CN115661036A - Corner point detection method and system based on texture features, electronic device and medium - Google Patents
Corner point detection method and system based on texture features, electronic device and medium Download PDFInfo
- Publication number
- CN115661036A CN115661036A CN202211178236.5A CN202211178236A CN115661036A CN 115661036 A CN115661036 A CN 115661036A CN 202211178236 A CN202211178236 A CN 202211178236A CN 115661036 A CN115661036 A CN 115661036A
- Authority
- CN
- China
- Prior art keywords
- image
- texture
- corner detection
- processed
- corner
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000001914 filtration Methods 0.000 claims description 43
- 238000004590 computer program Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000005316 response function Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The application relates to the technical field of image detection, and provides a corner detection method and system based on texture features, an electronic device and a medium. The method comprises the following steps: extracting texture features of the image to be processed to obtain a texture image; fusing the texture image and the image to be processed to obtain a fused image; and performing corner detection on the fused image based on the texture image. The method comprises the steps of separating a background and a texture of an image to be processed to obtain a texture image, fusing the texture image and the image to be processed to obtain a fused image, and carrying out corner point detection on the fused image based on the texture image. By adopting the method, the corner detection is carried out on the textural features of the image, and the selected pixel position can better reflect the performance of the corner, thereby greatly saving the calculation power and the time consumption.
Description
Technical Field
The present disclosure relates to the field of image detection technologies, and in particular, to a corner detection method and system based on texture features, an electronic device, and a medium.
Background
Interest points (also called keypoints, feature points) in an image are points that are easy to detect in the image and have a representative meaning. Based on these points, object recognition, image matching, defect detection, and the like can be performed. A corner point is a most basic point of interest in an image and can be defined as the intersection of two edges in the image, or a local maximum of curvature on the contour line of an object. The angular point features have the characteristics of less calculated amount, simple matching, invariance to rotation, translation, scaling and the like, so that the method plays a very important role in the application fields of image registration and matching, target recognition, motion analysis, target tracking and the like. The existing image corner detection depends heavily on the sequence of detection points and the distribution near corners, and the best response corner performance of the selected and compared pixel positions is difficult to explain; and because all the pixel points are traversed, the consumed time is more.
Disclosure of Invention
In view of the above-mentioned drawbacks and deficiencies of the prior art, it is desirable to provide a corner point detection method, system, electronic device, and medium based on texture features.
In a first aspect, an embodiment of the present application provides a corner detection method based on texture features, including:
extracting texture features of the image to be processed to obtain a texture image;
fusing the texture image and the image to be processed to obtain a fused image;
and performing corner point detection on the fused image based on the texture image.
In one embodiment, before performing texture feature extraction on the image to be processed, the method further includes:
and filtering the image to be processed to obtain a filtered image.
In one embodiment, the method of filtering processing includes at least one of: gaussian filtering, gabor filtering.
In one embodiment, the filtering the image to be processed by using the gaussian filtering method includes:
carrying out scale processing on the image to be processed by adopting Gaussian kernel functions with different scale factors and different radiuses to obtain a filtered image:
I(x,y) Ri ＝Gaussian i (I(x,y) in )；i＝[1,2,…,N]
wherein i represents the number of filtering times, gaussian i Denotes the ith scale factor as σ i Radius R i Gaussian kernel function of (1), I (x, y) in Representing the image to be processed, I (x, y) Ri Representing the ith filtered image.
In one embodiment, the texture feature extraction is performed on the filtered image to obtain a texture image, and the formula is as follows:
wherein, I (x, y) Detaili Representing the ith detail image; i (x, y) Detail Representing a texture image, w i Representing the ith weight value.
In one embodiment, the fused image I (x, y) out Comprises the following steps:
I(x,y) out ＝I(x,y) in +I(x,y) Detail 。
in one embodiment, the corner detection method includes at least one of: SIFT corner detection, ORB corner detection, FAST corner detection, harris corner detection and SURF corner detection.
In a second aspect, an embodiment of the present application provides a corner detection method based on texture features, including:
the texture extraction unit is used for extracting texture features of the image to be processed to obtain a texture image;
the image fusion unit is used for fusing the texture image and the image to be processed to obtain a fused image;
and the corner detection unit is used for detecting the corners of the fused image based on the texture image.
In one embodiment, the system further comprises:
and the image filtering unit is used for carrying out filtering processing on the image to be processed to obtain a filtered image.
