Image comparison method, device and terminal device based on drone aerial photography

Abstract

The present invention discloses an image comparison method, device and terminal device based on drone aerial photography. The method extracts feature points from the before-shooting image and the after-shooting image of the same scene taken by the drone at different times, and then performs registration, comparison and superposition to obtain a suspected abnormal area; after extracting feature points from the suspected abnormal area and the before-shooting image again, registration, comparison and superposition are performed again to obtain a second abnormal area. Compared with the existing technology that calculates the gray value and color channel of the image, the technical solution of the present invention matches and calculates the features of the before-shooting image and the after-shooting image through secondary registration, secondary comparison and secondary superposition, which reduces the measurement error caused by the slight difference in the position of the drone, thereby obtaining a more accurate abnormal area.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle (UAV) aerial photography, and in particular to an image comparison method, device and terminal equipment based on unmanned aerial vehicle (UAV) aerial photography. Background Art

[0002] Urban monitoring is an important way to ensure urban safety. Common monitoring methods include the Sky Eye system, user-installed cameras, and patrols by on-duty personnel. By checking abnormal areas, the safety of the city can be improved. Drones are usually equipped with cameras. By using drones to take low-altitude aerial photos of the city, a more comprehensive perspective can be obtained, which is conducive to users using drones to quickly and accurately find abnormal areas. With the continuous development of drone technology and camera technology, drone control has become more stable and image data acquisition has become more comprehensive. These two technologies make it possible to automatically monitor abnormal phenomena. Therefore, this application mainly compares images for drone aerial photography to obtain abnormal conditions at a certain location to improve people's safety.

[0003] As for the drone aerial photography method, the existing technologies include: "A method, device, equipment and medium for calculating the area of ​​farmland from aerial images" (CN111080526A). This technology obtains a panoramic image by splicing the aerial images obtained, and calculates the grayscale image and pixel area of ​​the panoramic image to obtain the area of ​​the farmland.

[0004] The inventors found in the process of implementing the present invention that the existing drones require professional pilots to control the drones to avoid safety accidents, and the data obtained by the drones also need to be manually analyzed, which is inefficient. In addition, carrying a variety of equipment on the drone body will increase the cost of using drones for urban monitoring, and the increased weight of the equipment will also reduce the endurance of the drone, making it impossible to obtain photos for a long time. Summary of the invention

[0005] The embodiments of the present invention provide an image comparison method, an apparatus and a terminal device based on drone aerial photography, which improve the detection accuracy of image abnormalities by secondary comparison of suspected abnormal areas.

[0006] In order to solve the above problem, an embodiment of the present invention provides an image comparison method based on drone aerial photography, comprising:

[0007] Registering a first image and a second image, extracting feature points of the first image and the second image, and obtaining a first common area in the first image and a second common area in the second image according to the feature points; wherein the first image and the second image are aerial images of the same scene but at different times;

[0008] Comparing the first common area with the second common area to obtain a grayscale binary image and a color channel binary image;

[0009] Superimposing the grayscale binary image and the color channel binary image to obtain a first abnormal area;

[0010] A second abnormal region is obtained by performing a secondary registration process, a secondary comparison process and a secondary superposition process on the first abnormal region and the first common region; wherein the second abnormal region is displayed in the second image.

[0011] As an improvement of the above solution, the grayscale binary image and the color channel binary image are obtained as follows:

[0012] Converting the first common area and the second common area into grayscale images;

[0013] Performing histogram normalization processing on the grayscale image of the first common area to obtain a grayscale histogram of the first common area;

[0014] Performing histogram regulation processing on the grayscale map of the second public area, adjusting the grayscale distribution of the second public area according to the grayscale histogram of the first public area, and obtaining the grayscale histogram of the second public area;

[0015] Subtracting the grayscale values ​​of the grayscale histograms of the first common area and the second common area to obtain a grayscale difference map;

[0016] The grayscale difference image is binarized to obtain the grayscale binary image.

[0017] As an improvement of the above solution, the step of obtaining the grayscale binary image and the color channel binary image further includes:

[0018] Extracting a color channel of the first common area and a color channel of the second common area and performing a subtraction to obtain a color channel difference map;

[0019] The color channel difference image is binarized to obtain the color channel binary image.

[0020] As an improvement of the above solution, the grayscale difference image is binarized to obtain the grayscale binary image, specifically:

[0021] Calculate a segmentation threshold with the maximum inter-class variance between the first common area and the second common area;

[0022] The grayscale difference image is binarized according to the segmentation threshold to obtain the grayscale binary image.

[0023] As an improvement of the above solution, the grayscale binary image and the color channel binary image are superimposed to obtain the first abnormal area, specifically:

[0024] The grayscale binary image and the color channel binary image are processed by a morphological opening operation, and after excluding abnormal areas whose pixel areas of the grayscale binary image and the color channel binary image are smaller than a set value, the grayscale binary image and the color channel binary image are superimposed on each other to obtain the first abnormal area.

[0025] As an improvement of the above solution, performing secondary registration processing, secondary comparison processing and secondary superposition processing on the first abnormal region and the first common region to obtain the second abnormal region is specifically:

[0026] Calculating the pixel area of ​​the first abnormal area, and removing the area with an area smaller than a set value;

[0027] The secondary registration process is to use the ASIFT feature point extraction algorithm to simulate different shooting angles of the image, and to register the first abnormal area with the small area removed and the first common area, so as to extract more extractable feature points;

[0028] Obtaining a third common area of ​​the first abnormal area and a fourth common area of ​​the first common area according to the feature points;

[0029] The secondary comparison process is to compare the third common area and the fourth common area again to obtain an updated grayscale binary image and a color channel binary image;

[0030] The secondary superposition process is to superimpose the updated grayscale binary image and the color channel binary image again to obtain a second abnormal area.

[0031] As an improvement of the above solution, before extracting the feature points of the first image and the second image, the method further includes:

[0032] The drone is controlled to perform aerial photography at a preset route and period, thereby acquiring the first image and the second image; wherein the route includes the GPS position, flight altitude, shooting angle, and nose direction of each waypoint.

[0033] The embodiment of the present invention also provides an image comparison device based on drone aerial photography, comprising: a registration module, a primary comparison module, a calculation module and a secondary comparison module;

[0034] The registration module is used to register the first image and the second image, extract feature points of the first image and the second image, and obtain a first common area in the first image and a second common area in the second image according to the feature points; wherein the first image and the second image are aerial images of the same scene and different periods;

[0035] The initial comparison module is used to compare the first common area and the second common area to obtain a grayscale binary image and a color channel binary image respectively;

[0036] The calculation module is used to superimpose the grayscale binary image and the color channel binary image to obtain a first abnormal area;

[0037] The secondary comparison module is used to perform secondary registration, secondary comparison and secondary superposition processing on the first abnormal area and the first common area to obtain a second abnormal area; wherein the second abnormal area is displayed in the second image.

[0038] An embodiment of the present invention also provides a computer terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the image comparison method based on drone aerial photography as described in the present invention is implemented.

[0039] An embodiment of the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the image comparison method based on drone aerial photography as described in the present invention.

[0040] The embodiments of the present invention have the following beneficial effects:

[0041] The present invention provides an image comparison method, device and terminal device based on drone aerial photography. The method extracts feature points from the before-shooting image and the after-shooting image of the same scene taken by the drone at different times, and then performs registration, comparison and superposition to obtain a suspected abnormal area; after extracting feature points from the suspected abnormal area and the before-shooting image again, registration, comparison and superposition are performed again to obtain a second abnormal area. Compared with the existing technology that calculates the gray value and color channel of the image, the technical solution of the present invention matches and calculates the features of the before-shooting image and the after-shooting image through secondary registration, secondary comparison and secondary superposition, which reduces the measurement error caused by the slight difference in the position of the drone, thereby obtaining a more accurate abnormal area.

[0042] Furthermore, when extracting feature points again from the first abnormal area and the image before shooting, the present invention uses the ASIFT feature point extraction algorithm to simulate different shooting angles of the image, thereby obtaining a larger number of feature points for registration, thereby improving the matching degree of small areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flow chart of an embodiment of the image comparison method based on drone aerial photography provided by the present invention;

[0044] Figure 2 It is a structural schematic diagram of an embodiment of an image comparison device based on drone aerial photography provided by the present invention;

[0045] Figure 3 It is a flow chart of another embodiment of the image comparison method based on drone aerial photography provided by the present invention;

[0046] Figure 4 It is a structural schematic diagram of an embodiment of the terminal device provided by the present invention. DETAILED DESCRIPTION

[0047] 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.

[0048] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of an embodiment of an image comparison method based on drone aerial photography provided by the present invention. Figure 1 As shown, the method includes steps 101 to 104, and each step is specifically as follows:

[0049] Step 101: align a first image and a second image, extract feature points of the first image and the second image, and obtain a first common area in the first image and a second common area in the second image based on the feature points; wherein the first image and the second image are aerial images of the same scene but at different times.

[0050] In this embodiment, before extracting the feature points of the first image and the second image, it also includes: controlling the drone to perform aerial photography at a preset route and period, so as to obtain the first image and the second image; wherein the route includes the GPS position, flight altitude, shooting angle and nose direction of each waypoint; thereby obtaining the first image and the second image at the same position and different time.

[0051] Preferably, the images obtained at different times need to be sorted and classified according to the locations of waypoints to ensure that the two images to be compared are taken at different times at the same location.

[0052] Preferably, the image captured first is defined as the first image, and the image captured later is defined as the second image; and Gaussian filtering is performed on the two images to reduce the influence of noise and improve the efficiency of feature point extraction.

[0053] Preferably, the feature points of the two images are extracted respectively using the SIFT feature extraction algorithm; and based on the feature points of the two images, the Brute Force matching method is used to match them, extracting the feature points of the first image one by one, traversing the feature points of the second image, and selecting the feature points with the highest matching degree as the matching point pairs, and then removing the matching point pairs with low matching degrees.

[0054] Preferably, a homography matrix of matching point pairs with a high matching degree is calculated, and the image mapping is completed according to the calculated homography matrix, so as to respectively obtain the common area of ​​the first image and the second image.

[0055] Step 102: Compare the first common area and the second common area to obtain a grayscale binary image and a color channel binary image.

[0056] In this embodiment, step 102 is specifically as follows: converting the first common area and the second common area into a grayscale image; performing histogram normalization processing on the grayscale image of the first common area to obtain a grayscale histogram of the first common area; performing histogram normalization processing on the grayscale image of the second common area, adjusting the grayscale distribution of the second common area according to the grayscale histogram of the first common area, and obtaining a grayscale histogram of the second common area; subtracting the grayscale values ​​of the grayscale histograms of the first common area and the second common area to obtain a grayscale difference image; and binarizing the grayscale difference image to obtain a grayscale binary image.

[0057] The color channel of the first common area and the color channel of the second common area are extracted and subtracted to obtain a color channel difference map; the color channel difference map is binarized to obtain a color channel binary map.

[0058] Preferably, a segmentation threshold with the maximum inter-class variance between the first common area and the second common area is calculated; and the grayscale difference image is binarized according to the segmentation threshold to obtain the grayscale binary image.

[0059] Preferably, the OTSU algorithm is used to binarize the difference image.

[0060] Step 103: superimpose the grayscale binary image and the color channel binary image to obtain a first abnormal area.

[0061] In this embodiment, step 103 is specifically as follows: performing a morphological opening operation on the grayscale binary image and the color channel binary image, and after excluding abnormal areas where the pixel area of ​​the grayscale binary image and the pixel area of ​​the color channel binary image are smaller than a set value, the grayscale binary image and the color channel binary image are superimposed on each other to obtain a first abnormal area.

[0062] Preferably, an abnormal region with a pixel area smaller than a set value is regarded as a useless region and excluded to improve the accuracy of the first abnormal region.

[0063] Step 104: performing secondary registration processing, secondary comparison processing and secondary superposition processing on the first abnormal region and the first common region to obtain a second abnormal region; wherein the second abnormal region is displayed in the second image.

[0064] In this embodiment, step 104 is specifically as follows: calculating the pixel area of ​​the first abnormal area and removing the area with an area smaller than a set value; the secondary registration process is to use the ASIFT feature point extraction algorithm to simulate different shooting angles of the image, and to register the first abnormal area with the small area removed and the first common area, and extract a larger number of extractable feature points; and obtaining the third common area of ​​the first abnormal area and the fourth common area of ​​the first common area according to the feature points.

[0065] The secondary comparison process is to compare the third common area and the fourth common area again to obtain an updated grayscale binary image and a color channel binary image.

[0066] The secondary superposition process is to superimpose the updated grayscale binary image and the color channel binary image again to obtain a second abnormal area.

[0067] Preferably, the ASIFT feature point extraction algorithm is used to simulate different shooting angles of the image, and then the SIFT feature point extraction algorithm is used to extract feature points, so as to obtain a larger number of feature points.

[0068] See also Figure 2 , Figure 2 FIG. 1 is a schematic diagram of a structure of an embodiment of an image comparison device based on drone aerial photography provided by the present invention. Figure 2 As shown, the device includes: a registration module 201, a primary comparison module 202, a calculation module 203 and a secondary comparison module 204;

[0069] The registration module 201 is used to register the first image and the second image, extract feature points of the first image and the second image, and obtain a first common area in the first image and a second common area in the second image according to the feature points; wherein the first image and the second image are aerial images of the same scene and different periods;

[0070] The initial comparison module 202 is used to compare the first common area and the second common area to obtain a grayscale binary image and a color channel binary image respectively;

[0071] The calculation module 203 is used to superimpose the grayscale binary image and the color channel binary image to obtain the first abnormal area;

[0072] The secondary comparison module 204 is used to perform secondary registration, secondary comparison and secondary superposition processing according to the first abnormal area and the first common area to obtain a second abnormal area; wherein the second abnormal area is displayed in the second image.

[0073] See also Figure 3 , Figure 3 FIG. 1 is a flow chart of another embodiment of the image comparison method based on drone aerial photography provided by the present invention. Figure 3 As shown, specifically:

[0074] In this embodiment, step 301: data acquisition: by setting the aerial photography cycle and route of the drone, two images of the same position and different times are acquired, and the images are divided into aerial images (front) and aerial images (back).

[0075] Step 302: Perform image preprocessing: obtain an aerial image (front) and an aerial image (back), and use Gaussian filtering to remove noise from the two images.

[0076] Step 303: Perform image matching: Use the SIFT feature point extraction algorithm to extract feature points of the two images, use the Brue Force matching method to calculate matching point pairs, and screen out point pairs with high matching degrees, calculate the homography matrix of the point pairs with high matching degrees, and perform image mapping according to the homography matrix, so as to obtain the common areas of the aerial image (front) and the aerial image (back), respectively.

[0077] Step 304: Perform initial image comparison: for the obtained common area (front) and common area (back), convert them into grayscale images to calculate grayscale difference images and divide them into three color channels to calculate color channel difference images, obtain grayscale difference images of the common area (front) and common area (back), and color channel difference images of the common area (front) and common area (back), perform binarization processing and image morphological opening processing on the obtained grayscale difference images and color channel difference images, exclude areas with pixel areas smaller than a set value, and then superimpose the processed grayscale difference images and color channel images to obtain suspected abnormal areas.

[0078] Step 305: Perform secondary image comparison: exclude areas in the suspected abnormal region where the pixel area is smaller than the set value, perform image matching and initial image comparison steps again on the obtained suspected abnormal region and the common region (front), and finally obtain the abnormal region.

[0079] See also Figure 4 , Figure 4 It is a structural schematic diagram of an embodiment of the terminal device provided by the present invention.

[0080] A terminal device of this embodiment includes: a processor 401, a memory 402, and a computer program stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program, the steps of the above-mentioned image comparison method based on drone aerial photography in the embodiment are implemented, for example Figure 1 Alternatively, when the processor executes the computer program, the functions of each module in the above-mentioned device embodiments are realized, for example: Figure 2 All modules of the image comparison device based on drone aerial photography are shown.

[0081] In addition, an embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the image comparison device based on drone aerial photography as described in any of the above embodiments.

[0082] Those skilled in the art will understand that the schematic diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the diagram, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0083] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 401 is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0084] The memory 402 can be used to store the computer program and / or module, and the processor 401 realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory 402. The memory 402 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0085] Wherein, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0086] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0087] As can be seen from the above, the present invention provides an image comparison method, device and terminal device based on drone aerial photography. The method fully utilizes the illumination and color information of the visible light image by performing grayscale image and three-color channel difference calculation on the common area of ​​the two previous and subsequent aerial images. It can be processed by ordinary camera equipment without the need to carry other equipment, and has the beneficial effect of reducing the cruising cost and cruising energy consumption of the drone. The present invention also adopts a secondary comparison method to improve the image matching degree through local alignment, thereby eliminating deformation caused by deviation in the shooting position, thereby improving the accuracy of the result. Even in the absence of professional drone operators, the present invention can set a route for shooting, thereby improving the consistency of aerial images. The present invention can be applied to low-altitude shooting of cities to discover illegal and irregular behaviors. It has the advantages of low cost, high efficiency and high accuracy, and can be widely used in the detection of abnormal areas.

[0088] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. An image comparison method based on drone aerial photography, characterized in that: include: Registering a first image and a second image, extracting feature points of the first image and the second image, and obtaining a first common area in the first image and a second common area in the second image according to the feature points; wherein the first image and the second image are aerial images of the same scene but at different times; Comparing the first common area with the second common area to obtain a grayscale binary image and a color channel binary image; Superimposing the grayscale binary image and the color channel binary image to obtain a first abnormal area; A second abnormal area is obtained by performing secondary registration processing, secondary comparison processing and secondary superposition processing on the first abnormal area and the first common area; wherein the second abnormal area is displayed in the second image; the second abnormal area is obtained by performing secondary registration processing, secondary comparison processing and secondary superposition processing on the first abnormal area and the first common area, specifically: calculating the pixel area of ​​the first abnormal area, and removing the area with an area smaller than a set value; the secondary registration processing is to simulate different shooting angles of the image by using the ASIFT feature point extraction algorithm, and to register the first abnormal area and the first common area with the small area removed, and extract more extractable feature points; the third common area of ​​the first abnormal area and the fourth common area of ​​the first common area are obtained according to the feature points; the secondary comparison processing is to compare the third common area with the fourth common area again, and obtain an updated grayscale binary image and a color channel binary image; the secondary superposition processing is to superimpose the updated grayscale binary image and the color channel binary image again to obtain the second abnormal area.

2. The image comparison method based on drone aerial photography according to claim 1 is characterized in that: The grayscale binary image and the color channel binary image are obtained as follows: Converting the first common area and the second common area into grayscale images; Performing histogram normalization processing on the grayscale image of the first common area to obtain a grayscale histogram of the first common area; Performing histogram regulation processing on the grayscale map of the second public area, adjusting the grayscale distribution of the second public area according to the grayscale histogram of the first public area, and obtaining the grayscale histogram of the second public area; Subtracting the grayscale values ​​of the grayscale histograms of the first common area and the second common area to obtain a grayscale difference map; The grayscale difference image is binarized to obtain the grayscale binary image.

3. The image comparison method based on drone aerial photography according to claim 2 is characterized in that: The step of obtaining the grayscale binary image and the color channel binary image further includes: Extracting a color channel of the first common area and a color channel of the second common area and performing a subtraction to obtain a color channel difference map; The color channel difference image is binarized to obtain the color channel binary image.

4. The image comparison method based on drone aerial photography according to claim 3 is characterized in that: The binarization process is performed on the grayscale difference image to obtain the grayscale binary image, specifically: Calculate a segmentation threshold with the maximum inter-class variance between the first common area and the second common area; The grayscale difference image is binarized according to the segmentation threshold to obtain the grayscale binary image.

5. The image comparison method based on drone aerial photography according to claim 1 is characterized in that: The superposition of the grayscale binary image and the color channel binary image to obtain the first abnormal area is specifically as follows: The grayscale binary image and the color channel binary image are processed by a morphological opening operation, and after excluding abnormal areas whose pixel areas of the grayscale binary image and the color channel binary image are smaller than a set value, the grayscale binary image and the color channel binary image are superimposed on each other to obtain the first abnormal area.

6. The image comparison method based on drone aerial photography according to claim 1 is characterized in that: Before extracting the feature points of the first image and the second image, the method further includes: The drone is controlled to perform aerial photography at a preset route and period, thereby acquiring the first image and the second image; wherein the route includes the GPS position, flight altitude, shooting angle, and nose direction of each waypoint.

7. An image comparison device based on drone aerial photography, characterized in that: include: Registration module, primary alignment module, calculation module and secondary alignment module; The registration module is used to register the first image and the second image, extract feature points of the first image and the second image, and obtain a first common area in the first image and a second common area in the second image according to the feature points; wherein the first image and the second image are aerial images of the same scene and different periods; The initial comparison module is used to compare the first common area and the second common area to obtain a grayscale binary image and a color channel binary image respectively; The calculation module is used to superimpose the grayscale binary image and the color channel binary image to obtain a first abnormal area; The secondary comparison module is used to perform secondary registration, secondary comparison and secondary superposition processing on the first abnormal area and the first common area to obtain a second abnormal area; wherein the second abnormal area is displayed in the second image; the secondary registration processing, secondary comparison processing and secondary superposition processing on the first abnormal area and the first common area to obtain the second abnormal area are specifically: calculating the pixel area of ​​the first abnormal area and removing the area with an area smaller than a set value; the secondary registration processing is to simulate different shooting angles of the image by using the ASIFT feature point extraction algorithm, and to register the first abnormal area and the first common area with the small area removed to extract more extractable feature points; the third common area of ​​the first abnormal area and the fourth common area of ​​the first common area are obtained according to the feature points; the secondary comparison processing is to compare the third common area and the fourth common area again to obtain an updated grayscale binary image and a color channel binary image; the secondary superposition processing is to superimpose the updated grayscale binary image and the color channel binary image again to obtain the second abnormal area.

8. A computer terminal device, characterized in that: It comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the image comparison method based on drone aerial photography as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the image comparison method based on drone aerial photography as described in any one of claims 1 to 6.

Images