CN113012181B - Novel quasi-circular detection method based on Hough transformation - Google Patents
Novel quasi-circular detection method based on Hough transformation Download PDFInfo
- Publication number
- CN113012181B CN113012181B CN202110294720.3A CN202110294720A CN113012181B CN 113012181 B CN113012181 B CN 113012181B CN 202110294720 A CN202110294720 A CN 202110294720A CN 113012181 B CN113012181 B CN 113012181B
- Authority
- CN
- China
- Prior art keywords
- circle
- edge
- quasi
- points
- circular
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 51
- 230000009466 transformation Effects 0.000 title claims abstract description 15
- 238000003708 edge detection Methods 0.000 claims description 19
- 238000000034 method Methods 0.000 claims description 15
- 238000001914 filtration Methods 0.000 claims description 7
- 238000009499 grossing Methods 0.000 claims description 6
- 230000001629 suppression Effects 0.000 claims description 6
- 238000011426 transformation method Methods 0.000 claims description 6
- 241001061260 Emmelichthys struhsakeri Species 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
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
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a novel quasi-circular detection method based on Hough transformation, which combines Hough transformation with a quasi-circular detection algorithm based on a circumferential angle and a quasi-circular detection algorithm based on a circular radius respectively, judges quasi-circular in a one-dimensional image, has high running speed, small occupied memory and higher detection precision under the condition of higher image definition, and has higher practical value and stronger universal applicability.
Description
Technical Field
The invention relates to the field of image recognition, in particular to a novel quasi-circular detection method based on Hough transformation.
Background
At present, a lot of targets need to perform quick and accurate quasi-circular detection first, so that quick and accurate quasi-circular detection from a picture is a necessary research problem, but under the condition that the picture data volume is increased, all existing circular or elliptical detection methods have problems in different aspects.
Among the various algorithms commonly used are classical hough, random hough and generalized hough. The learner uses the characteristic of the closed boundary of the ellipse to provide a method for efficiently detecting the ellipse, proposes the concept of the ellipse boundary chain code to detect and track the edge of the ellipse, uses filtering to eliminate noise and non-closed data to enable the edge detection to be clearer so as to form the ellipse boundary chain code, and searches dual points on the chain code to carry out Hough transformation, thereby accurately detecting the ellipse. But the algorithm has a time complexity of O (n×n) and a slow running speed. Shang Lu it is proposed that starting from the arc length of an ellipse, the general equation and parameters of the ellipse are determined by the position information and gradient information of the edge points of the same arc length, and the effectiveness and detection time of the algorithm are superior to those of the general detection algorithm. But the recognition accuracy of this algorithm is lower for non-standard ellipses.
The invention combines the specific characteristics of the quasi-circular shape, applies the geometric concept to carry out gray conversion and binarization on the image to be identified, sequentially obtains the edges of the image, discards scattered points to form the edges of the graph, and besides, carries out the extraction of quasi-circular parameters by using Hough transformation to obtain the center of the quasi-circular shape.
Disclosure of Invention
In order to overcome the defects in the prior art, the running speed is low, and the success rate of detection similar to a circle is low.
In order to achieve the above object, the technical scheme adopted for solving the technical problems is as follows:
the invention discloses a novel quasi-circular detection method based on Hough transformation, which is combined with a quasi-circular detection method based on a circumferential angle, and comprises the following steps of:
step 1: the method comprises the steps that the circle center of a similar circle is acquired, the acquired image boundary points are required to be filtered to acquire a continuous boundary, the circle center of the similar circle is assumed to be an O point, a horizontal scanning line is established on a plane where the image is located, the edge of the similar circle is scanned downwards in sequence, in one-dimensional space, a Hough transformation method is adopted for midpoint counting, and the midpoint corresponding to the maximum counting value can be regarded as the circle center O;
step 2: obtaining a quasi-circle radius, finding out the outline of the graph through edge detection, traversing each point on the outline in sequence, carrying out numerical comparison to obtain two points at the farthest distance on the outline, taking any point except the two points on the circle, and taking the connecting line of the two points at the farthest distance as the diameter of the quasi-circle;
further, the edge detection step in step 2 is as follows:
step 21: removing noise by using Gaussian filtering to achieve the purpose of smoothing the image;
step 22: searching the intensity gradient of the circular boundary, namely dividing the image according to different pixel values;
step 23: tracking edge points along the edge direction by using a non-maximum suppression technology to eliminate edge false detection;
step 24: determining possible boundaries by using a double-threshold method, and drawing the boundaries;
step 3: judging whether the angle range of the circumferential angle of the diameter is 80-100 degrees, if so, drawing the edge and giving a center point O.