In an embodiment, the image filtering unit is further configured to perform scale processing on the image to be processed by using gaussian kernel functions with different scale factors and different radii, so as to obtain a filtered image.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements, when executing the computer program, the steps of the corner detection method based on texture features provided in any embodiment of the present application.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the texture feature-based corner detection method provided in any embodiment of the present application.
According to the corner detection method based on the texture features, the background and the texture of an image to be processed are separated to obtain a texture image, the texture image and the image to be processed are fused to obtain a fused image, the fused image is subjected to corner detection based on the texture image, and the selected pixel position can better reflect the performance of a corner by performing the corner detection on the texture features of the image, so that the calculation force and the time consumption are greatly saved.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
fig. 1 is an exemplary flowchart of a corner detection method based on texture features according to an embodiment of the present disclosure;
fig. 2 is another exemplary flowchart of a corner detection method based on texture features according to an embodiment of the present disclosure;
FIG. 3 is a comparison graph of a to-be-processed image and a fused image provided in an embodiment of the present application; wherein, the image (a) is an image to be processed; FIG. (b) is the fused image;
fig. 4 is an exemplary flowchart of a FAST corner detection method provided in an embodiment of the present application;
fig. 5 is a block diagram of an exemplary structure of a corner detection system based on texture features according to an embodiment of the present disclosure;
fig. 6 is a block diagram of another exemplary structure of a corner detection system based on texture features according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Referring to an exemplary flowchart of a corner detection method based on texture features shown in fig. 1, an embodiment of the present application provides a corner detection method 100 based on texture features, including:
s120: extracting texture features of the image to be processed to obtain a texture image;
s130: fusing the texture image and the image to be processed to obtain a fused image;
s140: and performing corner point detection on the fused image based on the texture image.
Specifically, the image to be processed is any one frame of image extracted from the acquired video, the frame of image is used as an original image to perform texture feature extraction, so that the background of the original image is separated from the texture, thereby obtaining a texture image, the texture image is fused with the image to be processed, so as to obtain a fused image, the fused image is subjected to corner point detection based on the texture image, so that the calculation power and the time consumption can be greatly saved, and the subsequent image registration can also be performed based on the texture image.
According to the corner detection method based on the textural features, the detection of the corners does not depend on the sequence of detection points and the distribution near the corners, and the corners are basically located at the textural features, so that the corner detection is performed based on the textural features of the image, the selected pixel positions can better reflect the performance of the corners, the detection time is short, and the detection efficiency and the accuracy are high.
In one embodiment, the method further comprises the following steps before step S120:
s110: and filtering the image to be processed to obtain a filtered image.
Specifically, as shown in fig. 2, before performing texture feature extraction on the image to be processed, filtering is performed on the image to be processed, and then texture feature extraction is performed on the filtered image, so that noise in the image can be removed by performing filtering on the image to be processed, noise points in the image are prevented from being mistaken for corner points, and accuracy of corner point detection is improved.
In one embodiment, in step S110, the filtering process includes at least one of: gaussian filtering, gabor filtering.
Specifically, a gaussian filtering method, a Gabor filtering method, or the like may be used to remove noise in the image to be processed, so as to improve the accuracy of corner detection of the subsequent image.
In one embodiment, in step S110, the filtering the image to be processed by using a gaussian filtering method includes:
carrying out scale processing on the image to be processed by adopting Gaussian kernel functions with different scale factors and different radiuses to obtain a filtered image:
I(x,y) Ri ＝Gaussian i (I(x,y) in )；i＝[1,2,…,N]
where i denotes the number of filtering times, σ i Denotes the ith scale factor, R i Denotes the ith radius, gaussian i Denotes the ith scale factor as σ i Radius R i Gaussian kernel function of (I, y) in Representing the image to be processed, I (x, y) Ri Representing the ith filtered image.
Specifically, the gaussian kernel function is a method for constructing a scale space for an image in image processing, and different scale factors sigma are used i Different radius R i Gaussian kernel Gaussian i And (4) performing convolution on the image to achieve scale processing on the image so as to obtain the filtered image with different scales. In the embodiment of the application, the filtering times i and the scale factor sigma are measured i Radius R i The specific value of (b) is not particularly limited, and may be arbitrarily selected by those skilled in the art according to actual needs.
