Texture feature-based corner detection methods, systems, electronic devices, and media
By extracting and filtering texture features from images, separating the background from the texture, and combining multiple corner detection algorithms, the problems of long processing time and low accuracy in existing technologies are solved, achieving efficient and accurate corner detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANGHAI WINGTECH ELECTRONICS TECH
- Filing Date
- 2022-09-26
- Publication Date
- 2026-05-26
Smart Images
Figure CN115661036B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of image detection technology, and in particular to a corner detection method, system, electronic device and medium based on texture features. Background Technology
[0002] Points of interest (POIs) in an image (also known as keypoints or feature points) are easily detectable and representative points. Based on these points, target recognition, image matching, and defect detection can be performed. Corner points are one of the most fundamental types of POIs in an image; they can be defined as the intersection of two edges in an image, or a local maximum of curvature on a target contour line. Corner features are characterized by low computational cost, simple matching, and invariance to rotation, translation, and scaling. Therefore, they play a crucial role in applications such as image registration and matching, target recognition, motion analysis, and target tracking. Existing image corner detection methods heavily rely on the order of detection points and the distribution near the corner, making it difficult to determine whether the selected pixel positions best reflect corner performance; furthermore, traversing all pixels results in significant time consumption. Summary of the Invention
[0003] In view of the above-mentioned defects or deficiencies in the prior art, it is desirable to provide a corner detection method, system, electronic device and medium based on texture features.
[0004] In a first aspect, embodiments of this application provide a corner detection method based on texture features, comprising:
[0005] Texture features are extracted from the image to be processed to obtain a texture image;
[0006] The texture image is fused with the image to be processed to obtain the fused image;
[0007] Based on the texture image, corner detection is performed on the fused image.
[0008] In one embodiment, the process of extracting texture features from the image to be processed further includes:
[0009] The image to be processed is filtered to obtain the filtered image.
[0010] In one embodiment, the filtering method includes at least one of the following: Gaussian filtering and Gabor filtering.
[0011] In one embodiment, filtering the image to be processed using Gaussian filtering includes:
[0012] The images to be processed are scaled using Gaussian kernel functions with different scale factors and radii to obtain filtered images:
[0013] I(x,y) Ri =Gaussian i (I(x,y) in i = [1, 2, ..., N]
[0014] Where i represents the number of filters, Gaussian i Let σ represent the i-th scaling factor. i Radius R i The Gaussian kernel function, I(x,y). in Let I(x,y) represent the image to be processed. Ri This represents the i-th filtered image.
[0015] In one embodiment, texture features are extracted from the filtered image to obtain a texture image, as shown in the following formula:
[0016]
[0017] Where, I(x,y) Detaili Let I(x,y) represent the i-th detail image. Detail Represents a texture image, w i This represents the i-th weight value.
[0018] In one embodiment, the fused image I(x,y) out for:
[0019] I(x,y) out =I(x,y) in +I(x,y) Detail .
[0020] In one embodiment, the corner detection method includes at least one of the following: SIFT corner detection, ORB corner detection, FAST corner detection, Harris corner detection, and SURF corner detection.
[0021] Secondly, embodiments of this application provide a corner detection method based on texture features, including:
[0022] The texture extraction unit is used to extract texture features from the image to be processed, and obtain a texture image.
[0023] An image fusion unit is used to fuse the texture image with the image to be processed to obtain a fused image;
[0024] A corner detection unit is used to perform corner detection on the fused image based on the texture image.
[0025] In one embodiment, the system further includes:
[0026] An image filtering unit is used to filter the image to be processed to obtain a filtered image.
[0027] In one embodiment, the image filtering unit is further configured to perform scale processing on the image to be processed using Gaussian kernel functions with different scale factors and different radii to obtain a filtered image.
[0028] Thirdly, embodiments of this application provide an electronic device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the corner detection method based on texture features provided in any embodiment of this application.
[0029] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the corner detection method based on texture features provided in any embodiment of this application.