The invention also discloses a novel quasi-circular detection method based on Hough transformation, which is combined with the quasi-circular detection method based on the circular radius, and comprises the following steps:
step A: the method comprises the steps that the circle center of a similar circle is acquired, the acquired image boundary points are required to be filtered to acquire a continuous boundary, the circle center of the similar circle is assumed to be an O point, a horizontal scanning line is established on a plane where the image is located, the edge of the similar circle is scanned downwards in sequence, in one-dimensional space, a Hough transformation method is adopted for midpoint counting, and the midpoint corresponding to the maximum counting value can be regarded as the circle center O;
and (B) step (B): acquiring a quasi-circle radius, identifying the image contour through edge detection, traversing points on the contour in sequence to obtain two points with the farthest distance on the contour, and assuming that a midpoint O of the AB is a circle center, wherein the distance between the two points can be assumed to be the diameter;
further, the edge detection step in step B is as follows:
step B1: removing noise by using Gaussian filtering to achieve the purpose of smoothing the image;
step B2: searching the intensity gradient of the circular boundary, namely dividing the image according to different pixel values;
step B3: tracking edge points along the edge direction by using a non-maximum suppression technology to eliminate edge false detection;
step B4: determining possible boundaries by using a double-threshold method, and drawing the boundaries;
step C: if the distance from each point to the midpoint on the identified edge fluctuates around the radius value and the radius data is normalized to solve the problem of inconsistent fluctuation range of large diameter and small diameter, the graph class circle can be judged.
Compared with the prior art, the invention has the following advantages and positive effects due to the adoption of the technical scheme:
1. aiming at the problems of instability, high time and space consumption and the like of Hough transformation in circle detection, the invention provides a quasi-circle detection method for detecting according to a quasi-circle outline.
2. The invention combines Hough transformation with other two kinds of similar circle detection methods (a similar circle detection method based on a peripheral angle and a similar circle detection method based on a circle radius), and applies the same to the detection of meteorite pits, judges the similar circle in the one-dimensional image, has high running speed, small occupied memory and higher detection precision under the condition of higher image definition, and has higher practical value and stronger universal applicability. The method has good recognition effect on complex lunar surface topography, and lays an important theoretical foundation for avoiding obstacles of the lunar rover.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present invention, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is evident that the drawings in the following description are only some embodiments of the invention and that other drawings may be obtained from these drawings by those skilled in the art without inventive effort. In the accompanying drawings:
FIG. 1 is a detailed frame diagram of the detection method of the present invention;
FIG. 2 is a simulation of the determination of the circumferential angle in the present invention;
FIG. 3 is a simulation of the circle radius determination in the present invention;
FIG. 4 is a meteorite crater artwork in accordance with the present invention;
FIG. 5 is a diagram of the meteorite crater detection in the present invention;
FIG. 6 is a graph of the results of a conventional algorithm run;
FIG. 7 is a graph of the results of the operation of the algorithm of the present invention.
Detailed Description
The following description and the discussion of the embodiments of the present invention will be made more complete and less in view of the accompanying drawings, in which it is to be understood that the invention is not limited to the embodiments of the invention disclosed and that it is intended to cover all such modifications as fall within the scope of the invention.
Example 1
As shown in fig. 1, the invention discloses a novel quasi-circular detection method based on Hough transformation, which is combined with a quasi-circular detection method based on a circumferential angle, and comprises the following steps:
step 1: the method comprises the steps that the circle center of a similar circle is acquired, the acquired image boundary points are required to be filtered to acquire a continuous boundary, the circle center of the similar circle is assumed to be an O point, a horizontal scanning line is established on a plane where the image is located, the edge of the similar circle is scanned downwards in sequence, in one-dimensional space, a Hough transformation method is adopted for midpoint counting, and the midpoint corresponding to the maximum counting value can be regarded as the circle center O;
step 2: obtaining a quasi-circle radius, finding out the outline of the graph through edge detection, traversing each point on the outline in sequence, carrying out numerical comparison to obtain two points at the farthest distance on the outline, taking any point except the two points on the circle, and taking the connecting line of the two points at the farthest distance as the diameter of the quasi-circle;
step 3: judging whether the angle range of the circumferential angle of the diameter is 80-100 degrees, if so, drawing the edge and giving a center point O, wherein specific parameters are shown in figure 2.