Illustratively, if the maximum value N of the filtering times i is 3, the image to be processed is subjected to the third gaussian filtering, which is specifically as follows:
I(x,y) R1 ＝Gaussian 1 (I(x,y) in ),σ 1 ＝1.0,R 1 ＝r
I(x,y) R2 ＝Gaussian 2 (I(x,y) in ),σ 2 ＝2.0,R 1 ＝2r
I(x,y) R3 ＝Gaussian 3 (I(x,y) in ),σ 3 ＝4.0,R 1 ＝4r
by using three different scale factors sigma 1 、σ 2 、σ 3 And respectively processing the images to be processed to obtain three filtered images with different scales, so that the detail information of the images can be conveniently extracted subsequently according to the filtered images with different scales to obtain corresponding texture feature maps.
In an embodiment, in step S120, performing texture feature extraction on the filtered image to obtain a texture image, where the formula is as follows:
wherein, I (x, y) Detaili Representing the ith detail image; i (x, y) Detail Representing a texture image, w i Representing the ith weight value.
Specifically, a plurality of detail images are obtained according to the image to be processed and the filtered images with different scales, and then corresponding weights are configured for the plurality of detail images respectively to obtain the texture image. In the embodiment of the present application, the weighting value w i The setting is not particularly limited, and those skilled in the art can arbitrarily select the setting according to actual needs.
Illustratively, e.g. weight value w 1 ＝0.50，w 2 ＝0.50，w 3 =0.25, the plurality of detail images and texture images are as follows:
I(x,y) Detail1 ＝I(x,y) in -I(x,y) R1
I(x,y) Detail2 ＝I(x,y) R1 -I(x,y) R2
I(x,y) Detail3 ＝I(x,y) R2 -I(x,y) R3
I(x,y) Detail ＝(1-w 1 ×sgn(I(x,y) Detail1 ))×I(x,y) Detail1 +w 2 ×I(x,y) Detail2 +w 3 ×I(x,y) Detail3
in one embodiment, in step S130, the fused image I (x, y) out Comprises the following steps:
I(x,y) out ＝I(x,y) in +I(x,y) Detail
specifically, the image to be processed and the texture image are added to obtain a fused image. Fig. 3 (a) is an original image to be processed, and fig. 3 (b) is a fused image, and it can be known from comparing fig. 3 (a) and fig. 3 (b) that the texture features of the fused image are more obvious, which is beneficial to the detection of the corner points.
In one embodiment, in S140, the corner point detecting method includes at least one of: SIFT corner detection, ORB corner detection, FAST corner detection, harris corner detection and SURF corner detection.
Specifically, in the embodiment of the present application, based on the texture image, the corner detection may be performed by using a plurality of corner detection methods, such as any one of the corner detection methods of SIFT (Scale-invariant feature transform), ORB (organized FAST and Rotated BRIEF), FAST (Features from acquired Segment Test), harris, SURF (Speeded Up Robust Features), and the like.
The Harris corner detection is a point with a high enough gray scale change value in each direction in a neighborhood, and is a point with a maximum curvature value on an image edge curve, and the basic idea of the corner detection is as follows: calculating a Corner Response Function (Corner Response Function) for each pixel of the image by using a Corner detection operator, thresholding the Corner Response Function, selecting a threshold according to the actual situation, carrying out non-maximum suppression on the thresholded Corner Response Function, and acquiring a non-zero point as a Corner; and moving the window in any direction at the neighborhood detection corner point through a small sliding window, wherein if the gray values in the window are changed violently, the center of the window is the corner point.
In one embodiment, in step S140, performing corner detection on the fused image by using a FAST corner detection method based on the texture image, including:
determining a point P '(x, y) on the texture image, finding a point P (x, y) on the fused image corresponding to the point P' (x, y), the pixel of the set point P (x, y) being I P ；
In the fused image, taking a point P (x, y) as a central point and r as a radius to draw a circle, wherein the circle covers M pixels;
setting a threshold value t, if the pixels with continuous Q points in M pixels on the circle around the point P (x, y) are smaller than I P -t or greater than I P + t, the point P (x, y) is the angular point; m is more than or equal to Q.
Specifically, a point P ' (x, y) is determined on the texture image, a point P (x, y) corresponding to the point P ' (x, y) is found in the fused image, then, corner detection is performed on the fused image, for example, based on a FAST corner detection method, the point P (x, y) and 16 pixel points on a peripheral circle of the point are judged, whether the point P (x, y) is a corner point is determined, that is, whether the point P ' (x, y) is a corner point is determined, then, whether the next point in the texture image is a corner point is sequentially determined, until all corner points on the texture image are found, and the corner detection is finished. Because all the corner points are basically positioned at the texture positions, the detection time can be shortened and the detection efficiency can be improved by checking whether the texture points are the corner points.
For example, if a FAST corner detection method is used for corner detection, the FAST corner detection method is a corner detection method based on a template and machine learning, and has a high calculation speed and high accuracy. The FAST method mainly considers 16 pixels on a circular window near a pixel point, as shown in fig. 4 below, p is a central pixel point, and a point pixel marked by a white frame is a point that needs to be considered. The FAST corner is defined as: if a certain number of pixels around a pixel have different pixel values from the pixel value of the point, the pixel is regarded as an angular point, and the specific angular point detection comprises the following steps:
a point P of the image is selected, the pixel of the point P is represented as I P 。
A circle is drawn with r as the radius, covering M pixels around point P, as shown in fig. 4 below: r =3,m =16.
Setting a threshold value t, if the pixels of continuous Q points in 16 pixel points around the P point are smaller than I P -t or greater than I P + t, the point is considered as a corner point. The value of the threshold t is different in different scenes, and if the threshold t is 0, the pixel with continuous Q points is larger than or smaller than I P The point is a corner point. In the embodiment of the application, Q is usually 12 or 9, and experiments show that the corner detection performance is most stable, the speed is faster, and the effect is also good when Q is 12, and experiments also show that the corner detection performance is better when Q is 9. The specific corner detection formula is as follows:
wherein, I P The pixel value, I, representing the center point P p→x Pixel points at the surrounding circular template x representing point P; when the pixel point I of the surrounding circular template x of the point P p→x Is less than I P T, then the pixel belongs to dark, S p→x = d; other two cases are shown separatelyBright and similar, therefore, the circular area around the central point P is divided into three types d, s and b, and the number of times that d or b occurs is counted to be greater than Q (Q takes 12 or 9), and the point is considered as a candidate corner point.
In a preferred embodiment, in step S140, performing corner detection on the fused image by using an improved FAST corner detection method based on the texture image, including:
determining a point P '(x, y) on the texture image, finding a point P (x, y) on the fused image corresponding to the point P' (x, y), the pixel of the set point P (x, y) being I P ；
In the fused image, a circle is drawn by taking a point P (x, y) as a central point and r as a radius, and M pixels are covered on the circle;
setting a threshold value t, selecting four points in a mutually vertical direction from M pixels on a circle around the point P (x, y), and if the pixel values of at least three of the four points are less than I P -t or greater than I P + t, the point P (x, y) is the candidate angular point, and the judgment is repeated until the pixels with continuous Q points in M pixels on the circle around the point P (x, y) are smaller than I P -t or greater than I P + t, the point P (x, y) is the angular point; m is more than or equal to Q.
Specifically, in the above segmentation test, in order to increase the speed, the pixel points do not need to be compared one by one, the pixel values of four points in the horizontal direction and the vertical direction on the circle around the central point P and the pixel value of the central point, such as the pixel values of the points 1, 5, 9, and 13, may be first compared, and whether the pixel values of the four points satisfy 3 or more than 3 points smaller than I is first determined P -t or greater than I P + t, if not, directly skipping; if so, considering the point as a candidate corner point, and continuing to use the method, and if 12 points in the 16 pixel points meet the condition, considering the point as a corner point; the corner detection method further accelerates the corner detection rate.
It should be noted that while the operations of the method of the present invention are depicted in the drawings in a particular order, this does not require or imply that the operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Rather, the steps depicted in the flowcharts may change order of execution.
In a second aspect of the embodiment of the present application, referring to the exemplary structural block diagram of the texture-feature-based corner detection system shown in fig. 5, a texture-feature-based corner detection system 200 of the present embodiment includes:
the texture extracting unit 220 is configured to perform texture feature extraction on the image to be processed to obtain a texture image;
an image fusion unit 230, configured to fuse the texture image and the image to be processed to obtain a fused image;
and a corner detection unit 240, configured to perform corner detection on the fused image based on the texture image.
Specifically, the system provided by the embodiment of the application separates the background of the image to be processed from the texture to obtain the texture image, performs corner detection based on the texture features of the image, determines whether the texture features are corners, and can better reflect the performance of the corners at the selected pixel positions, thereby greatly saving calculation power and time.
In one embodiment, as shown in fig. 6, the system further comprises:
an image filtering unit 210, configured to perform filtering processing on the image to be processed to obtain a filtered image.