[0030] The corner detection method, system, electronic device, and medium based on texture features provided in this application embodiment separate the background and texture of the image to be processed to obtain a texture image, and then fuse the texture image with the image to be processed to obtain a fused image. Corner detection is performed on the fused image based on the texture image. By performing corner detection on the texture features of the image, the selected pixel position can better reflect the corner performance, greatly saving computing power and time. Attached Figure Description
[0031] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:
[0032] Figure 1 An exemplary flowchart of a corner detection method based on texture features provided in this application embodiment;
[0033] Figure 2 Another exemplary flowchart of a corner detection method based on texture features provided in this application embodiment;
[0034] Figure 3 A comparison image of the image to be processed and the fused image provided in an embodiment of this application; wherein, Figure (a) is the image to be processed; and Figure (b) is the fused image;
[0035] Figure 4 An exemplary flowchart of the FAST corner detection method provided in this application embodiment;
[0036] Figure 5An exemplary structural block diagram of a corner detection system based on texture features provided in this application embodiment;
[0037] Figure 6 Another exemplary structural block diagram of a corner detection system based on texture features provided in this application embodiment;
[0038] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0039] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.
[0040] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.
[0041] refer to Figure 1 The illustrated flowchart illustrates an exemplary corner detection method based on texture features. This application embodiment provides a corner detection method 100 based on texture features, comprising:
[0042] S120: Extract texture features from the image to be processed to obtain a texture image;
[0043] S130: The texture image is fused with the image to be processed to obtain a fused image;
[0044] S140: Based on the texture image, perform corner detection on the fused image.
[0045] Specifically, the image to be processed is any frame extracted from the acquired video. This frame is used as the original image for texture feature extraction, which separates the background and texture of the original image to obtain a texture image. The texture image is then fused with the image to be processed to obtain a fused image. Corner detection is performed on the fused image based on the texture image, which can greatly save computing power and time. Furthermore, image registration can also be performed based on the texture image in the future.
[0046] The corner detection method based on texture features provided in this application does not depend on the order of detection points or the distribution near the corner. Since the corners are basically located at texture features, the selected pixel positions can better reflect the corner performance when corner detection is performed based on the texture features of the image. The detection time is short and the detection efficiency and accuracy are high.
[0047] In one embodiment, the following steps are included before step S120:
[0048] S110: The image to be processed is filtered to obtain a filtered image.
[0049] Specifically, such as Figure 2 As shown, before extracting texture features from the image to be processed, the image to be processed is first filtered, and then texture features are extracted from the filtered image. Filtering the image to be processed can remove noise in the image, avoid mistaking noise points in the image for corner points, and improve the accuracy of corner point detection.
[0050] In one embodiment, in step S110, the filtering method includes at least one of the following: Gaussian filtering and Gabor filtering.
[0051] Specifically, Gaussian filtering, Gabor filtering, and other methods can be used to remove noise from the image to improve the accuracy of subsequent corner detection.
[0052] In one embodiment, step S110, filtering the image to be processed using a Gaussian filter method, includes:
[0053] The images to be processed are scaled using Gaussian kernel functions with different scale factors and radii to obtain filtered images:
[0054] I(x,y) Ri =Gaussian i (I(x,y) in i = [1, 2, ..., N]
[0055] Where i represents the number of filters, σ i Let R represent the i-th scaling factor. i Represents the i-th radius, Gaussian i Let σ represent the i-th scaling factor. i Radius R i The Gaussian kernel function, I(x,y). in Let I(x,y) represent the image to be processed. Ri This represents the i-th filtered image.
[0056] Specifically, the Gaussian kernel function is a method in image processing for constructing a scale space for an image, which uses different scale factors σ. i Different radii R i Gaussian kernel iConvolution is performed on the image to achieve scale processing, resulting in filtered images at different scales. In this embodiment, the filtering order i and the scale factor σ are... i radius R i The specific values are not particularly limited, and those skilled in the art can choose any value according to actual needs.
[0057] For example, if the maximum value N of the filtering order i is 3, that is, the image to be processed is subjected to three Gaussian filters, as follows:
[0058] I(x,y) R1 =Gaussian1(I(x,y) in ), σ1=1.0, R1=r
[0059] I(x,y) R2 =Gaussian2(I(x,y) in ), σ2=2.0, R1=2r
[0060] I(x,y) R3 =Gaussian3(I(x,y) in ), σ3=4.0, R1=4r
[0061] By using three different scale factors σ1, σ2, and σ3 to process the image to be processed, three filtered images at different scales are obtained, which facilitates the subsequent extraction of image detail information based on the filtered images at different scales to obtain the corresponding texture feature maps.
[0062] In one embodiment, in step S120, texture features are extracted from the filtered image to obtain a texture image, as shown in the following formula:
[0063]
[0064] Where, I(x,y) Detaili Let I(x,y) represent the i-th detail image. Detail Represents a texture image, w i This represents the i-th weight value.
[0065] Specifically, multiple detail images are first obtained based on the image to be processed and filtered images at different scales. Then, corresponding weights are assigned to each detail image to obtain a texture image. In this embodiment, the weight value w... i Without any special restrictions, those skilled in the art can choose any settings according to actual needs.
[0066] For example, if the weight values w1 = 0.50, w2 = 0.50, and w3 = 0.25, then the multiple detail images and texture images are as follows:
[0067] I(x,y) Detail1 =I(x,y) in -I(x,y) R1
[0068] I(x,y) Detail2 =I(x,y) R1 -I(x,y) R2
[0069] I(x,y) Detail3 =I(x,y) R2 -I(x,y) R3
[0070] I(x,y) Detail =(1-w1×sgn(I(x,y)) Detail1 ))×I(x,y) Detail1 +w2×I(x,y) Detail2 +w3×I(x,y) Detail3
[0071] In one embodiment, in step S130, the fused image I(x,y) out for:
[0072] I(x,y) out =I(x,y) in +I(x,y) Detail
[0073] Specifically, the image to be processed and the texture image are added together to obtain the fused image. Figure 3 (a) The image to be processed is the original image. Figure 3 (b) is the fused image, compared with... Figure 3 (a) and Figure 3 (b) It can be seen that the texture features of the fused image are more obvious, which is beneficial for corner detection.
[0074] In one embodiment, the corner detection method in S140 includes at least one of the following: SIFT corner detection, ORB corner detection, FAST corner detection, Harris corner detection, and SURF corner detection.
[0075] Specifically, in the embodiments of this application, based on texture images, various corner detection methods can be used for corner detection, such as SIFT (Scale-invariant feature transform) corner detection, ORB (Oriented FAST and Rotated BRIEF) corner detection, FAST (Features from Accelerated Segment Test) corner detection, Harris corner detection, SURF (Speeded Up Robust Features) corner detection, and any one of these corner detection methods.
[0076] Harris corner detection identifies points with sufficiently high gray-level changes in all directions within the neighborhood, which are also points with maximum curvature on the image edge curve. The basic idea of corner detection is as follows: using a corner detection operator, a corner response function is calculated for each pixel of the image. The corner response function is thresholded, and a threshold is selected based on the actual situation. Non-maximum suppression is applied to the thresholded corner response function, and non-zero points are obtained as corners. A small sliding window is used to detect corners in the neighborhood. If the gray-level values within the window change drastically in any direction, the center of the window is the corner.
[0077] In one embodiment, step S140 involves performing corner detection on the fused image based on the texture image using the FAST corner detection method, including:
[0078] A point P′(x,y) is determined on the texture image, and a point P(x,y) corresponding to point P′(x,y) is found on the fused image. The pixel value of point P(x,y) is set to I. P ;
[0079] In the fused image, a circle is drawn with point P(x,y) as the center point and radius r, and the circle covers M pixels;
[0080] Set a threshold t. If Q consecutive points within a circle surrounding point P(x,y) have a pixel value less than I... P -t or greater than I P If +t, then point P(x,y) is a corner point; M≥Q.
[0081] Specifically, a point P′(x,y) is determined on the texture image. The corresponding point P(x,y) is found in the fused image. Then, corner detection is performed on the fused image. For example, using the FAST corner detection method, point P(x,y) is compared with the 16 pixels surrounding it to determine if P(x,y) is a corner, i.e., whether point P′(x,y) is a corner. This process is repeated for each subsequent point in the texture image until all corners are found, ending the corner detection. Since most corners are located on the texture, checking texture points for corners shortens the detection time and improves efficiency.
[0082] For example, the FAST corner detection method can be used for corner detection. FAST is a template- and machine learning-based corner detection method that is not only fast in computation but also has high accuracy. The FAST method primarily considers 16 pixels within a circular window surrounding a pixel, as shown below. Figure 4 As shown, p is the center pixel, while the pixels marked with white boxes are the points we need to consider. FAST defines a corner as follows: if a pixel has a certain number of pixels around it with different values, it is considered a corner. Corner detection includes the following steps:
[0083] Select a point P in the image, and let the pixel of point P be I. P .
[0084] Draw a circle with radius r, covering M pixels around point P, as follows: Figure 4 As shown: r = 3, M = 16.
[0085] Set a threshold t. If Q consecutive pixels out of 16 pixels surrounding point P have a pixel value less than I... P -t or greater than I P If the threshold is +t, then the point is considered a corner point. The threshold t varies in different scenarios. If the threshold t is 0, it can be understood as having Q consecutive pixels greater than or less than I. P If the gray value is less than or equal to a certain value, then the point is a corner point. In the embodiments of this application, Q is usually 12 or 9. Experiments show that the corner detection performance is most stable, faster, and better when Q is 12, while some experiments show that the corner detection performance is better when Q is 9. The specific corner detection formula is as follows:
[0086]
[0087] Among them, I P I represents the pixel value of the center point P. p→x This represents the pixel at position x in the circular template surrounding point P; when the pixel at position x in the circular template surrounding point P is I... p→x Less than IP -t means the pixel belongs to the darker category. p→x =d; the other two cases represent brighter and similar, respectively. Therefore, the circular area around the center point P is divided into three types: d, s and b. If the number of occurrences of d or b is greater than Q (Q is 12 or 9), then the point is considered a candidate corner point.
[0088] In a preferred embodiment, in step S140, based on the texture image, corner detection is performed on the fused image using an improved FAST corner detection method, including:
[0089] A point P′(x,y) is determined on the texture image, and a point P(x,y) corresponding to point P′(x,y) is found on the fused image. The pixel value of point P(x,y) is set to I. P ;
[0090] In the fused image, a circle is drawn with point P(x,y) as the center point and radius r, and the circle covers M pixels;
[0091] Set a threshold t. Select four points perpendicular to each other from the M pixels on the circle surrounding point P(x,y). If the pixel value of at least three of the four points is less than I... P -t or greater than I P If +t, then point P(x,y) is a candidate corner point. Repeat this process until Q consecutive points within the M pixels surrounding point P(x,y) have pixels less than I. P -t or greater than I P If +t, then point P(x,y) is a corner point; M≥Q.
[0092] Specifically, in the above segmentation test, to speed up the process, it is unnecessary to compare each pixel individually. Instead, we can first compare the pixel values of four points on the circle surrounding the center point P in the horizontal and vertical directions with those of the center point, such as the pixel values at points 1, 5, 9, and 13. We then determine whether three or more of these pixel values are less than I. P -t or greater than I P If the condition is not met, skip directly; if it is met, consider the point as a candidate corner point and continue using the aforementioned method. If 12 out of 16 pixels meet the condition, consider the point as a corner point. This corner point detection method further accelerates the corner point detection rate.
[0093] It should be noted that although the operations of the method of the present invention are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. On the contrary, the steps depicted in the flowchart may be performed in a different order.
[0094] A second aspect of the embodiments of this application, referring to... Figure 5 The diagram shows an exemplary structural block diagram of a texture feature-based corner detection system. This embodiment of the texture feature-based corner detection system 200 includes:
[0095] The texture extraction unit 220 is used to extract texture features from the image to be processed to obtain a texture image;
[0096] The image fusion unit 230 is used to fuse the texture image with the image to be processed to obtain a fused image;
[0097] The corner detection unit 240 is used to perform corner detection on the fused image based on the texture image.
[0098] Specifically, the system provided in this application separates the background and texture of the image to be processed to obtain a texture image, performs corner detection based on the texture features of the image, determines whether the texture features are corners, and the selected pixel positions can better reflect the corner performance, which can greatly save computing power and time.
[0099] In one embodiment, such as Figure 6 As shown, the system also includes:
[0100] Image filtering unit 210 is used to filter the image to be processed to obtain a filtered image.
[0101] Specifically, the image filtering unit 210 can filter the image to be processed to remove noise, preventing noise points from being mistaken for corner points and improving the accuracy of corner detection. The image filtering unit 210 can be used to perform Gaussian filtering and Gabor filtering.
[0102] In one embodiment, the image filtering unit 210 is further configured to perform scale processing on the image to be processed using Gaussian kernel functions with different scale factors and different radii to obtain a filtered image.
[0103] Specifically, the image filtering unit 210 uses a Gaussian filtering method to filter the image to be processed. The specific Gaussian filtering method is as described above, and will not be repeated in detail in this embodiment.
[0104] In one embodiment, the texture extraction unit 220 is used to obtain multiple detail images based on the image to be processed and filtered images of different scales, and to configure corresponding weights for each of the multiple detail images to obtain texture images.
[0105] Specifically, the texture extraction unit 220 is used to process the image to be processed and the filtered images at different scales to obtain texture images. The specific texture image extraction method is as described above.
[0106] In one embodiment, the image fusion unit 230 is used to add the texture image to the image to be processed to obtain a fused image.
[0107] In one embodiment, the corner detection unit 240 is configured to perform at least one of the following methods: SIFT corner detection, ORB corner detection, FAST corner detection, Harris corner detection, and SURF corner detection.
[0108] Specifically, the detection method performed by the corner detection unit 240 is as described above, and will not be repeated in detail in this embodiment.
[0109] A third aspect of the embodiments of this application provides an electronic device whose internal structure diagram can be as follows: Figure 7 As shown, the electronic device includes a processor, memory, communication interface, display screen, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a corner detection method based on texture features. The display screen can be a liquid crystal display (LCD) or an e-ink display. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the device's casing, or an external keyboard, touchpad, or mouse.
[0110] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.
[0111] In one embodiment, the texture feature-based corner detection system 200 provided in this application can be implemented as a computer program, which can be implemented in various ways, such as... Figure 7 The system operates on the electronic device shown. The memory of the electronic device can store the various program modules that make up the texture-based corner detection system 200, for example, Figure 6 The image filtering unit 210, texture extraction unit 220, image fusion unit 230, corner detection unit 240, etc., are shown. The computer program composed of these various program modules causes the processor to execute the steps in the texture feature-based corner detection methods of the various embodiments of this application described in this specification.
[0112] In one embodiment, an electronic device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the texture feature-based corner detection method described above.
[0113] In one embodiment, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the steps in the above method embodiments.
[0114] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static random access memory (SRAM) and dynamic random access memory (DRAM), etc.
[0115] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0116] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.
Claims
1. A corner detection method based on texture features, characterized in that, include: Texture features are extracted from the image to be processed to obtain a texture image; The texture image is fused with the image to be processed to obtain the fused image; Based on the texture image, corner detection is performed on the fused image using the FAST corner detection method or an improved FAST corner detection method; The FAST corner detection method is used to detect corners in the fused image, including: Determine a point on the texture image Find points on the fused image Corresponding points Set point The number of pixels is ; In the fused image, in points Draw a circle with radius r as the center point, and cover the circle with r. 1 pixel; Set threshold If point On the surrounding circle There are consecutive pixels The number of pixels is less than or greater than Then point Corner point ; The improved FAST corner detection method is used to detect corners in the fused image, including: Determine a point on the texture image Find points on the fused image Corresponding points Set point The number of pixels is ; In the fused image, in points Draw a circle with radius r as the center point, and cover the circle with r. 1 pixel; Set threshold At point On the surrounding circle Select four points perpendicular to each other from a given set of pixels. If at least three of these four points have a pixel value less than [a certain value], then [the following condition applies]. or greater than Then point For candidate corner points, repeat the judgment until a point is found. On the surrounding circle There are consecutive pixels The number of pixels is less than or greater than Then point Corner point; .
2. The corner detection method based on texture features according to claim 1, characterized in that, Before extracting texture features from the image to be processed, the following steps are also included: The image to be processed is filtered to obtain the filtered image.
3. The corner detection method based on texture features according to claim 2, characterized in that, The filtering method includes at least one of the following: Gaussian filtering and Gabor filtering.
4. The corner detection method based on texture features according to claim 3, characterized in that, The filtering process for the image to be processed using Gaussian filtering includes: The images to be processed are scaled using Gaussian kernel functions with different scale factors and radii to obtain filtered images: ； in, Indicates the number of filters. Indicates the first Each scaling factor is , radius is Gaussian kernel function, This represents the image to be processed. Indicates the first A filtered image.
5. The corner detection method based on texture features according to claim 4, characterized in that, The filtered image is subjected to texture feature extraction to obtain a texture image, as shown in the following formula: in, Indicates the first A detailed image; Represents a texture image. Indicates the first Each weight value.
6. The corner detection method based on texture features according to claim 5, characterized in that, The fused image for: 。 7. The corner detection method based on texture features according to any one of claims 1-6, characterized in that, The corner detection method includes at least one of the following: SIFT corner detection, ORB corner detection, FAST corner detection, Harris corner detection, and SURF corner detection.
8. A corner detection system based on texture features, characterized in that, The system is used to execute the corner detection method based on texture features according to any one of claims 1-7, including: The texture extraction unit is used to extract texture features from the image to be processed, and obtain a texture image. An image fusion unit is used to fuse the texture image with the image to be processed to obtain a fused image; A corner detection unit is used to perform corner detection on the fused image based on the texture image.
9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the corner detection method based on texture features as described in any one of claims 1-7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the corner detection method based on texture features as described in any one of claims 1-7.