In the detection method, edge detection is needed to be carried out on an original image, and the data scale of the image is obviously reduced under the condition of retaining the original image attribute, and the specific edge detection steps are as follows:
step 21: removing noise by using Gaussian filtering to achieve the purpose of smoothing the image;
step 22: searching the intensity gradient of the circular boundary, namely dividing the image according to different pixel values;
step 23: tracking edge points along the edge direction by using a non-maximum suppression technology to eliminate edge false detection;
step 24: a double threshold approach is used to determine the possible boundaries and draw the boundaries.
After the edge detection is successful, searching the outline of the point to be judged in the picture, and traversing each point on the outline in turn to obtain two points furthest on the outline, as shown in an AB (figure 2), taking any point (except the two points) on a circle, judging whether the angle a corresponding to the AB edge is between 80 degrees and 100 degrees, and if the angle is within the range, marking the graph for further identification.
Example two
With continued reference to fig. 1, the invention also discloses a novel quasi-circular detection method based on Hough transformation, which is combined with a quasi-circular detection method based on a circular radius, and the detection method is based on the characteristic of the circular radius, any line segment from the center to the periphery of the detection method is equal, and if any point on a certain graph to the midpoint after judgment fluctuates in the radius, the graph can be approximately seen as a circle, and the method specifically comprises the following steps:
step A: the method comprises the steps that the circle center of a similar circle is acquired, the acquired image boundary points are required to be filtered to acquire a continuous boundary, the circle center of the similar circle is assumed to be an O point, a horizontal scanning line is established on a plane where the image is located, the edge of the similar circle is scanned downwards in sequence, in one-dimensional space, a Hough transformation method is adopted for midpoint counting, and the midpoint corresponding to the maximum counting value can be regarded as the circle center O;
and (B) step (B): acquiring a quasi-circle radius, identifying the image contour through edge detection, and traversing points on the contour in sequence to obtain two points with the farthest distance on the contour, wherein as shown in an AB in fig. 3, a midpoint O of the AB is assumed to be a circle center, and the distance between the two points can be assumed to be a diameter;
in the detection method, edge detection is needed to be carried out on an original image, and the data scale of the image is obviously reduced under the condition of retaining the original image attribute, and the specific edge detection steps are as follows:
step B1: removing noise by using Gaussian filtering to achieve the purpose of smoothing the image;
step B2: searching the intensity gradient of the circular boundary, namely dividing the image according to different pixel values;
step B3: tracking edge points along the edge direction by using a non-maximum suppression technology to eliminate edge false detection;
step B4: determining possible boundaries by using a double-threshold method, and drawing the boundaries;
step C: if the distance from each point to the midpoint on the identified edge fluctuates around the radius value, i.e. the lengths of m and n can be approximately equal, normalization processing is further needed to be performed on the radius data to solve the problem of inconsistent fluctuation ranges of large diameter and small diameter, the graph class circle can be judged, and specific parameters are shown in fig. 3.
The implementation of the invention is completed in three stages, as follows:
the first stage: specific implementation of the algorithm
Firstly, edge detection is needed to be carried out on an original image, and the round edge is determined after binarization operation. For any non-zero point of the image edge, a Sobel operator is required, and for each pixel specified by the parameter, superposition and marking in an accumulator are required. Inverse resolution of accumulator image = 1, high threshold of canny edge function set to 60, center detection threshold set to 26. The circle center detection threshold value needs to be set according to the size of the circle in the image, when the circle in the image is smaller, the value should be set smaller, so that noise is avoided 。
The implementation steps of the circumference angle algorithm are as follows:
1. searching the outline of the target graph through edge detection;
2. traversing each point on the contour in turn;
3. performing numerical comparison to obtain two points at the furthest distance on the contour;
4. taking any point on the circle (except for the two points), and taking the connecting line of the two points at the farthest distance as the diameter of the circular shape;
5. judging whether the angle range of the diameter is about 80-100 degrees.
The circle radius algorithm comprises the following implementation steps:
1. identifying the image contour by edge detection;
2. traversing the points on the contour in turn;
3. judging two points with the farthest distance on the contour as diameters;
4. it is determined whether the distance from each point on the identified edge to the midpoint fluctuates around the radius value.