Specifically, the image filtering unit 210 may filter the image to be processed to remove noise in the image, so as to avoid mistaking noise points in the image as corner points, and improve accuracy of corner point detection. The image filtering unit 210 may be configured to perform a gaussian filtering method or a Gabor filtering method.
In an embodiment, the image filtering unit 210 is further configured to perform scale processing on the image to be processed by using gaussian kernel functions with different scale factors and different radii, so as to obtain a filtered image.
Specifically, the image filtering unit 210 performs filtering processing on the image to be processed by using a gaussian filtering method, and the specific gaussian filtering method is as described above, which is not described in detail in this embodiment of the present application.
In an embodiment, the texture extracting unit 220 is configured to obtain a plurality of detail images according to the image to be processed and the filtered images with different scales, and configure corresponding weights for the plurality of detail images respectively to obtain the texture image.
Specifically, the texture extracting unit 220 is configured to process the image to be processed and the filtered images with different scales to obtain a texture image, where the specific texture image extracting method is as described above.
In an embodiment, the image fusion unit 230 is configured to add the texture image and the image to be processed to obtain a fused image.
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.
Specifically, the detection method performed by the corner detection unit 240 is as described above, and the embodiments of the present application are not described in detail.
In a third aspect of the embodiments of the present application, an electronic device is provided, where an internal structure diagram of the electronic device may be as shown in fig. 7. The electronic device comprises a processor, a memory, a communication interface, a display screen and an input device which are connected through a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic equipment comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the electronic device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, near Field Communication (NFC) or other technologies. The computer program is executed by a processor to implement a method of corner detection based on texture features. The display screen of the electronic equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the electronic equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 7 is a block diagram of only a portion of the architecture associated with the subject application, and does not constitute a limitation on the electronic devices to which the subject application may be applied, and that a particular electronic device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, the texture feature-based corner detection system 200 provided in the present application may be implemented in the form of a computer program, which may be run on an electronic device as shown in fig. 7. The memory of the electronic device may store various program modules constituting the texture feature-based corner detection system 200, such as an image filtering unit 210, a texture extraction unit 220, an image fusion unit 230, a corner detection unit 240, and the like shown in fig. 6. The program modules constitute computer programs that cause the processor to execute the steps of the texture feature-based corner detection method according to the embodiments of the present application described in the present specification.
In one embodiment, an electronic device is provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps of the texture feature-based corner detection method when executing the computer program.
In an embodiment, a computer-readable storage medium is also provided, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, databases, or other media used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM is available in many forms, such as Static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), and the like.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A corner detection method based on texture features is characterized by comprising the following steps:
extracting texture features of the image to be processed to obtain a texture image;
fusing the texture image and the image to be processed to obtain a fused image;
and performing corner point detection on the fused image based on the texture image.
2. The corner detection method based on texture features of claim 1, wherein before the texture feature extraction of the image to be processed, the method further comprises:
and filtering the image to be processed to obtain a filtered image.
3. The texture feature-based corner detection method according to claim 2, wherein the filtering process comprises at least one of: gaussian filtering, gabor filtering.
4. The method for detecting angular points based on texture features according to claim 3, wherein the filtering the image to be processed by using the Gaussian filtering method comprises:
carrying out scale processing on the image to be processed by adopting Gaussian kernel functions with different scale factors and different radiuses to obtain a filtered image:
I(x,y) Ri ＝Gaussian i (I(x,y) in )；i＝[1,2,…,N]
wherein i represents the number of filtering times, gaussian i Denotes the ith scale factor as σ i Radius R i Gaussian kernel function of (I, y) in Representing the image to be processed, I (x, y) Ri Representing the ith filtered image.
5. The method according to claim 4, wherein the filtered image is subjected to texture feature extraction to obtain a texture image, and the formula is as follows:
wherein, I (x, y) Detaili Representing the ith detail image; i (x, y) Detail Representing a texture image, w i Representing the ith weight value.
6. The texture feature-based corner detection method according to claim 5, wherein the corner detection method is characterized in thatThen, the fused image I (x, y) out Comprises the following steps:
I(x,y) out ＝I(x,y) in +I(x,y) Detail 。
7. the texture feature-based corner detection method according to any one of claims 1 to 6, wherein the corner detection method comprises at least one of: SIFT corner detection, ORB corner detection, FAST corner detection, harris corner detection and SURF corner detection.
