Image processing method for dynamic sampling of unmanned aerial vehicle

By calculating and averagely correcting the amplitude ratio of the continuous frame data during switching operations during the image acquisition of the drone, the blur problem caused by image jitter is solved, and the accuracy and stability of image processing are improved.

CN118918502AInactive Publication Date: 2024-11-08ZHEJIANG DEFANG DATA TECHNOLOGY CO LTD
View PDF 14 Cites 0 Cited by

Patent Information

Application Number
CN202411380060.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-30
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

During the drone survey, as the image moves vertically or left and right, the image is prone to jitter at the moment of switching, resulting in the highly blurred image collected, which makes it difficult for the prior art to effectively solve this problem.

Method used

By obtaining image data of continuous frames in the same period of switching operations, a problem frame collection is formed, amplitude ratio calculation and average correction are performed using the comparison of the front and rear frames, and the processing is frame-by-frame to reduce the impact of blur.

Benefits of technology

It improves the accuracy and robustness of image correction, dynamically adapts to image changes, processes complex scenes, reduces errors caused by single-frame differences, and has stronger stability and reliability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118918502A_ABST
    Figure CN118918502A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of image processing, and particularly discloses an image processing method for dynamic sampling of an unmanned aerial vehicle, which comprises the following steps: S01, acquiring image data a of continuous frames in a switching action execution time period to form a problem frame set A; s02, taking the problem frame set A as a window, and obtaining image data a of a frame before and after the window as a first comparison frame B1 and a second comparison frame B2; s03, comparing each frame in the problem frame set A with a first comparison frame B1 and a second comparison frame B2 to obtain a first amplitude ratio and a second amplitude ratio; and S04, averaging the obtained first amplitude ratio and the second amplitude ratio, and correcting the image data a in the problem frame set A. By comparing the problem frame set A with the front and back frames, the change in the image can be detected and corrected more accurately, so that the image correction precision is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to an image processing method for dynamic sampling of unmanned aerial vehicles. Background Art

[0002] In the process of municipal road planning and construction, drones are widely used in survey work. Compared with satellite cloud images, drones can provide real-time image data. Since the images taken by drones during flight may be blurred due to the flight speed, the system will use internal algorithms to repair the image data frame by frame. This process can effectively restore the clear image of each frame, thereby ensuring the accuracy and reliability of the survey data.

[0003] Publication (announcement) number: CN114500848A, publication (announcement) date: 2022-05-13, a drone image acquisition method is disclosed, comprising the following steps: S1, receiving a data acquisition instruction, obtaining a shooting route, a target shooting object and saving the characteristics of the target shooting object; S2, receiving a data acquisition instruction for an object to be collected sent by the background, and obtaining the position of the object to be collected according to the data acquisition instruction, and following the shooting through the shooting route according to the position of the object to be collected; S3, through an auxiliary shooting device installed on the drone, the light intensity of the area corresponding to the position of the object to be collected can be obtained; the present invention senses the flight attitude of the drone through an attitude sensor, so that the attitude of the drone can be adjusted at any time according to needs, and image acquisition can be performed at multiple positions according to needs, and the attitude of the drone can be adjusted in time during acquisition through the attitude sensor to avoid unstable shaking of the drone affecting the clarity of image acquisition.

[0004] In the prior art including the above patents, as the drone moves vertically up or down, or moves left or right, the images often shake at the moment of switching, resulting in highly blurred images. This blur phenomenon is different from the blur of images taken when the drone accelerates forward in a single direction. How to effectively solve this problem is expected to be well solved! Summary of the invention

[0005] The purpose of the present invention is to provide an image processing method for dynamic sampling of unmanned aerial vehicles to solve the above problems.

[0006] In order to achieve the above object, the present invention provides the following technical solution: an image processing method for dynamic sampling of unmanned aerial vehicles, comprising:

[0007] S01, obtaining image data a of continuous frames during the period when the switching action is executed, and forming a problem frame collection A;

[0008] S02, taking the problem frame collection A as a window, obtaining image data a of one frame before and after the window as the first comparison frame B 1 and the second comparison frame B 2 ;

[0009] S03, compare each frame in the problem frame collection A with the first comparison frame B 1 and the second comparison frame B 2 Performing comparison to obtain a first amplitude ratio and a second amplitude ratio;

[0010] S04. Take an average value of the first amplitude ratio and the second amplitude ratio, and correct the image data a in the problem frame collection A.

[0011] Preferably, in step S01, arranging the acquired image data a of the continuous frames into a problem frame collection A comprises:

[0012] S11, reading the terminal fuzzy area of ​​the image data a, and selecting the fuzzy area;

[0013] S12, extracting pixels from the fuzzy area selected by the frame, and generating a grid in the area according to the extraction rule, so that the extracted pixel units have coordinates;

[0014] S13, performing tone change mapping according to the continuous pixel units of the longitudinal coordinate axis and the transverse coordinate axis of the grid to determine the first tone value and the first luminosity value of the continuous coordinate pixels;

[0015] S14, binding the extracted pixels and the corresponding first hue values, first luminosity values ​​and coordinates with the frame image data a, and processing frame by frame to form a set.

[0016] Preferably, the first comparison frame B in step S02 1 and the second comparison frame B 2 The processing includes:

[0017] S21, based on the determined time period of the problem frame collection A, set an extraction time period to obtain two sets of image data a sufficient for identifying image content;

[0018] S22, perform image content extraction respectively, and extract the features x 1 ...x n , forming B 1 (x 1 ...x n ) and B 2 (x 1 ...x n );

[0019] S23, determining a grid for x according to the extraction rule in step S01, thereby forming a comparison pixel unit with coordinates;

[0020] S24, performing tone change mapping according to the continuous contrast pixel units of the vertical coordinate axis and the horizontal coordinate axis of the grid, and generating a second tone value and a second luminosity value respectively.

[0021] Preferably, in step S02, the first comparison frame B 1 and the second comparison frame B 2 The processing also includes:

[0022] S25, x 1 ...x n The intensity values ​​of the corresponding contrast pixel units are sorted and collected;

[0023] S26, B 1 and B 2 The second hue value and the second luminosity value corresponding to x are processed respectively:

[0024] Tone value processing:

[0025] S261, Extract B 1 and B 2 The hue channel is obtained by hue 1 and hue 2, where:

[0026] The hue range is from 0 to 360 degrees, 0 degrees represents red, 120 degrees represents green, and 240 degrees represents blue;

[0027] S262. Calculate the absolute value difference between two hue values: |hue1−hue2|

[0028] S263, calculating the cycle difference between two hue values: hue range - absolute difference, cycle difference = 180 - absolute difference, to obtain hue difference = min (absolute difference, cycle difference);

[0029] Photometric value processing:

[0030] S264, by weighted average method B 1 and B 2 The RGB color channels are calculated to obtain B 1 and B 2 Luminosity:

[0031] L (B1) =k×R+k×G+k×B;

[0032] L (B2)= k×R+k×G+k×B;

[0033] Where: R is the value of the red channel, G is the value of the green channel, B is the value of the blue channel, and k is the coefficient (0.299 for the red channel, 0.587 for the green channel, and 0.114 for the blue channel).

[0034] Preferably, obtaining the first amplitude ratio and the second amplitude ratio in step S03 includes:

[0035] S31, extracting the features B of each frame of image data aa in the corresponding problem frame collection A 1 and B 2 Middle image features;

[0036] S32, then the first hue value and the first luminosity value of a and B 1 and B 2 Subtract the first hue value and the first luminance value of the image data a from each image data a in the problem frame collection A, thereby obtaining a hue value difference and a luminance value difference of each image data a in the problem frame collection A;

[0037] S33, subtract the tone value differences of two adjacent image data a, and take the average value after continuous subtraction to obtain a first amplitude ratio;

[0038] S34, subtract the luminance value differences of two adjacent image data a, take the average value after continuous subtraction, and obtain the second amplitude ratio.

[0039] Preferably, the correction of the image data a in the problem frame collection A in step S04 includes:

[0040] S41. Linear adjustment of luminosity or chromaticity values:

[0041] ;

[0042] Among them, Y is the luminance value, Cb is the blue differential chromaticity component, Cr is the red differential chromaticity component, a is the second amplitude ratio, c is the middle red channel value of the first amplitude ratio, e is the middle blue channel value of the first amplitude ratio, and d is the image data a and B 1 and B 2 The average value of the difference between the red channel values, b is the image data a and B 1 and B 2 The average value of the difference in luminosity values, f is the image data a and B 1 and B 2 The average of the differences in the blue channel values;

[0043] S42, applying a correction transformation function to each pixel of the image.

[0044] In the above technical solution, the present invention provides an image processing method for dynamic sampling of unmanned aerial vehicles, which has the following beneficial effects:

[0045] 1. By comparing the problem frame set A with the previous and next frames, the changes in the image can be detected and corrected more accurately, thereby improving the accuracy of image correction;

[0046] 2. Using the image data of the previous and next frames as the comparison benchmark can better understand the context of the problem frame and reduce the error caused by the difference of a single frame;

[0047] 3. Correct the image by calculating the average value of the amplitude ratio, which can dynamically adapt to image changes and handle more complex scenes;

[0048] 4. The comparison method does not rely on the data of a single frame. By comprehensively analyzing multiple frames, it improves the robustness to changes in image quality;

[0049] 5. The continuous frame data in the problem frame collection A can better capture the trend of movement or change, making the correction result more stable and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0051] Figure 1 A schematic structural diagram of a pipe clamp provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] like Figure 1 As shown, an image processing method for dynamic sampling of a drone includes:

[0054] S01, obtaining image data a of continuous frames during the switching action execution period, forming a problem frame collection A, including:

[0055] S11, reading the terminal fuzzy area of ​​the image data a, and selecting the fuzzy area;

[0056] S12, extracting pixels from the framed fuzzy area, and generating a grid in the area according to the extraction rule, so that the extracted pixel units have coordinates;

[0057] S13, performing tone change mapping according to the continuous pixel units of the longitudinal coordinate axis and the transverse coordinate axis of the grid to determine the first tone value and the first luminosity value of the continuous coordinate pixels;

[0058] S14, binding the extracted pixels and the corresponding first hue values, first luminosity values ​​and coordinates with the frame image data a, and processing frame by frame to form a set.

[0059] S02, using the problem frame collection A as a window, obtaining image data a of one frame before and after the window as the first comparison frame B 1 and the second comparison frame B 2 ,include:

[0060] S21, based on the determined time period of the problem frame collection A, set an extraction time period to obtain two sets of image data a sufficient for identifying image content;

[0061] S22, perform image content extraction respectively, and extract the features x 1 ...x n , forming B 1 (x 1 ...x n ) and B 2 (x 1 ...x n );

[0062] S23, determining a grid for x according to the extraction rule in step S01, thereby forming a comparison pixel unit with coordinates;

[0063] S24, performing tone change mapping according to the continuous contrast pixel units of the longitudinal coordinate axis and the transverse coordinate axis of the grid, and generating a second tone value and a second luminosity value respectively;

[0064] S25, x 1 ...x n The intensity values ​​of the corresponding contrast pixel units are sorted and collected;

[0065] S26, B 1 and B 2 The second hue value and the second luminosity value corresponding to x are processed respectively:

[0066] Tone value processing:

[0067] S261, Extract B 1 and B 2 The hue channel is obtained by hue 1 and hue 2, where:

[0068] The hue range is from 0 to 360 degrees, 0 degrees represents red, 120 degrees represents green, and 240 degrees represents blue;

[0069] S262. Calculate the absolute value difference between two hue values: |hue1−hue2|

[0070] S263, calculating the cycle difference between two hue values: hue range - absolute difference, cycle difference = 180 - absolute difference, to obtain hue difference = min (absolute difference, cycle difference);

[0071] Photometric value processing:

[0072] S264, by weighted average method B 1 and B 2 The RGB color channels are calculated to obtain B 1 and B 2 Luminosity:

[0073] L (B1) =k×R+k×G+k×B;

[0074] L (B2)= k×R+k×G+k×B;

[0075] Where: R is the value of the red channel, G is the value of the green channel, B is the value of the blue channel, and k is the coefficient (0.299 for the red channel, 0.587 for the green channel, and 0.114 for the blue channel).

[0076] S03, compare each time in the problem frame collection A with the first comparison frame B 1 and the second comparison frame B 2 Comparing to obtain a first amplitude ratio and a second amplitude ratio includes:

[0077] S41, extracting the feature B of each frame image data aa in the corresponding problem frame collection A 1 and B 2 Middle image features;

[0078] S42, then the first hue value and the first luminosity value of a and B 1 and B 2 Subtract the first hue value and the first luminance value of the image data a from each image data a in the problem frame collection A, thereby obtaining a hue value difference and a luminance value difference of each image data a in the problem frame collection A;

[0079] S43, subtracting the difference between the tone values ​​of two adjacent image data a, taking the average value after continuous subtraction, and obtaining a first amplitude ratio;

[0080] S44, subtract the luminance value differences of two adjacent image data a, take the average value after continuous subtraction, and obtain the second amplitude ratio.

[0081] S04, taking an average value of the first amplitude ratio and the second amplitude ratio, and correcting the image data a in the problem frame collection A, including:

[0082] S41. Linear adjustment of luminosity or chromaticity values:

[0083] ;

[0084] Among them, Y is the luminance value, Cb is the blue differential chromaticity component, Cr is the red differential chromaticity component, a is the second amplitude ratio, c is the middle red channel value of the first amplitude ratio, e is the middle blue channel value of the first amplitude ratio, and d is the image data a and B 1 and B 2 The average value of the difference between the red channel values, b is the image data a and B 1 and B 2 The average value of the difference in luminosity values, f is the image data a and B 1 and B 2 The average of the differences in the blue channel values;

[0085] S42, applying a correction transformation function to each pixel of the image.

[0086] It should be noted that obtaining the first hue value and the first luminosity value includes:

[0087] Tone value processing:

[0088] Extract the hue channel of image data a and get hue 3.

[0089] Photometric value processing:

[0090] The RGB color channels of image data a are calculated by weighted averaging, and B is obtained respectively. 1 and B 2 Luminosity:

[0091] L = k × R + k × G + k × B;

[0092] Where: R is the value of the red channel, G is the value of the green channel, B is the value of the blue channel, and k is the coefficient (0.299 for the red channel, 0.587 for the green channel, and 0.114 for the blue channel).

[0093] In summary, by comparing the problem frame collection A with the previous and next frames, changes in the image can be detected and corrected more accurately, thereby improving the accuracy of image correction; and by using the image data of the previous and next frames as the comparison benchmark, the context of the problem frame can be better understood, reducing errors caused by single frame differences; secondly, by calculating the average value of the amplitude ratio to correct the image, it is possible to dynamically adapt to image changes and handle more complex scenes; furthermore, the comparison method does not rely on the data of a single frame, and through the comprehensive analysis of multiple frames, the robustness to changes in image quality is improved; in addition, the continuous frame data in the problem frame collection A can better capture the trend of movement or change, making the correction result more stable and reliable.

[0094] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0095] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to 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 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 device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing 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.

[0096] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture 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.

[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing 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.

[0098] The present invention uses specific embodiments 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 methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

[0099] The embodiments of the present application also provide a specific implementation of an electronic device capable of implementing all the steps of the method in the above embodiments, and the electronic device specifically includes the following contents:

[0100] Processor, memory, communications interface and bus;

[0101] Wherein, the processor, memory, and communication interface communicate with each other via the bus;

[0102] The processor is used to call the computer program in the memory, and when the processor executes the computer program, all the steps in the method in the above embodiment are implemented.

[0103] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the method in the above embodiments, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps of the method in the above embodiments are implemented.

[0104] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program 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. Although the embodiment of this specification provides the method operation steps as described in the embodiment or flowchart, more or fewer operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiment is only one way of executing the order of many steps, and does not represent the only execution order. When the device or terminal product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, product or device. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. For the convenience of description, the above device is described by dividing it into various modules according to its functions. Of course, when implementing the embodiments of this specification, the functions of each module can be implemented in the same or more software and / or hardware, or the module implementing the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process 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.

[0105] Those skilled in the art should understand that the embodiments of this specification can be provided as methods, systems or computer program products. Therefore, the embodiments of this specification can be in the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the embodiments of this specification can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system 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. In the description of this specification, the description of the reference term "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of this specification.

[0106] In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradicting each other. The above is only an embodiment of the embodiment of this specification and is not intended to limit the embodiment of this specification. For those skilled in the art, the embodiment of this specification may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiment of this specification shall be included in the scope of the claims of the embodiment of this specification.

Claims

1. An image processing method for dynamic sampling of unmanned aerial vehicles, characterized in that: include: S01, obtaining image data a of continuous frames during the period when the switching action is executed, and forming a problem frame collection A; S02, taking the problem frame collection A as a window, obtaining image data a of one frame before and after the window as the first comparison frame B 1 and the second comparison frame B 2 ; S03, compare each frame in the problem frame collection A with the first comparison frame B 1 and the second comparison frame B 2 Performing comparison to obtain a first amplitude ratio and a second amplitude ratio; S04. Take an average value of the first amplitude ratio and the second amplitude ratio, and correct the image data a in the problem frame collection A.

2. The image processing method for dynamic sampling of unmanned aerial vehicles according to claim 1 is characterized in that: In step S01, the image data a of the acquired continuous frames are sorted into a problem frame collection A, which includes: S11, reading the terminal fuzzy area of ​​the image data a, and selecting the fuzzy area; S12, extracting pixels from the fuzzy area selected by the frame, and generating a grid in the area according to the extraction rule, so that the extracted pixel units have coordinates; S13, performing tone change mapping according to the continuous pixel units of the longitudinal coordinate axis and the transverse coordinate axis of the grid to determine the first tone value and the first luminosity value of the continuous coordinate pixels; S14, binding the extracted pixels and the corresponding first hue values, first luminosity values ​​and coordinates with the frame image data a, and processing frame by frame to form a set.

3. The image processing method for dynamic sampling of unmanned aerial vehicles according to claim 1 is characterized in that: In step S02, the first comparison frame B 1 and the second comparison frame B 2 The processing includes: S21, based on the determined time period of the problem frame collection A, set an extraction time period to obtain two sets of image data a sufficient for identifying image content; S22, perform image content extraction respectively, and extract the features x 1 ...x n , forming B 1 (x 1 ...x n ) and B 2 (x 1 ...x n ); S23, determining a grid for x according to the extraction rule in step S01, thereby forming a comparison pixel unit with coordinates; S24, performing tone change mapping according to the continuous contrast pixel units of the vertical coordinate axis and the horizontal coordinate axis of the grid, and generating a second tone value and a second luminosity value respectively.

4. The image processing method for dynamic sampling of unmanned aerial vehicles according to claim 3 is characterized in that: In step S02, the first comparison frame B 1 and the second comparison frame B 2 The processing also includes: S25, x 1 ...x n The intensity values ​​of the corresponding contrast pixel units are sorted and collected; S26, B 1 and B 2 The second hue value and the second luminosity value corresponding to x are processed respectively: Tone value processing: S261, Extract B 1 and B 2 The hue channel is obtained by hue 1 and hue 2, where: The hue range is from 0 to 360 degrees, with 0 degrees representing red, 120 degrees representing green, and 240 degrees representing blue; S262. Calculate the absolute difference between two hue values: |hue1−hue2| S263, calculating the cycle difference between two hue values: hue range - absolute difference, cycle difference = 180 - absolute difference, to obtain hue difference = min (absolute difference, cycle difference); Photometric value processing: S264, by weighted average method B 1 and B 2 The RGB color channels are calculated to obtain B 1 and B 2 Luminosity: L (B1) =k×R+k×G+k×B; L (B2)= k×R+k×G+k×B; Where: R is the value of the red channel, G is the value of the green channel, B is the value of the blue channel, and k is the coefficient (0.299 for the red channel, 0.587 for the green channel, and 0.114 for the blue channel).

5. The image processing method for dynamic sampling of unmanned aerial vehicles according to claim 1 is characterized in that: The step S03 of acquiring the first amplitude ratio and the second amplitude ratio includes: S31, extracting the features B of each frame of image data aa in the corresponding problem frame collection A 1 and B 2 Middle image features; S32, then the first hue value and the first luminosity value of a and B 1 and B 2 Subtract the first hue value and the first luminance value of the image data a from each image data a in the problem frame collection A, thereby obtaining a hue value difference and a luminance value difference of each image data a in the problem frame collection A; S33, subtract the tone value differences of two adjacent image data a, and take the average value after continuous subtraction to obtain a first amplitude ratio; S34, subtract the luminance value differences of two adjacent image data a, take the average value after continuous subtraction, and obtain the second amplitude ratio.

6. The image processing method for dynamic sampling of unmanned aerial vehicles according to claim 1 is characterized in that: The correction of the image data a in the problem frame collection A in step S04 includes: S41. Linear adjustment of luminosity or chromaticity values: ; Among them, Y is the luminance value, Cb is the blue differential chromaticity component, Cr is the red differential chromaticity component, a is the second amplitude ratio, c is the middle red channel value of the first amplitude ratio, e is the middle blue channel value of the first amplitude ratio, and d is the image data a and B 1 and B 2 The average value of the difference between the red channel values, b is the image data a and B 1 and B 2 The average value of the difference in luminosity values, f is the image data a and B 1 and B 2 The average of the differences in the blue channel values; S42, applying a correction transformation function to each pixel of the image.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the image processing method for dynamic sampling of a drone according to any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the image processing method for dynamic sampling of a drone as described in any one of claims 1 to 6 are implemented.

Citation Information

Patent Citations

  • Method and apparatus for correcting color of display device

    CN101763844A

  • Image splicing quality evaluation-based unmanned aerial vehicle remote sensing image splicing method

    CN107146200A

  • Image synthesis method, apparatus, imaging apparatus, electronic apparatus, and computer-readable storage medium

    CN108989699A

  • Image processing method and device, electronic equipment and computer readable storage medium

    CN113596573A

  • Multi-angle SAR dynamic imaging detection method and device

    CN114240805A