CN112489065B - Chessboard standard point sub-pixel extraction method - Google Patents
Chessboard standard point sub-pixel extraction method Download PDFInfo
- Publication number
- CN112489065B CN112489065B CN202011358598.3A CN202011358598A CN112489065B CN 112489065 B CN112489065 B CN 112489065B CN 202011358598 A CN202011358598 A CN 202011358598A CN 112489065 B CN112489065 B CN 112489065B
- Authority
- CN
- China
- Prior art keywords
- point
- checkerboard
- pixel
- neighborhood image
- extraction method
- 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.)
- Active
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 30
- 238000005070 sampling Methods 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000000034 method Methods 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 12
- 238000003708 edge detection Methods 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30244—Camera pose
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 invention belongs to the technical field of machine vision, and particularly relates to a checkerboard standard point sub-pixel extraction method, which comprises the steps of extracting a pixel-level checkerboard standard point to (x) 0 ，y 0 ) Obtaining a neighborhood image In within a sampling radius R for the center 0 Iterating to obtain k neighborhood images, traversing the field image In k‑1 Extracting points smaller than an error threshold value as checkerboard mark points of sub-pixel positioning. The invention solves the problems of inaccurate positioning and low positioning precision of the checkerboard calibration points, effectively reduces the calibration error and effectively improves the calibration extraction accuracy and precision.
Description
Technical Field
The invention belongs to the technical field of machine vision, and particularly relates to a checkerboard mark point sub-pixel extraction method.
Background
In the field of machine vision, a checkerboard calibration plate calibration method can be used for parameter calibration of an industrial camera, wherein the neighborhood of checkerboard calibration points can be divided into an edge area and a solid color area.
However, the inventor has found that in an actual calibration image, the checkerboard calibration plate is easily interfered by ambient light or the quality of the calibration plate itself, so that the problem of inaccurate or failed positioning of the checkerboard calibration points occurs. Meanwhile, the conventional method adopts a Gaussian weight distribution method of center distance to extract the checkerboard calibration points, the pure color areas of the checkerboard calibration points are easily influenced by ambient light, the calibration precision of the obtained checkerboard calibration point coordinates is low, moreover, only the checkerboard calibration point coordinates with pixel level precision can be obtained, and sub-pixel extraction of the checkerboard calibration points cannot be realized.
For this reason, a new extraction method is needed to solve the above problems.
Disclosure of Invention
The invention aims at: aiming at the defects of the prior art, the chessboard marking point sub-pixel extraction method can remarkably solve the problems of inaccurate positioning and low positioning precision of the chessboard marking point, effectively reduces the marking error and remarkably improves the accuracy and precision of the marking extraction.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a checkerboard mark point sub-pixel extraction method comprises the following steps:
s1, extracting a checkerboard calibration point of a pixel level from an image of a checkerboard calibration plate, and marking the initial sitting of the calibration point as (x) 0 ，y 0 ) In (x) 0 ，y 0 ) Obtaining a neighborhood image In within a sampling radius R for the center 0 ；
S2, aiming at the neighborhood image In 0 Binarizing, and extracting the neighborhood image In by using an edge detection algorithm 0 Is subjected to hough transformation to obtain direction vectors (vx) 1 ，vy 1 ) And (vx) 2 ，vy 2 ) Wherein, (vx) 1 ，vy 1 ) Vector of first straight line representing intersecting straight line, (vx) 2 ，vy 2 ) The vector of a second straight line representing the crossed straight line is iterated to obtain k neighborhood images, wherein k is more than or equal to 1;
s3, assuming that the iteration is carried out until the kth step, and the coordinates of the checkerboard mark points in the kth neighborhood image are (x) k-1 ，y k-1 ) Both of the two intersecting straight lines of S2 cross points (x k-1 ，y k-1 ) In (x) k-1 ，y k-1 ) Obtaining a neighborhood image In within a sampling radius R for the center k-1 The neighborhood image In k-1 N pixels, for the neighborhood image In k-1 The coordinates of the ith pixel point in (b) are denoted as (nx i ，ny i ) I is less than or equal to n, and calculating the neighborhood image In k-1 The minimum distance dm between the ith pixel point of (2) and the two intersecting straight lines of S2 i ；
S4, calculating the neighborhood image In k-1 The weight w of the ith pixel point in (b) i At right angles to the planeGradient gx is calculated in the X-direction and Y-direction of the coordinate system i And gy i Traversing the domain image In k-1 N pixels of (a) and a coordinate point (x k ，y k ) For the checkerboard mark points to be extracted, apply the formula
s5, calculating a point (x) k ，y k ) And point (x) k-1 ，y k-1 ) Error e of (2) k Setting an error threshold e t If e k <e t Points (x) k ，y k ) Marked as checkerboard mark points for sub-pixel positioning.
