Unmanned aerial vehicle image processing system, method, device, equipment and medium

Abstract

The embodiment of the invention provides an unmanned aerial vehicle image processing system, method, device and equipment and a medium. The system comprises an unmanned aerial vehicle and a server. The unmanned aerial vehicle is used for shooting images according to a preset time interval and acquiring a shooting position when the images are shot; determining a reference image; for images shot after the reference image, respectively comparing the images with previous images shot at adjacent time intervals to obtain difference images corresponding to the images shot after the reference image; sending the reference image, the shooting position of the reference image, a difference image corresponding to an image shot after the reference image and the shooting position to a server; the server is used for determining the flight path of the unmanned aerial vehicle according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image; and according to the flight path, the reference image and the difference image, obtaining an image shot after the reference image, thereby reducing image data packets returned by the unmanned aerial vehicle, and improving the efficiency of image data transmission.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an unmanned aerial vehicle image processing system, method, device, equipment and medium. Background Art

[0002] Usually, video playback is like a movie, with a minimum of 24 frames per second. In this case, the human eye cannot distinguish the images and thinks it is a continuous video playback. With the development of science and technology, more and more drones are used for aerial photography. Drone aerial photography is to transmit multiple continuous images to the system, and then the system interprets the multiple continuous images into videos. As the distance between the drone and the interactive device becomes farther and farther, the clearer the image sent back by the drone, the larger the amount of data sent back, which will greatly reduce the efficiency of image data transmission. Summary of the invention

[0003] In order to solve the above problems, the embodiments of the present invention disclose a drone image processing system, method, device, equipment and medium.

[0004] In a first aspect, an embodiment of the present invention provides a drone image processing system, including: a drone and a server;

[0005] The drone is used to capture images at preset time intervals and obtain a capture position when capturing images; determine a reference image from the captured images; compare the images captured after the reference image with previous images captured at adjacent time intervals to obtain a difference image corresponding to the image captured after the reference image; send the reference image, the capture position corresponding to the reference image, the difference image and the capture position corresponding to the image captured after the reference image to the server, so that the server determines a flight trajectory of the drone according to the capture position corresponding to the reference image and the capture position corresponding to the image captured after the reference image; obtain an image captured after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the image captured after the reference image;

[0006] The server is used to receive the reference image, the shooting position corresponding to the reference image, and the difference image and shooting position corresponding to the image shot after the reference image, which are sent by the drone; determine the flight trajectory of the drone according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image, and obtain the image shot after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the image shot after the reference image.

[0007] Optionally, the shooting position when shooting the image is the position coordinates of the shot image in a spatial rectangular coordinate system;

[0008] The drone is used to obtain the position coordinates when taking an image; send the position coordinates corresponding to the reference image and the position coordinates corresponding to the image taken after the reference image to the server, so that the server performs a difference operation between the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals to obtain the flight trajectory of the drone;

[0009] The server is used to receive the position coordinates corresponding to the reference image sent by the drone and the position coordinates corresponding to the image taken after the reference image; perform difference calculation on the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals to obtain the flight trajectory of the drone.

[0010] Optionally, the drone is used to compare the image taken after the reference image with the previous image taken at adjacent time intervals, respectively, to determine the overlapping area of ​​the image taken after the reference image; based on the overlapping area, the image taken after the reference image is cropped to obtain a difference image corresponding to the image taken after the reference image.

[0011] Optionally, the server is used to determine, according to the flight trajectory of the drone, a compensation area corresponding to the image taken after the reference image in the previous images taken at adjacent time intervals; and splice the compensation area with the difference images corresponding to the images taken after the reference image to obtain the images taken after the reference image.

[0012] In a second aspect, an embodiment of the present invention provides a method for processing an image of a drone, which is applied to a drone, and the method includes:

[0013] Taking images at a preset time interval and obtaining the shooting position when the images are taken;

[0014] Determine a reference image from the captured images;

[0015] For an image taken after the reference image, respectively compare the image with a previous image taken at adjacent time intervals to obtain a difference image corresponding to the image taken after the reference image;

[0016] The reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the image shot after the reference image are sent to the server, so that the server determines the flight trajectory of the UAV according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image, and obtains the image shot after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the image shot after the reference image.

[0017] Optionally, the shooting position when shooting the image is the position coordinate of the shot image in a spatial rectangular coordinate system; the sending of the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the image shot after the reference image to the server, so that the server determines the flight trajectory of the UAV according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image, includes:

[0018] The position coordinates corresponding to the reference image and the position coordinates corresponding to the image taken after the reference image are sent to the server, so that the server performs a difference operation on the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals to obtain the flight trajectory of the drone.

[0019] Optionally, the comparing the image with a previous image taken at adjacent time intervals to obtain a difference image corresponding to an image taken after the reference image includes:

[0020] Comparing the images captured after the reference image with the previous images captured at adjacent time intervals respectively, to determine the overlapping areas of the images captured after the reference image;

[0021] The image captured after the reference image is cropped according to the overlapping area to obtain a difference image corresponding to the image captured after the reference image.

[0022] Optionally, the server determines, according to the flight trajectory of the drone, a compensation area corresponding to the image taken after the reference image in the previous images taken at adjacent time intervals, and splices the compensation area with the difference images corresponding to the images taken after the reference image.

[0023] In a third aspect, an embodiment of the present invention provides a method for processing drone images, which is applied to a server. The method includes:

[0024] Receive a reference image sent by a drone, a shooting position corresponding to the reference image, and a difference image and shooting position corresponding to an image shot after the reference image;

[0025] Determining a flight trajectory of the UAV according to a shooting position corresponding to the reference image and a shooting position corresponding to an image shot after the reference image;

[0026] The image shot after the reference image is obtained according to the flight trajectory, the reference image and the difference image corresponding to the image shot after the reference image.

[0027] Optionally, the shooting position when shooting the image is a position coordinate of the shot image in a spatial rectangular coordinate system; and determining the flight trajectory of the drone according to the shooting position corresponding to the reference image and the shooting position corresponding to an image shot after the reference image includes:

[0028] Receiving the position coordinates corresponding to the reference image and the position coordinates corresponding to the image taken after the reference image sent by the drone;

[0029] The flight trajectory of the UAV is obtained by performing a difference operation on the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals.

[0030] Optionally, the difference image corresponding to the image taken after the reference image is obtained by the drone comparing the image taken after the reference image with a previous image taken at adjacent time intervals, determining the overlapping area of ​​the image taken after the reference image, and cropping the image taken after the reference image according to the overlapping area.

[0031] Optionally, obtaining the image shot after the reference image according to the flight trajectory, the reference image and a difference image corresponding to an image shot after the reference image comprises:

[0032] According to the flight trajectory of the UAV, determining, in the previous images taken at adjacent time intervals, compensation areas corresponding to the images taken after the reference image;

[0033] The compensation area is respectively spliced ​​with the difference image corresponding to the image shot after the reference image to obtain the image shot after the reference image.

[0034] In a fourth aspect, an embodiment of the present invention provides a drone image processing device, which is applied to a drone, and the device includes:

[0035] A shooting image acquisition module is used to shoot images at preset time intervals and obtain the shooting position when the images are shot;

[0036] A reference image determination module, used to determine a reference image from the captured image;

[0037] a difference image determination module, for comparing an image taken after the reference image with a previous image taken at adjacent time intervals, to obtain a difference image corresponding to the image taken after the reference image;

[0038] The reference image sending module is used to send the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the image shot after the reference image to the server, so that the server can determine the flight trajectory of the UAV according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image, and obtain the image shot after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the image shot after the reference image.

[0039] Optionally, the shooting position when shooting the image is the position coordinates of the shot image in a spatial rectangular coordinate system; the reference image sending module includes:

[0040] The reference image sending submodule is used to send the position coordinates corresponding to the reference image and the position coordinates corresponding to the image taken after the reference image to the server, so that the server performs a difference operation on the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals to obtain the flight trajectory of the UAV.

[0041] Optionally, the difference image determination module includes:

[0042] An overlapping region determination submodule, used to compare the image captured after the reference image with the previous image captured at adjacent time intervals, respectively, to determine the overlapping region of the image captured after the reference image;

[0043] The difference image determination submodule is used to crop the image shot after the reference image according to the overlapping area to obtain a difference image corresponding to the image shot after the reference image.

[0044] Optionally, the server determines, according to the flight trajectory of the drone, a compensation area corresponding to the image taken after the reference image in the previous images taken at adjacent time intervals, and splices the compensation area with the difference images corresponding to the images taken after the reference image.

[0045] In a fifth aspect, an embodiment of the present invention provides a drone image processing device, which is applied to a server, and the device includes:

[0046] A reference image receiving module, used to receive a reference image sent by a drone, a shooting position corresponding to the reference image, and a difference image and shooting position corresponding to an image shot after the reference image;

[0047] A flight trajectory determination module, used to determine the flight trajectory of the UAV according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image;

[0048] The captured image restoration module is used to obtain the image captured after the reference image based on the flight trajectory, the reference image and the difference image corresponding to the image captured after the reference image.

[0049] Optionally, the shooting position when shooting the image is the position coordinate of the shot image in a spatial rectangular coordinate system; the flight trajectory determination module includes:

[0050] A position coordinate receiving submodule, used to receive the position coordinates corresponding to the reference image and the position coordinates corresponding to the image taken after the reference image sent by the drone;

[0051] The flight trajectory determination submodule is used to perform a difference operation between the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals to obtain the flight trajectory of the UAV.

[0052] Optionally, the difference image corresponding to the image taken after the reference image is obtained by the drone comparing the image taken after the reference image with a previous image taken at adjacent time intervals, determining the overlapping area of ​​the image taken after the reference image, and cropping the image taken after the reference image according to the overlapping area.

[0053] Optionally, the captured image restoration module includes:

[0054] A compensation area determination submodule, used to determine, according to the flight trajectory of the UAV, in the previous images taken at adjacent time intervals, the compensation area corresponding to the image taken after the reference image;

[0055] The captured image restoration submodule is used to stitch the compensation area with the difference images corresponding to the images captured after the reference image to obtain the images captured after the reference image.

[0056] In a sixth aspect, the present invention shows an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned drone image processing method when executing the computer program.

[0057] In a seventh aspect, the present invention shows a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned drone image processing method are implemented.

[0058] The embodiments of the present invention include the following advantages:

[0059] The drone image processing system of the embodiment of the present invention comprises: a drone and a server; the drone is used to take images at preset time intervals and obtain the shooting position when taking the images; determine the reference image from the captured images; for the images taken after the reference image, respectively compare the images with the previous images taken at adjacent time intervals to obtain the difference images corresponding to the images taken after the reference image; send the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the images taken after the reference image to the server, so as to reduce each image data packet transmitted back; the server is used to determine the flight trajectory of the drone according to the shooting position corresponding to the reference image and the shooting position corresponding to the images taken after the reference image; obtain the images taken after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the images taken after the reference image, so as to restore the images and reduce pixel distortion. The embodiment of the present invention can reduce the image data packets transmitted back by the drone while ensuring the image clarity, thereby improving the efficiency of image data transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0061] Figure 1 is a structural block diagram of a drone image processing system according to an embodiment of the present invention;

[0062] Figure 2 is a schematic diagram of a drone image processing system according to an embodiment of the present invention;

[0063] Figure 3 is a flowchart of the steps of a method for processing drone images according to an embodiment of the present invention;

[0064] Figure 4 is a flowchart of another method for processing drone images according to an embodiment of the present invention;

[0065] Figure 5 is a structural block diagram of a drone image processing device according to an embodiment of the present invention;

[0066] Figure 6 4 is a structural block diagram of another unmanned aerial vehicle image processing device according to an embodiment of the present invention.

[0067] Description of reference numerals:

[0068] Drone 11 and server 12. DETAILED DESCRIPTION

[0069] The present invention proposes a method for processing drone images, the purpose of which is to improve the efficiency of drone image data transmission. To achieve this goal, the embodiment of the present invention crops the image transmitted back by the drone to reduce the image data packet transmitted back by the drone, and restores the cropped image through a server, thereby improving the efficiency of image data transmission while ensuring image clarity.

[0070] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0071] Reference Figure 1 , shows a structural block diagram of a drone image processing system according to an embodiment of the present invention. The system comprises: a drone 11 and a server 12;

[0072] The drone 11 is used to take images at preset time intervals and obtain the shooting positions when taking the images; determine a reference image from the captured images; compare the images taken after the reference image with the previous images taken at adjacent time intervals, respectively, to obtain a difference image corresponding to the image taken after the reference image; send the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the image taken after the reference image to the server 12, so that the server 12 determines the flight trajectory of the drone 11 according to the shooting position corresponding to the reference image and the shooting position corresponding to the image taken after the reference image; obtain the image taken after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the image taken after the reference image;

[0073] In an embodiment of the present invention, the drone can take images at preset time intervals and obtain the shooting position when the images are taken. The preset time interval can be 0.04 seconds, that is, the drone takes 25 pictures in one second. The higher the definition of the video, the more pictures the drone takes per second. The drone can determine the reference image from the captured images; for the images taken after the reference image, the images are compared with the previous images taken at adjacent time intervals to obtain the difference images corresponding to the images taken after the reference image; the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the images taken after the reference image are sent to the server, so that each returned image data packet can be reduced by only returning the difference image, so that the video presented by the interaction between the drone and the server can be faster, reduce pixel distortion, and bring a better user experience to the user.

[0074] For example, assuming that the first image taken by the camera is the reference image, the second image is obtained after the adjacent time interval of the reference image is 0.04 seconds. By calculating the overlapped portion of the second image with the first image, the newly added portion of the second image (i.e., the difference image) is transmitted back based on the overlapped portion. The server can analyze how much of the second image needs to be cut from the first image to compensate and restore the second image based on the fixed size of the image.

[0075] The server 12 is used to receive the reference image, the shooting position corresponding to the reference image, and the difference image and shooting position corresponding to the image shot after the reference image, which are sent by the drone 11; determine the flight trajectory of the drone 11 according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image, and obtain the image shot after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the image shot after the reference image.

[0076] In the embodiment of the present invention, the server may be a mobile terminal or other intelligent device having an image processing function and an interactive function with the drone. The server may determine the flight trajectory of the drone based on the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image; and restore the returned image based on the flight trajectory, the reference image, and the difference image corresponding to the image shot after the reference image to obtain the image shot after the reference image.

[0077] The drone image processing system of the embodiment of the present invention comprises: a drone and a server; the drone is used to take images at preset time intervals and obtain the shooting position when taking the images; determine the reference image from the captured images; for the images taken after the reference image, respectively compare the images with the previous images taken at adjacent time intervals to obtain the difference images corresponding to the images taken after the reference image; send the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the images taken after the reference image to the server, so as to reduce each image data packet transmitted back; the server is used to determine the flight trajectory of the drone according to the shooting position corresponding to the reference image and the shooting position corresponding to the images taken after the reference image; obtain the images taken after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the images taken after the reference image, so as to restore the images and reduce pixel distortion. The embodiment of the present invention can reduce the image data packets transmitted back by the drone while ensuring the image clarity, thereby improving the efficiency of image data transmission.

[0078] In one embodiment, the shooting position when shooting the image is the position coordinates of the shot image in a spatial rectangular coordinate system;

[0079] The drone 11 is used to obtain the position coordinates when taking an image; send the position coordinates corresponding to the reference image and the position coordinates corresponding to the image taken after the reference image to the server 12, so that the server 12 performs a difference operation between the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals, and obtains the flight trajectory of the drone 11;

[0080] The server 12 is used to receive the position coordinates corresponding to the reference image and the position coordinates corresponding to the image taken after the reference image sent by the drone 11; perform difference calculation on the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals to obtain the flight trajectory of the drone 11.

[0081] In an embodiment of the present invention, the shooting position when shooting an image may be the position coordinates of the shooting image in a spatial rectangular coordinate system. The drone may obtain the position coordinates when shooting an image; send the position coordinates corresponding to the reference image and the position coordinates corresponding to the image shot after the reference image to the server, so that the server performs a difference operation between the position coordinates corresponding to each image shot after the reference image and the position coordinates of the previous image shot at adjacent time intervals, and obtain the flight trajectory of the drone.

[0082] In one embodiment, the drone 11 is used to compare the image taken after the reference image with the previous image taken at adjacent time intervals, respectively, to determine the overlapping area of ​​the image taken after the reference image; based on the overlapping area, the image taken after the reference image is cropped to obtain a difference image corresponding to the image taken after the reference image.

[0083] Reference Figure 2 , shows a schematic diagram of a drone image processing system according to an embodiment of the present invention. The position coordinates of the image taken by the drone during navigation are calculated by sensors such as a camera and a gyroscope on the drone to determine the flight trajectory of the drone.

[0084] For example, Figure 2 As shown in the figure, when the reference image is F0 and the second image taken 0.04 seconds later is F1, the drone is in a level flight state. The gyroscope records the position coordinates of the reference image F0 as X0, Y0, and Z0, and the position coordinates of the second image F1 as X1, Y1, and Z1. By performing a difference operation between the position coordinates of the second image and the position coordinates of the reference image, the distance traveled by the drone can be obtained, so that the flight trajectory of the drone can be known, and the direction in which the second image overlaps with the reference image can also be known. The four corners of the reference image F0 are set to a0, b0, c0, and d0 respectively. The four corners of the second picture F1 are set to a1, b1, c1, and d1 respectively. The UAV system cuts the a1, b1, c0, and d0 parts of the second picture from the overlapping parts of the two pictures, and takes the outer edges c0 and d0 of the first picture as the line, and only takes the difference image of d0, c0, c1, and d1 added in the second picture for data transmission, so as to reduce the data packet transmitted by the second picture.

[0085] like Figure 2 As shown in the figure, when the reference image is G0 and the second image taken 0.04 seconds later is G1, the drone is in an ascending state and overlaps the upper right corner of the reference image G0. The four corners of the reference image G0 are set to a0, b0, c0, and d0 respectively, and the four corners of the second image G1 are set to a1, b1, c1, and d1 respectively. The overlapping part of the two images is aa1, b1, bb1, and d0. The drone uses the outer edge aa1, d0, and bb1 of the reference image G0 as a line to crop the aa1, b1, bb1, and d0 part of the second image G1, and only takes the difference image of a1, aa1, d0, bb1, c1, and d1 added in the second image G1 for data transmission, so as to reduce the data packet transmitted by the second image.

[0086] In one embodiment, the server 12 is used to determine, based on the flight trajectory of the drone 11, a compensation area corresponding to an image taken after the reference image in the previous images taken at adjacent time intervals; and splice the compensation area with the difference images corresponding to the images taken after the reference image to obtain the images taken after the reference image.

[0087] In an embodiment of the present invention, the server can determine, based on the flight trajectory of the drone, the compensation area corresponding to the image taken after the reference image in the previous images taken at adjacent time intervals; and splice the compensation area with the difference images corresponding to the images taken after the reference image to obtain the images taken after the reference image.

[0088] Exemplarily, the server performs image transmission and analysis according to the flight trajectory of the drone. When the drone is ascending or descending, just overlap the second picture a1, aa1, d0, bb1, c1, d1 with the edge aa1, d0, bb1 of the first picture. The missing part of the second picture must be cut from the first picture, and the size value of each picture is fixed. In this way, it is known that the size of the picture to be completed from the first picture is at the position of aa1, b1, bb1. The second complete picture is restored. When panning, just overlap the second picture d0, c0, c1, d1 with d0, c0 of the first picture. The missing part of the second picture must be cut from the first picture, and the size value of each picture is fixed. In this way, it is known that the size of the picture to be completed from the first picture is at the position of a1, b1. The second complete picture is restored. And so on, when all 25 pictures in one second are sent back in this way, the fourth picture will be presented with a video playback effect.

[0089] The drone of the drone image processing system of the embodiment of the present invention can take images at preset time intervals and obtain the shooting position when taking the images; determine the reference image from the captured images; for the images taken after the reference image, respectively compare the images with the previous images taken at adjacent time intervals to obtain the difference images corresponding to the images taken after the reference image; send the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the images taken after the reference image to the server, so as to reduce each image data packet transmitted back; the server can determine the flight trajectory of the drone according to the shooting position corresponding to the reference image and the shooting position corresponding to the images taken after the reference image; obtain the image taken after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the images taken after the reference image, so as to restore the image and reduce pixel distortion. The embodiment of the present invention can reduce the image data packets transmitted back by the drone while ensuring the image clarity, thereby improving the efficiency of image data transmission.

[0090] Reference Figure 3 , shows a flowchart of a method for processing an image of a drone according to an embodiment of the present invention, which is applied to a drone. The method may specifically include the following steps:

[0091] Step 201, capturing images at preset time intervals and obtaining the capturing positions when capturing the images;

[0092] Step 202, determining a reference image from the captured image;

[0093] Step 203, for an image captured after the reference image, respectively compare the image with a previous image captured at adjacent time intervals to obtain a difference image corresponding to the image captured after the reference image;

[0094] In an embodiment of the present invention, the drone can take images at preset time intervals and obtain the shooting position when the images are taken. The preset time interval can be 0.04 seconds, that is, the drone takes 25 pictures in one second. The higher the definition of the video, the more pictures the drone takes per second. The drone can determine the reference image from the captured images; for the images taken after the reference image, the images are compared with the previous images taken at adjacent time intervals to obtain the difference images corresponding to the images taken after the reference image; the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the images taken after the reference image are sent to the server, so that each returned image data packet can be reduced by only returning the difference image, so that the video presented by the interaction between the drone and the server can be faster, reduce pixel distortion, and bring a better user experience to the user.

[0095] In one embodiment, the step of comparing the image with a previous image taken at adjacent time intervals to obtain a difference image corresponding to an image taken after the reference image may further include the following sub-steps:

[0096] Sub-step S11, comparing the images shot after the reference image with the previous images shot at adjacent time intervals, to determine the overlapping area of ​​the images shot after the reference image;

[0097] Sub-step S12: cropping the image captured after the reference image according to the overlapping area to obtain a difference image corresponding to the image captured after the reference image.

[0098] In an embodiment of the present invention, the drone can compare the images taken after the reference image with the previous images taken at adjacent time intervals to determine the overlapping areas of the images taken after the reference image; based on the overlapping areas, the images taken after the reference image are cropped to obtain a difference image corresponding to the images taken after the reference image.

[0099] For example, for example, Figure 2 As shown in the figure, when the reference image is F0 and the second image taken 0.04 seconds later is F1, the drone is in a level flight state. The four corners of the reference image F0 are set to a0, b0, c0, and d0 respectively. The four corners of the second image F1 are set to a1, b1, c1, and d1 respectively. The drone system cuts the a1, b1, c0, and d0 part of the second image from the overlapping part of the two images a1, b1, c0, and d0, and takes the outer edge c0 and d0 of the first image as the line, and only takes the difference image of d0, c0, c1, and d1 added in the second image for data transmission.

[0100] When the reference image is G0 and the second image taken 0.04 seconds later is G1, the drone is in an ascending state and overlaps the upper right corner of the reference image G0. The four corners of the reference image G0 are set to a0, b0, c0, and d0 respectively, and the four corners of the second image G1 are set to a1, b1, c1, and d1 respectively. The overlapping part of the two images is aa1, b1, bb1, and d0. The drone uses the outer edge aa1, d0, and bb1 of the reference image G0 as a line to crop the aa1, b1, bb1, and d0 part of the second image G1, and only takes the difference image of a1, aa1, d0, bb1, c1, and d1 added in the second image G1 for data transmission, so as to reduce the data packet transmitted by the second image.

[0101] Step 204, sending the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the image shot after the reference image to the server, so that the server determines the flight trajectory of the UAV according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image, and obtains the image shot after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the image shot after the reference image.

[0102] In one embodiment, the shooting position when shooting the image is the position coordinate of the shot image in a spatial rectangular coordinate system; the step of sending the reference image, the shooting position corresponding to the reference image, and the difference image and the shooting position corresponding to the image shot after the reference image to the server so that the server determines the flight trajectory of the drone according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image, may also include the following sub-steps:

[0103] Sub-step S21, sending the position coordinates corresponding to the reference image and the position coordinates corresponding to the image taken after the reference image to the server, so that the server performs a difference operation on the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals to obtain the flight trajectory of the drone.

[0104] In an embodiment of the present invention, the shooting position when shooting an image may be the position coordinates of the shooting image in a spatial rectangular coordinate system. The drone may obtain the position coordinates when shooting an image; send the position coordinates corresponding to the reference image and the position coordinates corresponding to the image shot after the reference image to the server, so that the server performs a difference operation between the position coordinates corresponding to each image shot after the reference image and the position coordinates of the previous image shot at adjacent time intervals, and obtain the flight trajectory of the drone.

[0105] For example, Figure 2 As shown, the gyroscope records the position coordinates of the reference image F0 as X0, Y0, and Z0, and the position coordinates of the second image F1 as X1, Y1, and Z1. By performing a difference operation between the position coordinates of the second image and the position coordinates of the reference image, the distance traveled by the drone can be obtained, thereby knowing the flight trajectory of the drone and the direction in which the second image overlaps with the reference image.

[0106] In one embodiment, the server determines the compensation area corresponding to the image taken after the reference image in the previous images taken at adjacent time intervals according to the flight trajectory of the drone, and splices the compensation area with the difference images corresponding to the images taken after the reference image.

[0107] In an embodiment of the present invention, the server can perform image transmission and analysis according to the flight trajectory of the drone. When the drone is ascending or descending, just overlap the second picture a1, aa1, d0, bb1, c1, d1 with the edge aa1, d0, bb1 of the first picture. The missing part of the second picture must be cut from the first picture, and the size value of each picture is fixed. In this way, it is known that the size of the picture to be completed from the first picture is at the position of aa1, b1, bb1. The second complete picture is restored. When panning, just overlap the second picture d0, c0, c1, d1 with d0, c0 of the first picture. The missing part of the second picture must be cut from the first picture, and the size value of each picture is fixed. In this way, it is known that the size of the picture to be completed from the first picture is at the position of a1, b1. The second complete picture is restored. And so on, when all 25 pictures in one second are sent back in this way, the fourth picture will be presented with a video playback effect.

[0108] The drone of the embodiment of the present invention can take images at preset time intervals and obtain the shooting position when taking the images; determine the reference image from the captured images; for the images taken after the reference image, respectively compare the images with the previous images taken at adjacent time intervals to obtain the difference images corresponding to the images taken after the reference image; send the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the images taken after the reference image to the server, so that the server can determine the flight trajectory of the drone according to the shooting position corresponding to the reference image and the shooting position corresponding to the images taken after the reference image; obtain the images taken after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the images taken after the reference image, so that the images can be restored and pixel distortion can be reduced. The embodiment of the present invention can reduce the image data packets returned by the drone while ensuring the image clarity, thereby improving the efficiency of image data transmission.

[0109] Reference Figure 4 , shows a flowchart of another method for processing drone images according to an embodiment of the present invention, which is applied to a server. The method may specifically include the following steps:

[0110] Step 301, receiving a reference image sent by a drone, a shooting position corresponding to the reference image, and a difference image and shooting position corresponding to an image shot after the reference image;

[0111] In one embodiment, a difference image corresponding to an image taken after the reference image is obtained by the drone comparing the image taken after the reference image with a previous image taken at adjacent time intervals, determining an overlapping area of ​​the image taken after the reference image, and cropping the image taken after the reference image based on the overlapping area.

[0112] In an embodiment of the present invention, a drone can take images at a preset time interval and obtain the shooting position when taking the images. The preset time interval can be 0.04 seconds, that is, the drone takes 25 pictures in one second. The higher the definition of the video, the more pictures the drone takes per second. The drone can determine the reference image from the captured images; for the images taken after the reference image, the images are compared with the previous images taken at adjacent time intervals to obtain the difference images corresponding to the images taken after the reference image; the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the images taken after the reference image are sent to the server, so that each returned image data packet can be reduced by only returning the difference image, so that the video presented by the interaction between the drone and the server can be faster, reduce pixel distortion, and bring a better user experience to the user.

[0113] Step 302, determining the flight trajectory of the UAV according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image;

[0114] In one embodiment, the shooting position when shooting the image is the position coordinate of the shot image in a spatial rectangular coordinate system; the step of determining the flight trajectory of the drone according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image may further include the following sub-steps:

[0115] Sub-step S31, receiving the position coordinates corresponding to the reference image and the position coordinates corresponding to the image taken after the reference image sent by the drone;

[0116] Sub-step S32, performing a difference operation between the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals to obtain the flight trajectory of the UAV.

[0117] In an embodiment of the present invention, the shooting position when shooting an image may be the position coordinates of the shooting image in a spatial rectangular coordinate system. The drone may obtain the position coordinates when shooting an image; send the position coordinates corresponding to the reference image and the position coordinates corresponding to the image shot after the reference image to the server, so that the server performs a difference operation between the position coordinates corresponding to each image shot after the reference image and the position coordinates of the previous image shot at adjacent time intervals, and obtain the flight trajectory of the drone.

[0118] For example, Figure 2 As shown, the gyroscope records the position coordinates of the reference image F0 as X0, Y0, and Z0, and the position coordinates of the second image F1 as X1, Y1, and Z1. By performing a difference operation between the position coordinates of the second image and the position coordinates of the reference image, the distance traveled by the drone can be obtained, thereby knowing the flight trajectory of the drone and the direction in which the second image overlaps with the reference image.

[0119] Step 303: Obtain an image taken after the reference image based on the flight trajectory, the reference image, and a difference image corresponding to an image taken after the reference image.

[0120] In one embodiment, the step of obtaining the image taken after the reference image according to the flight trajectory, the reference image, and the difference image corresponding to the image taken after the reference image may further include the following sub-steps:

[0121] Sub-step S41, determining, according to the flight trajectory of the drone, in the previous images taken at adjacent time intervals, a compensation area corresponding to the image taken after the reference image;

[0122] Sub-step S42, splicing the compensation area with the difference images corresponding to the images taken after the reference image, to obtain the images taken after the reference image.

[0123] In an embodiment of the present invention, the server can perform image transmission and analysis according to the flight trajectory of the drone. When the drone is ascending or descending, just overlap the second picture a1, aa1, d0, bb1, c1, d1 with the edge aa1, d0, bb1 of the first picture. The missing part of the second picture must be cut from the first picture, and the size value of each picture is fixed. In this way, it is known that the size of the picture to be completed from the first picture is at the position of aa1, b1, bb1. The second complete picture is restored. When panning, just overlap the second picture d0, c0, c1, d1 with d0, c0 of the first picture. The missing part of the second picture must be cut from the first picture, and the size value of each picture is fixed. In this way, it is known that the size of the picture to be completed from the first picture is at the position of a1, b1. The second complete picture is restored. And so on, when all 25 pictures in one second are sent back in this way, the fourth picture will be presented with a video playback effect.

[0124] The server of the embodiment of the present invention can receive the reference image sent by the drone, the shooting position corresponding to the reference image, the difference image and shooting position corresponding to the image shot after the reference image; determine the flight trajectory of the drone according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image; obtain the image shot after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the image shot after the reference image, so as to restore the image and reduce pixel distortion. The embodiment of the present invention can reduce the image data packet sent back by the drone while ensuring the image clarity, thereby improving the efficiency of image data transmission.

[0125] For the method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0126] Reference Figure 5 , shows a structural block diagram of a drone image processing device provided by an embodiment of the present invention, which is applied to a drone and may specifically include the following modules:

[0127] The captured image acquisition module 401 is used to capture images at preset time intervals and obtain the capture position when the images are captured;

[0128] A reference image determination module 402, used to determine a reference image from the captured image;

[0129] The difference image determination module 403 is used to compare the image taken after the reference image with the previous image taken at adjacent time intervals to obtain a difference image corresponding to the image taken after the reference image;

[0130] The reference image sending module 404 is used to send the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the image shot after the reference image to the server, so that the server can determine the flight trajectory of the UAV according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image, and obtain the image shot after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the image shot after the reference image.

[0131] In the embodiment of the present invention, the shooting position when shooting the image is the position coordinate of the shot image in the spatial rectangular coordinate system; the reference image sending module 404 includes:

[0132] The reference image sending submodule is used to send the position coordinates corresponding to the reference image and the position coordinates corresponding to the image taken after the reference image to the server, so that the server performs a difference operation on the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals to obtain the flight trajectory of the UAV.

[0133] In the embodiment of the present invention, the difference image determination module 403 includes:

[0134] An overlapping region determination submodule, used to compare the image captured after the reference image with the previous image captured at adjacent time intervals, respectively, to determine the overlapping region of the image captured after the reference image;

[0135] The difference image determination submodule is used to crop the image shot after the reference image according to the overlapping area to obtain a difference image corresponding to the image shot after the reference image.

[0136] In an embodiment of the present invention, the image taken after the reference image is determined by the server according to the flight trajectory of the drone, in the previous images taken at adjacent time intervals, to obtain a compensation area corresponding to the image taken after the reference image, and the compensation area is spliced ​​with the difference image corresponding to the image taken after the reference image.

[0137] The drone of the embodiment of the invention can take images at preset time intervals and obtain the shooting position when taking the images; determine the reference image from the captured images; for the images taken after the reference image, respectively compare the images with the previous images taken at adjacent time intervals to obtain the difference images corresponding to the images taken after the reference image; send the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the images taken after the reference image to the server, so that the server can determine the flight trajectory of the drone according to the shooting position corresponding to the reference image and the shooting position corresponding to the images taken after the reference image; obtain the images taken after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the images taken after the reference image, so that the images can be restored and pixel distortion can be reduced. The embodiment of the present invention can reduce the image data packets returned by the drone while ensuring the image clarity, thereby improving the efficiency of image data transmission.

[0138] Reference Figure 6 , shows a structural block diagram of a drone image processing device provided by an embodiment of the present invention, which is applied to a server and may specifically include the following modules:

[0139] The reference image receiving module 501 is used to receive a reference image sent by a drone, a shooting position corresponding to the reference image, and a difference image and shooting position corresponding to an image shot after the reference image;

[0140] A flight trajectory determination module 502, configured to determine the flight trajectory of the UAV according to a shooting position corresponding to the reference image and a shooting position corresponding to an image shot after the reference image;

[0141] The captured image restoration module 503 is used to obtain the image captured after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the image captured after the reference image.

[0142] In the embodiment of the present invention, the shooting position when shooting the image is the position coordinate of the shot image in the spatial rectangular coordinate system; the flight trajectory determination module 502 includes:

[0143] A position coordinate receiving submodule, used to receive the position coordinates corresponding to the reference image and the position coordinates corresponding to the image taken after the reference image sent by the drone;

[0144] The flight trajectory determination submodule is used to perform a difference operation between the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals to obtain the flight trajectory of the UAV.

[0145] In an embodiment of the present invention, the difference image corresponding to the image taken after the reference image is obtained by comparing the image taken after the reference image with the previous image taken at adjacent time intervals by the drone, determining the overlapping area of ​​the image taken after the reference image, and cropping the image taken after the reference image according to the overlapping area.

[0146] In the embodiment of the present invention, the captured image restoration module 503 includes:

[0147] A compensation area determination submodule, used to determine, according to the flight trajectory of the UAV, in the previous images taken at adjacent time intervals, the compensation area corresponding to the image taken after the reference image;

[0148] The captured image restoration submodule is used to stitch the compensation area with the difference images corresponding to the images captured after the reference image to obtain the images captured after the reference image.

[0149] The server of the embodiment of the present invention can receive the reference image sent by the drone, the shooting position corresponding to the reference image, the difference image and shooting position corresponding to the image shot after the reference image; determine the flight trajectory of the drone according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image; obtain the image shot after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the image shot after the reference image, so as to restore the image and reduce pixel distortion. The embodiment of the present invention can reduce the image data packet sent back by the drone while ensuring the image clarity, thereby improving the efficiency of image data transmission.

[0150] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0151] An embodiment of the present invention 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 implements the steps of the above-mentioned drone image processing method when executing the computer program.

[0152] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned drone image processing method are implemented.

[0153] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0154] Those skilled in the art will appreciate that the embodiments of the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more machine-readable media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0155] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0156] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0157] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0158] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0159] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal 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 terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0160] The above is a detailed introduction to the drone image processing system, method, device, equipment and medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A drone image processing system, characterized in that: include: drones and servers; The drone is used to take images at preset time intervals and obtain the shooting positions when the images are taken; Determine a reference image from the captured images; compare the images captured after the reference image with previous images captured at adjacent time intervals to obtain a difference image corresponding to the images captured after the reference image; send the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the images captured after the reference image to the server, so that the server determines the flight trajectory of the UAV according to the shooting position corresponding to the reference image and the shooting position corresponding to the images captured after the reference image; obtain the images captured after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the images captured after the reference image; The server is used to receive the reference image, the shooting position corresponding to the reference image, and the difference image and shooting position corresponding to the image shot after the reference image, which are sent by the drone; determine the flight trajectory of the drone according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image, and obtain the image shot after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the image shot after the reference image.

2. The system according to claim 1, characterized in that The shooting position when shooting the image is the position coordinates of the shot image in a spatial rectangular coordinate system; The drone is used to obtain the position coordinates when taking an image; send the position coordinates corresponding to the reference image and the position coordinates corresponding to the image taken after the reference image to the server, so that the server performs a difference operation between the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals to obtain the flight trajectory of the drone; The server is used to receive the position coordinates corresponding to the reference image sent by the drone and the position coordinates corresponding to the image taken after the reference image; perform difference calculation on the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals to obtain the flight trajectory of the drone.

3. The system according to claim 1, characterized in that The drone is used to compare the images taken after the reference image with the previous images taken at adjacent time intervals, respectively, to determine the overlapping area of ​​the images taken after the reference image; and to crop the images taken after the reference image according to the overlapping area to obtain a difference image corresponding to the images taken after the reference image.

4. The system according to claim 1, characterized in that The server is used to determine, according to the flight trajectory of the drone, in the previous images taken at adjacent time intervals, a compensation area corresponding to the image taken after the reference image; and splice the compensation area with the difference images corresponding to the images taken after the reference image to obtain the images taken after the reference image.

5. A method for processing drone images, characterized in that: Applied to a drone, the method comprises: Taking images at a preset time interval and obtaining the shooting position when the images are taken; Determine a reference image from the captured images; For an image taken after the reference image, respectively compare the image with a previous image taken at adjacent time intervals to obtain a difference image corresponding to the image taken after the reference image; The reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the image shot after the reference image are sent to the server, so that the server determines the flight trajectory of the UAV according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image, and obtains the image shot after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the image shot after the reference image.

6. The method according to claim 5, characterized in that The shooting position when shooting the image is the position coordinate of the shot image in the spatial rectangular coordinate system; the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the image shot after the reference image are sent to the server, so that the server determines the flight trajectory of the drone according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image, including: The position coordinates corresponding to the reference image and the position coordinates corresponding to the image taken after the reference image are sent to the server, so that the server performs a difference operation on the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals to obtain the flight trajectory of the drone.

7. The method according to claim 5, characterized in that The step of comparing the image with a previous image taken at adjacent time intervals to obtain a difference image corresponding to an image taken after the reference image comprises: Comparing the images captured after the reference image with the previous images captured at adjacent time intervals respectively, to determine the overlapping areas of the images captured after the reference image; The image captured after the reference image is cropped according to the overlapping area to obtain a difference image corresponding to the image captured after the reference image.

8. The method according to claim 5, characterized in that The image taken after the reference image is determined by the server according to the flight trajectory of the drone, in the previous images taken at adjacent time intervals, to correspond to the image taken after the reference image, and the compensation area is spliced ​​with the difference image corresponding to the image taken after the reference image.

9. A method for processing drone images, characterized in that: Applied to a server, the method comprises: Receive a reference image sent by a drone, a shooting position corresponding to the reference image, and a difference image and shooting position corresponding to an image shot after the reference image; Determining a flight trajectory of the UAV according to a shooting position corresponding to the reference image and a shooting position corresponding to an image shot after the reference image; The image shot after the reference image is obtained according to the flight trajectory, the reference image and the difference image corresponding to the image shot after the reference image.

10. The method according to claim 9, characterized in that The shooting position when shooting the image is the position coordinate of the shot image in a spatial rectangular coordinate system; the determining the flight trajectory of the UAV according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image includes: Receiving the position coordinates corresponding to the reference image and the position coordinates corresponding to the image taken after the reference image sent by the drone; The flight trajectory of the UAV is obtained by performing a difference operation on the position coordinates corresponding to each image taken after the reference image and the position coordinates of the previous image taken at adjacent time intervals.

11. The method according to claim 9, characterized in that The difference image corresponding to the image taken after the reference image is obtained by comparing the image taken after the reference image with the previous image taken at adjacent time intervals by the drone, determining the overlapping area of ​​the image taken after the reference image, and cropping the image taken after the reference image according to the overlapping area.

12. The method according to claim 9, characterized in that The step of obtaining the image shot after the reference image according to the flight trajectory, the reference image, and a difference image corresponding to an image shot after the reference image comprises: According to the flight trajectory of the UAV, determining, in the previous images taken at adjacent time intervals, compensation areas corresponding to the images taken after the reference image; The compensation area is respectively spliced ​​with the difference image corresponding to the image shot after the reference image to obtain the image shot after the reference image.

13. A drone image processing device, characterized in that: Applied to a drone, the device comprises: A shooting image acquisition module is used to shoot images at preset time intervals and obtain the shooting position when the images are shot; A reference image determination module, used to determine a reference image from the captured image; a difference image determination module, for comparing an image taken after the reference image with a previous image taken at adjacent time intervals, to obtain a difference image corresponding to the image taken after the reference image; The reference image sending module is used to send the reference image, the shooting position corresponding to the reference image, the difference image and the shooting position corresponding to the image shot after the reference image to the server, so that the server can determine the flight trajectory of the UAV according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image, and obtain the image shot after the reference image according to the flight trajectory, the reference image and the difference image corresponding to the image shot after the reference image.

14. A drone image processing device, characterized in that: Applied to a server, the device comprises: A reference image receiving module, used to receive a reference image sent by a drone, a shooting position corresponding to the reference image, and a difference image and shooting position corresponding to an image shot after the reference image; A flight trajectory determination module, used to determine the flight trajectory of the UAV according to the shooting position corresponding to the reference image and the shooting position corresponding to the image shot after the reference image; The captured image restoration module is used to obtain the image captured after the reference image based on the flight trajectory, the reference image and the difference image corresponding to the image captured after the reference image.

15. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of a drone image processing method as described in any one of claims 1 to 4 or claims 5 to 8 are implemented.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of a drone image processing method as described in any one of claims 1-4 or claims 5-8 are implemented.

Images