And a second stage: specific application of algorithm
The quasi-circular identification and detection method has wide application in industrial detection lines, biomedical monitoring equipment and automatic assembly lines.
The problem which cannot be ignored in the related research of obstacle avoidance of the lunar rover is the research of complex terrains, and the invention applies two kinds of circular detection algorithms to the identification of the lunar meteorite pits and obtains good effect. In the aspect of path planning of the lunar rover, the recognition and detection of the merle can provide a better data basis for path planning to avoid obstacles, and the method is particularly applied to the scheme shown in fig. 4 and 5.
And a third stage: accuracy analysis of class circle identification
The accuracy of the invention for circular-like identification is shown by the detailed implementation diagram, and as can be seen from fig. 6 and 7, the accuracy of the conventional algorithm for circular-like detection is lower than that of the algorithm proposed by the invention.
The present invention is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present invention are intended to be included in the scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.
Claims (2)
1. The novel quasi-circular detection method based on Hough transformation is combined with a quasi-circular detection method based on a circumferential angle, and is characterized by comprising the following steps of:
step 1: the method comprises the steps that the circle center of a similar circle is acquired, the acquired image boundary points are required to be filtered to acquire a continuous boundary, the circle center of the similar circle is assumed to be an O point, a horizontal scanning line is established on a plane where the image is located, the edge of the similar circle is scanned downwards in sequence, in one-dimensional space, a Hough transformation method is adopted for midpoint counting, and the midpoint corresponding to the maximum counting value can be regarded as the circle center O;
step 2: obtaining a quasi-circle radius, finding out the outline of the graph through edge detection, traversing each point on the outline in sequence, carrying out numerical comparison to obtain two points at the farthest distance on the outline, taking any point except the two points on the circle, and taking the connecting line of the two points at the farthest distance as the diameter of the quasi-circle;
the edge detection step in step 2 is as follows:
step 21: removing noise by using Gaussian filtering to achieve the purpose of smoothing the image;
step 22: searching the intensity gradient of the circular boundary, namely dividing the image according to different pixel values;
step 23: tracking edge points along the edge direction by using a non-maximum suppression technology to eliminate edge false detection;
step 24: determining possible boundaries by using a double-threshold method, and drawing the boundaries;
step 3: judging whether the angle range of the circumferential angle of the diameter is 80-100 degrees, if so, drawing the edge and giving a center point O.
2. The novel quasi-circular detection method based on Hough transformation is combined with the quasi-circular detection method based on the circular radius, and is characterized by comprising the following steps of:
step A: the method comprises the steps that the circle center of a similar circle is acquired, the acquired image boundary points are required to be filtered to acquire a continuous boundary, the circle center of the similar circle is assumed to be an O point, a horizontal scanning line is established on a plane where the image is located, the edge of the similar circle is scanned downwards in sequence, in one-dimensional space, a Hough transformation method is adopted for midpoint counting, and the midpoint corresponding to the maximum counting value can be regarded as the circle center O;
and (B) step (B): acquiring a quasi-circle radius, identifying the image contour through edge detection, traversing points on the contour in sequence to obtain two points with the farthest distance on the contour, and assuming that a midpoint O of the AB is a circle center, wherein the distance between the two points can be assumed to be the diameter;
the edge detection step in step B is as follows:
step B1: removing noise by using Gaussian filtering to achieve the purpose of smoothing the image;
step B2: searching the intensity gradient of the circular boundary, namely dividing the image according to different pixel values;
step B3: tracking edge points along the edge direction by using a non-maximum suppression technology to eliminate edge false detection;
step B4: determining possible boundaries by using a double-threshold method, and drawing the boundaries;
step C: if the distance from each point to the midpoint on the identified edge fluctuates around the radius value and the radius data is normalized to solve the problem of inconsistent fluctuation range of large diameter and small diameter, the graph class circle can be judged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110294720.3A CN113012181B (en) | 2021-03-18 | 2021-03-18 | Novel quasi-circular detection method based on Hough transformation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110294720.3A CN113012181B (en) | 2021-03-18 | 2021-03-18 | Novel quasi-circular detection method based on Hough transformation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113012181A CN113012181A (en) | 2021-06-22 |
| CN113012181B true CN113012181B (en) | 2023-09-19 |
Family
ID=76402946
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110294720.3A Active CN113012181B (en) | 2021-03-18 | 2021-03-18 | Novel quasi-circular detection method based on Hough transformation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113012181B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570593B (en) * | 2021-08-10 | 2024-05-14 | 深圳诺博医疗科技有限公司 | Accurate counting method and device for medicament, computer equipment and storage medium |
| CN114359320B (en) * | 2021-12-15 | 2023-02-03 | 哈尔滨工业大学 | Moon detector robust ring mountain detection method and aircraft navigation method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5189711A (en) * | 1989-11-24 | 1993-02-23 | Isaac Weiss | Automatic detection of elliptical shapes |
| DE102015205505A1 (en) * | 2015-03-26 | 2016-09-29 | Mando Corporation | Method and apparatus for detecting elliptical structures in an image |
| CN108986038A (en) * | 2018-06-01 | 2018-12-11 | 浙江大学 | A kind of wheel-hub contour detection method based on Improved Hough Transform |
| CN110060259A (en) * | 2019-04-04 | 2019-07-26 | 东华大学 | A kind of fish eye lens effective coverage extracting method based on Hough transformation |
-
2021
- 2021-03-18 CN CN202110294720.3A patent/CN113012181B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5189711A (en) * | 1989-11-24 | 1993-02-23 | Isaac Weiss | Automatic detection of elliptical shapes |
| DE102015205505A1 (en) * | 2015-03-26 | 2016-09-29 | Mando Corporation | Method and apparatus for detecting elliptical structures in an image |
| CN108986038A (en) * | 2018-06-01 | 2018-12-11 | 浙江大学 | A kind of wheel-hub contour detection method based on Improved Hough Transform |
| CN110060259A (en) * | 2019-04-04 | 2019-07-26 | 东华大学 | A kind of fish eye lens effective coverage extracting method based on Hough transformation |
Non-Patent Citations (2)
| Title |
|---|
| 屈汉章 ; 王洋 ; 吴成茂 ; .基于直径累积的霍夫变换检测圆算法.西安邮电大学学报.2017,(第05期),全文. * |
| 秦开怀 ; 王海颍 ; 郑辑涛 ; .一种基于Hough变换的圆和矩形的快速检测方法.中国图象图形学报.2010,(第01期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113012181A (en) | 2021-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109060836B (en) | Machine vision-based high-pressure oil pipe joint external thread detection method | |
| CN113012181B (en) | Novel quasi-circular detection method based on Hough transformation | |
| CN107292310A (en) | A kind of circular pointer dial plate vision positioning and automatic reading method | |
| CN110814465B (en) | Universal method for automatically extracting welding seam contour | |
| CN107192716A (en) | A kind of workpiece, defect quick determination method based on contour feature | |
| CN106778551A (en) | A kind of fastlink and urban road Lane detection method | |
| CN112598922B (en) | Parking space detection method, device, equipment and storage medium | |
| CN107748855B (en) | Detection method for two-dimensional code image finding graph | |
| CN113870235A (en) | Method for detecting defects of circular stamping part based on quantum firework arc edge extraction | |
| CN109300104B (en) | Angular point detection method and device | |
| CN104778707A (en) | Electrolytic capacitor detecting method for improving general Hough transform | |
| CN110906875A (en) | Visual processing method for aperture measurement | |
| CN103632137A (en) | Human iris image segmentation method | |
| CN108109154A (en) | A kind of new positioning of workpiece and data capture method | |
| CN111476804A (en) | Method, device and equipment for efficiently segmenting carrier roller image and storage medium | |
| CN111127498A (en) | Canny edge detection method based on edge self-growth | |
| CN115294527A (en) | Subway tunnel damage detection method based on computer vision | |
| CN107808165B (en) | Infrared image matching method based on SUSAN corner detection | |
| CN109544513A (en) | A kind of steel pipe end surface defect extraction knowledge method for distinguishing | |
| CN113191281B (en) | ORB (object oriented binary) feature extraction method based on region of interest and self-adaptive radius | |
| CN112991327B (en) | Steel grid welding system, method and terminal equipment based on machine vision | |
| CN113034526B (en) | Grabbing method, grabbing device and robot | |
| CN117893553A (en) | Image processing titanium metal segmentation method and system | |
| US9830532B1 (en) | Object detection in images using distance maps | |
| CN113781413A (en) | Electrolytic capacitor positioning method based on Hough gradient 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 |