Further, the hough transform in the step S2 determines the shape of the object by voting on the parameter space, and determines the shape feature of the object by accumulating the local maxima in the space.
Further, in the S3, the minimum distance dm i The calculation process of (1) is dm i ＝min(vx 1 ·(nx i -x k-1 )-vy 1 ·(ny i -y k-1 ),vx 2 ·(nx i -x k-1 )-vy 2 ·(ny i -y k-1 ) And) wherein vx 1 Vector vy representing the first straight line of the intersecting straight line in the S2 in the X direction of the plane rectangular coordinate system 1 A vector vx representing the Y-direction vector of the first straight line of the intersecting straight lines in the S2 step in the plane rectangular coordinate system 2 Vector vy representing the X direction of the second straight line of the intersecting straight line in the S2 step in the plane rectangular coordinate system 2 A vector, nx, representing the Y direction vector of the second straight line of the intersecting straight lines in the step S2 in the plane rectangular coordinate system i Representing the neighborhood image In k-1 The abscissa, ny, of the ith pixel point in (1) i Representing the neighborhood image In k-1 The ordinate, x of the ith pixel point in (a) k-1 Representing the abscissa, y, of the checkerboard mark points in the kth neighborhood image k-1 Representing the ordinate of the checkerboard mark point in the kth neighborhood image, the first and second straight lines of the intersecting straight lines in the S2 step both cross points (x k-1 ，y k-1 )。
Further, in the S4, the weight w of the ith pixel point i The calculation process of (1) is that
Wherein said dm i Representing neighborhood image In k-1 The minimum distance from the ith pixel point of (2) to the two intersecting straight lines of S, and R represents the value of the sampling radius.
Further, in the S4, the gradient gx i And the gradient gy i The calculation process of (1) is that
Further, in said S5, a point (x k ，y k ) And point (x) k-1 ，y k-1 ) Error e of (2) k The calculation process of (1) is that
Further, in the step S5, the error threshold e t The value of (2) is 0.0001-0.1, or 0.001-0.01.
Further, in S4, when i=1, the values of pa, pb, pc, pd and pe are both 0.
Further, in the step S2, the neighborhood image In may be extracted by Sobel operator, prewitt operator, roberts operator or Canny operator 0 Is a boundary point of the frame.
Further, in the step S2, the upper limit value of k is 10 to 1000, and the neighborhood image In 0 The binarization process comprises the steps of reading image data, obtaining gray values of pixel points in an image, obtaining the binary values of the pixels according to a threshold value, reassigning color components of the pixel points, and obtaining a binary image.
Further, the sampling radius R may be 10% to 50% of the side length of each square pixel, and the sampling radius R may be 20%, 30% and 40% of the side length of each square pixel, where when the value of R is larger, the calculation speed is slower, but the calculation result is more accurate, and the value of R may be different according to the checkerboard of different sizes, and the value of R may be set according to actual needs.
The invention has the beneficial effects that: according to the extraction method, binarization, edge extraction and Hough transformation are carried out on the neighborhood image of the checkerboard mark point, so that the direction vector of two crossed straight lines of the checkerboard mark point is obtained, furthermore, the pixel points participating in calculation are subjected to the iterative calculation of the sub-pixel coordinates of the checkerboard mark point by adopting Gaussian weight distribution of the nearest distance from the crossed straight lines, and the influence of solid-color region interference points in the neighborhood image of the checkerboard mark point on an extraction result is avoided, and the influence of pixel gradient generated by ambient light on the extraction result is avoided, so that the extraction precision is effectively improved.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is an image of a checkerboard calibration plate of the present invention.
Fig. 3 is a schematic view of two intersecting straight lines obtained by the present invention.
Fig. 4 is a schematic diagram of two intersecting straight lines in a rectangular planar coordinate system in step S2 of the present invention.
Detailed Description
As a particular component is referred to by some of the terms used in the description and claims, it should be understood by those skilled in the art that a manufacturer may refer to the same component by different terms. The description and claims do not take the form of an element differentiated by name, but rather by functionality. As used throughout the specification and claims, the word "comprise" is an open-ended term, and thus should be interpreted to mean "include, but not limited to. By "substantially" is meant that within an acceptable error range, a person skilled in the art can solve the technical problem within a certain error range, substantially achieving the technical effect.
In the description of the present invention, it should be understood that the directions or positional relationships indicated by the terms "upper", "lower", "front", "rear", "left", "right", "horizontal", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
The present invention will be described in further detail below with reference to fig. 1 to 4 and specific examples, but is not limited thereto.
A checkerboard mark point sub-pixel extraction method comprises the following steps:
s1, extracting a checkerboard calibration point of a pixel level from an image of a checkerboard calibration plate, and marking the initial sitting of the calibration point as (x) 0 ，y 0 ) In (x) 0 ，y 0 ) Obtaining a neighborhood image In within a sampling radius R for the center 0 ；
S2, aiming at neighborhood image In 0 Binarization is carried out, and a canny edge detection algorithm is used for extracting a neighborhood image In 0 Is subjected to hough transformation to obtain direction vectors (vx) 1 ，vy 1 ) And (vx) 2 ，vy 2 ) Iterating to obtain k neighborhood images, wherein k is more than or equal to 5 and less than or equal to 50;
s3, assuming that the iteration is carried out until the kth step, and the coordinates of the checkerboard mark points in the kth neighborhood image are (x) k-1 ，y k-1 ) Both intersecting straight lines of step S2 pass through the point (x k-1 ，y k-1 ) In (x) k-1 ，y k-1 ) Obtaining a neighborhood image In within a sampling radius R for the center k-1 Neighborhood image In k-1 N pixels, for the neighborhood image In k-1 The coordinates of the ith pixel point in (b) are denoted as (nx i ，ny i ) I is less than or equal to n, and the following formula is applied
dm i ＝min(vx 1 ·(nx i -x k-1 )-vy 1 ·(ny i -y k-1 ),vx 2 ·(nx i -x k-1 )-vy 2 ·(ny i -y k-1 ))
Calculation ofNeighborhood image In k-1 Minimum distance dm between ith pixel point in (1) and two intersecting straight lines of S2 i Wherein dm i Reference is made to fig. 4 for a schematic representation of the values of (2);
s4, calculating neighborhood image In k-1 The weight w of the ith pixel point in (b) i ，
Wherein the weight w i Is a gaussian weight distribution model in which pixels closer to a center point are weighted higher and gradients gx are calculated in the X and Y directions of a planar rectangular coordinate system i And gy i The calculation formula is
gx i ＝g(nx i +1,ny i )-g(nx i -1,ny i )
gy i ＝g(nx i ,ny i +1)-g(nx i ,ny i -1)，
Wherein g (nx) i ，ny i ) Representing neighborhood image In k-1 The gray value of the i-th pixel point in (c),
then, the domain image In is traversed k-1 N pixels of (a) and a coordinate point (x k ，y k ) For the checkerboard mark points to be extracted, apply the formula
wherein, when i=1, the values of pa, pb, pc, pd and pe are both 0;
s5, applying a formula
Calculation Point (x) k ，y k ) And point (x) k-1 ，y k-1 ) Error e of (2) k Setting an error threshold e t ，0.001≤e t Less than or equal to 0.01, if e k <e t Points (x) k ，y k ) Marked as checkerboard mark points for sub-pixel positioning.
In addition, in the step S2, an edge detection algorithm, namely a Canny operator, may be used for edge detection, and the detection process may include the following steps:
(1) Using a gaussian filter to smooth the image and filter out noise;
(2) Calculating the gradient strength and direction of each pixel point in the image;
(3) Non-maximum (Non-Maximum Suppression) suppression is applied to eliminate spurious responses from edge detection;
(4) Applying Double-Threshold (Double-Threshold) detection to determine true and potential edges;
(5) Edge detection is finally accomplished by suppressing isolated weak edges and extracting all contours.