8. A texture feature-based corner detection system, comprising:
the texture extraction unit is used for extracting texture features of the image to be processed to obtain a texture image;
the image fusion unit is used for fusing the texture image and the image to be processed to obtain a fused image;
and the corner detection unit is used for detecting the corner of the fused image based on the texture image.
9. An electronic device comprising a memory and a processor, the memory storing a computer program, wherein the processor, when executing the computer program, performs the steps of the texture feature based corner detection method according to any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the texture feature based corner detection method according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211178236.5A CN115661036A (en) | 2022-09-26 | 2022-09-26 | Corner point detection method and system based on texture features, electronic device and medium |
| PCT/CN2022/141469 WO2024066090A1 (en) | 2022-09-26 | 2022-12-23 | Corner detection method and system based on texture features, electronic device, and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211178236.5A CN115661036A (en) | 2022-09-26 | 2022-09-26 | Corner point detection method and system based on texture features, electronic device and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115661036A true CN115661036A (en) | 2023-01-31 |
Family
ID=84985341
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211178236.5A Pending CN115661036A (en) | 2022-09-26 | 2022-09-26 | Corner point detection method and system based on texture features, electronic device and medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115661036A (en) |
| WO (1) | WO2024066090A1 (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913463B (en) * | 2016-04-11 | 2018-12-25 | 中南大学 | A kind of texture based on location-prior-color characteristic overall situation conspicuousness detection method |
| CN111340752A (en) * | 2019-12-04 | 2020-06-26 | 京东方科技集团股份有限公司 | Screen detection method and device, electronic equipment and computer readable storage medium |
| AU2020100199A4 (en) * | 2020-02-08 | 2020-03-19 | Cao, Sihua MR | A medical image fusion method based on two-layer decomposition and improved spatial frequency |
| CN111784642B (en) * | 2020-06-10 | 2021-12-28 | 中铁四局集团有限公司 | Image processing method, target recognition model training method and target recognition method |
| CN114449181B (en) * | 2020-11-05 | 2023-04-21 | 晶晨半导体(上海)股份有限公司 | Image and video processing method and system, data processing device and medium |
| CN114998162A (en) * | 2022-06-23 | 2022-09-02 | 上海闻泰信息技术有限公司 | Moving object detection method and device, terminal equipment and storage medium |
-
2022
- 2022-09-26 CN CN202211178236.5A patent/CN115661036A/en active Pending
- 2022-12-23 WO PCT/CN2022/141469 patent/WO2024066090A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024066090A1 (en) | 2024-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108875723B (en) | Object detection method, device and system and storage medium | |
| CN107945111B (en) | Image stitching method based on SURF (speeded up robust features) feature extraction and CS-LBP (local binary Pattern) descriptor | |
| US9240038B2 (en) | Method and apparatus for acquiring weight coefficient of digital filter | |
| CN114155365B (en) | Model training method, image processing method and related device | |
| CN110503704B (en) | Method and device for constructing three-dimensional graph and electronic equipment | |
| CN114359591A (en) | Self-adaptive image matching algorithm with edge features fused | |
| CN111951283A (en) | Medical image identification method and system based on deep learning | |
| CN113781406A (en) | Scratch detection method and device for electronic component and computer equipment | |
| CN116030237A (en) | Industrial defect detection method and device, electronic equipment and storage medium | |
| CN110796250A (en) | Convolution processing method and system applied to convolutional neural network and related components | |
| CN108960247B (en) | Image significance detection method and device and electronic equipment | |
| CN111199197B (en) | Image extraction method and processing equipment for face recognition | |
| CN113128554A (en) | Target positioning method, system, device and medium based on template matching | |
| CN112634288A (en) | Equipment area image segmentation method and device | |
| CN114359665A (en) | Training method and device of full-task face recognition model and face recognition method | |
| CN110516731B (en) | Visual odometer feature point detection method and system based on deep learning | |
| CN113129298B (en) | Method for identifying definition of text image | |
| CN111382638A (en) | Image detection method, device, equipment and storage medium | |
| CN116580028B (en) | Object surface defect detection method, device, equipment and storage medium | |
| CN112734747A (en) | Target detection method and device, electronic equipment and storage medium | |
| CN115661036A (en) | Corner point detection method and system based on texture features, electronic device and medium | |
| CN111753722B (en) | Fingerprint identification method and device based on feature point type | |
| CN109815791B (en) | Blood vessel-based identity recognition method and device | |
| CN109977937B (en) | Image processing method, device and equipment | |
| CN113129227A (en) | Image processing method, image processing device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |