implementing the method for correcting the flight path of an LED display screen by a drone in the above-mentioned method embodiment.

[0155] Memory 720 may include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function; the data storage area may store data generated based on the use of the device for correcting the flight path of an unmanned aerial vehicle (UAV) LED display. Furthermore, memory 720 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state memory device. In some embodiments, memory 720 may optionally include memory remotely located relative to processor 710. Such remote memory may be connected to the device for correcting the flight path of an UAV LED display via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0156] The one or more modules are stored in the memory 720, and when executed by the one or more electronic devices 700, a method for correcting the flight path of an LED display screen by a drone in any of the above method embodiments is executed, for example, Figure 2 Steps 210 to 250 of the method, Figure 2a In method steps 210-290, as Figure 2b Method steps 210-390, Figure 4 Method steps 410 to 430; implementing Figure 6a Middle modules 610 to 700, Figure 6bThe functions of modules 610-700.

[0157] An embodiment of the present application also provides a non-volatile computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by one or more processors, the one or more processors can execute a method for correcting the flight path of an LED display screen by a drone in any of the above embodiments.

[0158] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0159] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course, can also be implemented by hardware. Those skilled in the art can understand that all or part of the processes in the above embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Based on the concept of the present application, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the present application as described above. For the sake of simplicity, they are not provided in detail. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for correcting the flight path of an LED display screen by a drone, characterized in that: The method comprises: Control the center of the drone's field of view to align with the center of the sign's border; Control the LED module to display the module code; Obtaining a module code image taken by the drone; Identifying the module code image to determine the starting module; Starting from the starting module, correct the next module with a smaller code than the current module in units of rows; Record the offset of the current position of the drone relative to the starting module position until the module with the smallest module code is calibrated; Get the total offset; controlling the drone to return to the starting module based on the total offset; Taking the starting module as the starting point again, calibrate the next module with a larger module code than the current module in units of rows, until the module with the largest module code is calibrated; or Starting from the starting module, correct the next module with a larger code than the current module in units of rows; Record the offset of the current position of the drone relative to the starting module position until the module with the largest module code is corrected; Get the total offset; controlling the drone to return to the starting module based on the total offset; Taking the initial module as the starting point again, the next module with a smaller module code than the current module is corrected in order in rows until the module with the smallest module code is corrected.

2. The method according to claim 1, characterized in that Controlling the center of the drone's field of view to align with the center of the sign frame includes: Get the pictures collected during the automatic takeoff of the drone; Identify the image and determine a landmark border close to the center of the drone's field of view; The center of the UAV's field of view is controlled to align with the center of the logo frame.

3. The method according to claim 2, characterized in that The step of identifying the module code picture and determining the starting module includes: The module encoding picture is identified by a pre-trained recognition model to determine the starting module.

4. The method according to claim 3, characterized in that The method further comprises: Control the drone to land automatically according to the preset landing path.

5. A device for correcting the flight path of an LED display screen by a drone, characterized in that: The device comprises: The first control module is used to control the center of the drone's field of view to align with the center of the sign frame; The second control module is used to control the LED module to display the module code; A first acquisition module is used to acquire a module code image taken by the drone; An identification module, configured to identify the module code image and determine a starting module; A first correction module is configured to correct the next module with a smaller code than the current module in units of rows, starting from the starting module; A first recording module is used to record the offset of the current position of the drone relative to the position of the starting module until the module with the smallest module code is corrected; The second acquisition module is used to obtain the total offset; a third control module, configured to control the drone to return to the starting module based on the total offset; The second correction module is configured to start again with the starting module and sequentially correct the next module with a larger module code than the current module in units of rows until the module with the largest module code is corrected; or A third correction module is configured to correct the next module with a larger code than the current module in units of rows, starting from the starting module; A second recording module is used to record the offset of the current position of the drone relative to the position of the starting module until the module with the largest module code is corrected; The third acquisition module is used to obtain the total offset; a fourth control module, configured to control the drone to return to the starting module based on the total offset; The fourth correction module is configured to again use the initial module as a starting point and sequentially correct the next module with a smaller module code than the current module in units of rows until the module with the smallest module code is corrected.

6. The device according to claim 5, characterized in that The first control module is specifically configured to: Get the pictures collected during the automatic takeoff of the drone; Identify the image and determine a landmark border close to the center of the drone's field of view; The center of the UAV's field of view is controlled to align with the center of the logo frame.

7. The device according to claim 6, characterized in that The identification module is specifically used for: The module encoding picture is identified by a pre-trained recognition model to determine the starting module.

8. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

9. A system for determining the flight path of a drone based on an LED module, characterized in that: The electronic device, drone and LED display according to claim 8 are included. The electronic equipment is connected to the drone and the LED display screen respectively.

10. A non-volatile computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the processor is caused to execute the method according to any one of claims 1 to 4.

Images