Moreover, as can be seen from table 1, the calibration error of the extraction method of the present invention is smaller than that of the conventional extraction method, thereby effectively reducing the calibration error.
| General method (Pixel) | The patent method (pixel) |
| 0.1975 | 0.1904 |
TABLE 1
Obviously, the extraction method can avoid the influence of the interference points of the solid color region in the neighborhood image of the checkerboard mark points on the extraction result, thereby effectively improving the extraction precision.
Variations and modifications of the above embodiments will occur to those skilled in the art to which the invention pertains from the foregoing disclosure and teachings. Therefore, the present invention is not limited to the above-described embodiments, but is intended to be capable of modification, substitution or variation in light thereof, which will be apparent to those skilled in the art in light of the present teachings. In addition, although specific terms are used in the present specification, these terms are for convenience of description only and do not limit the present invention in any way.
Claims (9)
1. The checkerboard mark point sub-pixel extraction method is characterized by comprising the following steps of:
s1, extracting a checkerboard calibration point of a pixel level from an image of a checkerboard calibration plate, and marking the initial sitting of the calibration point as (x) 0 ，y 0 ) In (x) 0 ，y 0 ) Obtaining a neighborhood image In within a sampling radius R for the center 0 ；
S2, aiming at the neighborhood image In 0 Binarizing, and extracting the neighborhood image In by using an edge detection algorithm 0 Is subjected to Hough transformation from the extracted edge pointsTo obtain the direction vector (vx) of two crossed straight lines 1 ，vy 1 ) And (vx) 2 ，vy 2 ) Iterating to obtain k neighborhood images, wherein k is more than or equal to 1;
s3, the coordinates of the checkerboard mark points in the kth neighborhood image are (x) k-1 ，y k-1 ) Both of the two intersecting straight lines of S2 cross points (x k-1 ，y k-1 ) In (x) k-1 ，y k-1 ) Obtaining a neighborhood image In within a sampling radius R for the center k-1 The neighborhood image In k-1 N pixels, for the neighborhood image In k-1 The coordinates of the ith pixel point in (b) are denoted as (nx i ，ny i ) I is less than or equal to n, and calculating the neighborhood image In k-1 The minimum distance dm between the ith pixel point of (2) and the two intersecting straight lines of S2 i ；
S4, calculating the neighborhood image In k-1 The weight w of the ith pixel point in (b) i Calculating gradient gx in X direction and Y direction of plane rectangular coordinate system i And gy i Traversing the neighborhood image In k-1 N pixels of (a) and a coordinate point (x k ，y k ) For the checkerboard mark points to be extracted, apply the formula
wherein pa, pb, pc, pd and pe are both custom parameters,
s5, calculating a point (x) k ，y k ) And point (x) k-1 ，y k-1 ) Error e of (2) k Setting an error threshold e t If e k <e t Points (x) k ，y k ) Marked as checkerboard mark points for sub-pixel positioning.
2. The checkerboard mark point sub-pixel extraction method of claim 1, wherein: in said S3, said minimum distance dm i The calculation process of (1) is that
dm i ＝min(vx 1 ·(nx i -x k-1 )-vy 1 ·(ny i -y k-1 ),vx 2 ·(nx i -x k-1 )-vy 2 ·(ny i -y k-1 ))。
3. The checkerboard mark point sub-pixel extraction method of claim 1, wherein: in the S4, the neighborhood image In k-1 The weight w of the ith pixel point in (b) i The calculation process of (1) is that
Wherein said dm i Representing neighborhood image In k-1 The minimum distance from the ith pixel point of (2) to the two intersecting straight lines of S, and R represents the value of the sampling radius.
4. The checkerboard mark point sub-pixel extraction method of claim 1, wherein: in the S4, the gradient gX i And the gradient gy i The calculation process of (1) is that
5. The checkerboard mark point sub-pixel extraction method of claim 1, wherein: in said S5, the point (x k ，y k ) And point (x) k-1 ，y k-1 ) Error e of (2) k The calculation process of (1) is that
6. The checkerboard mark point sub-pixel extraction method of claim 1, wherein: in the S5, the error threshold e t The value range of (2) is 0.0001-0.1.
7. The checkerboard mark point sub-pixel extraction method of claim 1, wherein: in S4, when i=1, the values of pa, pb, pc, pd and pe are both 0.
8. The checkerboard mark point sub-pixel extraction method of claim 1, wherein: in the S2, the neighborhood image In can be extracted by adopting a Sobel operator, a Prewitt operator, a Roberts operator or a Canny operator 0 Is a boundary point of the frame.
9. The checkerboard mark point sub-pixel extraction method of claim 1, wherein: in S2, the upper limit value of k is 10 to 1000.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011358598.3A CN112489065B (en) | 2020-11-27 | 2020-11-27 | Chessboard standard point sub-pixel extraction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011358598.3A CN112489065B (en) | 2020-11-27 | 2020-11-27 | Chessboard standard point sub-pixel extraction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112489065A CN112489065A (en) | 2021-03-12 |
| CN112489065B true CN112489065B (en) | 2023-07-07 |
Family
ID=74936335
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011358598.3A Active CN112489065B (en) | 2020-11-27 | 2020-11-27 | Chessboard standard point sub-pixel extraction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112489065B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113674342B (en) * | 2021-08-30 | 2022-02-11 | 民航成都物流技术有限公司 | Method for quickly identifying and positioning luggage basket based on area-array 3D camera |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101261115A (en) * | 2008-04-24 | 2008-09-10 | 吉林大学 | Spatial circular geometric parameter binocular stereo vision measurement method |
| CN103345755A (en) * | 2013-07-11 | 2013-10-09 | 北京理工大学 | Chessboard angular point sub-pixel extraction method based on Harris operator |
| WO2018018987A1 (en) * | 2016-07-29 | 2018-02-01 | 深圳市未来媒体技术研究院 | Calibration pre-processing method for light field camera |
-
2020
- 2020-11-27 CN CN202011358598.3A patent/CN112489065B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101261115A (en) * | 2008-04-24 | 2008-09-10 | 吉林大学 | Spatial circular geometric parameter binocular stereo vision measurement method |
| CN103345755A (en) * | 2013-07-11 | 2013-10-09 | 北京理工大学 | Chessboard angular point sub-pixel extraction method based on Harris operator |
| WO2018018987A1 (en) * | 2016-07-29 | 2018-02-01 | 深圳市未来媒体技术研究院 | Calibration pre-processing method for light field camera |
Non-Patent Citations (1)
| Title |
|---|
| 自适应的Harris棋盘格角点检测算法;侯建辉;林意;;计算机工程与设计(第20期);167-169+227 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112489065A (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112819772B (en) | High-precision rapid pattern detection and recognition method | |
| Hao et al. | Improved self-adaptive edge detection method based on Canny | |
| CN107481284A (en) | Method, apparatus, terminal and the system of target tracking path accuracy measurement | |
| CN105913396A (en) | Noise estimation-based image edge preservation mixed de-noising method | |
| CN110969656B (en) | Detection method based on laser beam spot size of airborne equipment | |
| CN109886935A (en) | A kind of road face foreign matter detecting method based on deep learning | |
| CN111489389A (en) | Light spot center detection method | |
| CN112489065B (en) | Chessboard standard point sub-pixel extraction method | |
| CN114612410A (en) | Novel clothing detects device | |
| CN116385495A (en) | Moving target closed-loop detection method of infrared video under dynamic background | |
| CN113781413B (en) | Electrolytic capacitor positioning method based on Hough gradient method | |
| CN116503462A (en) | Method and system for quickly extracting circle center of circular spot | |
| CN117764983A (en) | Visual detection method for binocular identification of intelligent manufacturing production line | |
| CN106530485A (en) | Image boundary obtaining method and apparatus | |
| CN111951178B (en) | Image processing method and device for remarkably improving image quality and electronic equipment | |
| CN117853510A (en) | Canny edge detection method based on bilateral filtering and self-adaptive threshold | |
| CN115775278B (en) | Element identification positioning method and system containing local feature constraint and storage medium | |
| CN106127147B (en) | A kind of face depth texture restorative procedure based on three-dimensional data | |
| CN116958120A (en) | Weak target signal extraction method based on gradient distribution characteristics | |
| CN113592953B (en) | Binocular non-cooperative target pose measurement method based on feature point set | |
| CN110599510A (en) | Picture feature extraction method | |
| CN111667429B (en) | Target positioning correction method for inspection robot | |
| CN111626180B (en) | Lane line detection method and device based on polarization imaging | |
| CN109272540B (en) | SFR automatic extraction and analysis method of image of graphic card | |
| CN117495863B (en) | Vision-assisted triode packaging quality detection method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |