CN111508032B - Method for sorting feature points in camera calibration process - Google Patents
Method for sorting feature points in camera calibration process Download PDFInfo
- Publication number
- CN111508032B CN111508032B CN202010303979.5A CN202010303979A CN111508032B CN 111508032 B CN111508032 B CN 111508032B CN 202010303979 A CN202010303979 A CN 202010303979A CN 111508032 B CN111508032 B CN 111508032B
- Authority
- CN
- China
- Prior art keywords
- point
- points
- characteristic
- feature points
- feature
- 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
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000006243 chemical reaction Methods 0.000 claims description 13
- 238000003384 imaging method Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000002203 pretreatment Methods 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing 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
- G06T7/80—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
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G06T7/337—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/35—Determination of transform parameters for the alignment of images, i.e. image registration using statistical methods
-
- 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
- G06T2207/20072—Graph-based image processing
Abstract
The invention discloses a characteristic point sequencing method in the camera calibration process, wherein a camera acquires calibration plate images and carries out the following processing on the calibration plate images: extracting characteristic points in the calibration plate image, and selecting an initial point; search for a preselected set of points A for an initial point i (ii) a Traverse A i Marking each adjacent point of the initial point; marking other feature points in the calibration plate image as initial points, and performing the step 2) again until all the feature points are traversed, and establishing an adjacency relation among the feature points; establishing a world coordinate system, and matching world coordinates for each characteristic point according to the adjacency relation among the characteristic points; the method can be used for finishing the sorting of the world coordinates of all the feature points, does not need to set a threshold value, can adapt to the condition of non-whole row and whole column, is not influenced by the distance between the feature points on the calibration board, and effectively improves the stability and convenience of camera calibration.
Description
Technical Field
The invention relates to the field of laser vision measurement, in particular to a characteristic point sorting method in a camera calibration process.
Background
The camera calibration is a precondition of precise vision measurement, a mathematical model is established according to a pinhole imaging principle and a lens distortion principle of a camera by knowing world point coordinates and pixel point coordinates of a calibration point, and finally camera internal parameters are calculated by a nonlinear least square method to finish the camera calibration. In the process, determining the world system coordinates corresponding to each feature point through sequencing is a very critical step, and the correct camera internal parameters can be calculated only when the world coordinates of each point are completely correct.
At present, in a calibration method based on a two-dimensional calibration object, a circular target (circle center is a feature point) and a checkerboard (angular point is a feature point) are usually adopted for a calibration target, and circles or rectangles on the calibration target generally satisfy whole-row whole-column high-precision equidistant distribution, and on the premise, the current sequencing method is as follows: straight-line ordering methods, such as thesis: based on a method for extracting and sequencing characteristic points of a circular calibration plate (author: Liu Zhi, digital technology and application), based on automatic identification and sequencing of angular points of black and white ring sector disks (author: field seedling, Hao facing the sun, Liu Song Lin-science and technology report), the method determines the coordinates of each calibration point by setting a threshold of the distance between the calibration points and searching adjacent calibration points along a straight line in the threshold range, and has the following problems:
(1) because the relation that object point to image point is perspective projection in the aperture imaging model of camera, the nearly big problem of distance that can appear when the formation of image of the scale point interval on the calibration plate plane on the camera imaging plane, simultaneously because the camera lens has the distortion, the equidistant distribution of scale point no longer according to the straight line after the formation of image, if carry out the straight line search sequencing according to fixed threshold value this moment and appear some scale point world coordinate matching mistake very easily.
(2) In the actual calibration process, incomplete imaging circles exist at the edge of the calibration plate, when the image quality is poor or partial circles are affected by factors such as illumination and the like, the circles can be removed, at the moment, partial calibration points on the calibration plate are lost, the whole row and column distribution is not met, at the moment, if the problem of world coordinate matching error also occurs according to the original method, the method has higher requirements on the calibration environment, and meanwhile, the calibration image needs to be preprocessed manually, and the time is consumed.
Disclosure of Invention
Aiming at the problems, the invention provides a characteristic point sorting method in the camera calibration process, which does not need to set a threshold value, but utilizes the neighbor relation between calibration points, can adapt to the condition of non-whole row and whole column, is not influenced by the distance between the characteristic points on the calibration plate, and effectively improves the stability and the convenience of camera calibration.
A camera collects images of a calibration board, a plurality of feature patterns are distributed on the calibration board, the centers or angular points of the feature patterns are marked as feature points, and the distances between any two adjacent feature points are equal;
the method is characterized in that the following processing is carried out on the calibration plate image:
1) extracting feature points in the calibration plate image, and optionally selecting one of the feature points as an initial point;
2) searching four characteristic points with the closest distance to the initial point and marking as a preselected point set A i ，i＝1,2,3,4；
Traverse the set of preselected points A i The following processing procedures are carried out on each pre-selected point:
I. recording the current traversal point as a pending point, and recording other three points as a point set B i ，i＝1,2,3；
The undetermined point is judged according to the following steps:
from point set B i Selecting one point from the points C; obtaining: the distance d between the initial point and the undetermined point, the distance d1 between the undetermined point and the point C, and the distance d2 between the initial point and the point C;
if d1< d and d2< d, the undetermined point is not considered as the adjacent point of the initial point; carrying out the step III;
otherwise, from the current point set B i Removing point C, proceeding step I, from point set B i Selecting one point as a new point C, continuing to judge the undetermined point until a point set B is reached i If no point exists, storing the undetermined point as an adjacent point of the initial point; carrying out the step III;
thirdly, switching the next preselected point to be a traversal point, returning to the step I, updating the undetermined point, and performing the same judgment process on the new undetermined point;
3) marking other feature points in the calibration plate image as initial points, and performing the step 2) again until all the feature points are traversed, and establishing an adjacency relation among the feature points;
taking the initial point marked in the step 1) as the origin of a coordinate system, establishing a world coordinate system, and matching world coordinates for each characteristic point according to the adjacency relation among the characteristic points; and finishing the sorting of the world coordinates of all the feature points.
Due to the problems of big and small in the imaging of the calibration plate image, such as: when the calibration plate is inclined relatively to the camera greatly, the distance value between the characteristic points in the image is possibly inaccurate, so that a more accurate sequencing result is obtained;
further, a step 4) of solving a homography matrix between the calibration plate plane and the camera imaging plane by using a RANSAC method based on the pixel coordinates of each feature point and the world coordinates obtained in the step 3);
converting the pixel coordinates of each characteristic point into world coordinates by using the homography matrix, recording the converted world coordinate points as conversion coordinate points, and establishing an adjacent relation among the conversion coordinate points by adopting the method same as the steps 1) to 3) to match the world coordinates for each conversion coordinate point; and finishing the sorting of the world coordinates of all the conversion coordinate points.
In order to efficiently acquire the adjacency relation between the feature points, in the step 3), a graph structure is established, and then the graph structure is traversed by using a breadth-first traversal method to match world coordinates for each feature point; and finishing the sorting of the world coordinates of all the feature points.
Further, before step 1), the following pre-treatments were carried out: and inwards constructing a rectangular area with the width of 5-10 pixels at the edge of the calibration plate image, wherein the gray value of the rectangular area is the same as that of the characteristic pattern, communicating the characteristic patterns at each edge, removing the area with the largest communicated area, and removing the incomplete characteristic patterns at each edge.
Furthermore, the characteristic patterns are checkerboards or characteristic circles, and the corners of the checkerboards or the centers of the characteristic circles are marked as characteristic points.
For the convenience of distinguishing, preferably, a checkerboard or a feature circle with an area larger than that of other patterns is arranged on the calibration plate, and in the step 1), the corresponding feature point is selected as an initial point.
The method is applied to the camera calibration process, can effectively improve the robustness of the ordered matching of the pixel coordinates of the calibration point and the world coordinates, and mainly has the following advantages compared with the traditional method:
the graph structure is constructed through the distance relation of the adjacent calibration points, a distance threshold is not required to be set, the robustness problem caused by improper threshold selection and non-whole-row and whole-column distribution of the calibration points is solved, manual intervention is not required in the whole process, and the efficiency is high; in addition, the homography matrix is solved through RANSAC, the pixel system coordinates of the feature points are converted into a world system through homography transformation, the adjacency relation is constructed again, and the problem of wrong sorting matching caused by the large and small distances between the pixel coordinate points of the calibration points during first sorting is solved.
Drawings
FIG. 1 is a schematic flow chart of the method in the example;
FIG. 2 is a diagram illustrating a position relationship of adjacent points in an embodiment;
FIG. 3 is a real shot of the calibration plate in the embodiment;
FIG. 4 is a schematic diagram illustrating the adjacency relation of each feature point in the embodiment;
FIG. 5 is a schematic diagram showing the positions of the pixel coordinates of the feature points in the embodiment;
fig. 6 is a schematic diagram of the positions of the conversion coordinate points in the embodiment.
Detailed Description
The technical solution of the present invention is described in detail below with reference to the accompanying drawings and the detailed description.
A camera collects images of a calibration plate (as shown in figure 3), a plurality of characteristic patterns are distributed on the calibration plate, the centers or angular points of the characteristic patterns are marked as characteristic points, and the distances between any two adjacent characteristic points are equal;
the characteristic patterns are checkerboards or characteristic circles, and the corner points of the checkerboards or the centers of the characteristic circles are marked as characteristic points.
In this embodiment, the feature pattern is a feature circle, and before step 1), the following preprocessing is performed: and inwards constructing a rectangular area with the width of 5-10 pixels at the edge of the calibration plate image, wherein the gray value of the rectangular area is the same as that of the characteristic pattern, communicating the characteristic patterns at each edge, removing the area with the largest communicated area, and removing the incomplete characteristic patterns at each edge.
As shown in fig. 1, the following processing is performed on the calibration plate image:
1) extracting feature points in the calibration plate image, and selecting one of the feature points as an initial point;
2) searching four characteristic points with the nearest distance from the initial point and recording the four characteristic points as a preselected point set A i ，i＝1,2,3,4；
Traverse the preselection point set A i The following processing procedures are carried out on each pre-selected point:
I. recording the current traversal point as an undetermined point, and recording other three points as a point set B i ，i＝1,2,3；
The following judgment process is carried out on the point to be fixed:
set of points B i Selecting one point, and marking as a point C;
as shown in fig. 2, the following are acquired: the distance d between the initial point and the undetermined point, the distance d1 between the undetermined point and the point C, and the distance d2 between the initial point and the point C;
if d1< d and d2< d, the undetermined point is not considered as the adjacent point of the initial point; carrying out the step III;
otherwise, from the current point set B i Removing point C, proceeding step I, collecting point B i Selecting one point from the points as a new point C, and continuing to judge the undetermined point until a point set B i If the undetermined point is not found, storing the undetermined point as an adjacent point of the initial point; carrying out the step III;
thirdly, switching the next preselected point to be a traversal point, returning to the step I, updating the undetermined point, and performing the same judgment process on the new undetermined point;
3) marking other feature points in the calibration plate image as initial points, and performing the step 2) again until all the feature points are traversed, and establishing an adjacency relation among the feature points as shown in fig. 4;
taking the initial point marked in the step 1) as the origin of a coordinate system, establishing a world coordinate system, and matching world coordinates for each characteristic point according to the adjacency relation among the characteristic points; and finishing the sorting of the world coordinates of all the feature points.
In order to obtain more accurate sequencing results; the embodiment comprises a step 4) of solving a homography matrix between a calibration plate plane and a camera imaging plane by using a RANSAC method based on pixel coordinates (shown in FIG. 5) of each feature point and world coordinates obtained in the step 3);
the RANSAC algorithm is introduced, so that a correct homography matrix can be stably solved, and the influence of partial error matching points is overcome;
converting the pixel coordinates of each characteristic point into world coordinates by using the homography matrix, recording the converted world coordinate points as conversion coordinate points (as shown in fig. 6), and establishing an adjacent relation among the conversion coordinate points by adopting the same method as the steps 1) to 3) to match the world coordinates for each conversion coordinate point; and finishing the sorting of the world coordinates of all the conversion coordinate points.
In order to efficiently acquire the adjacency relation between the feature points, in the specific implementation, in the step 3), a graph structure can be established, and then the graph structure is traversed by using a breadth-first traversal method to match world coordinates for each feature point; and finishing the sorting of the world coordinates of all the feature points.
For convenience of distinction, as shown in fig. 3, in this embodiment, a checkerboard or a feature circle having an area larger than that of other patterns is disposed on the calibration board, and in step 1), the corresponding feature point is selected as the initial point, that is, the origin of the world coordinate system in step 3).
In this embodiment, the position relationship between each adjacent point and the current feature point is determined according to the neighbor relationship of the relative distance between the feature points, the feature points are constructed into a Graph structure (Graph) according to the position relationship, and the coarse matching of the pixel coordinates of the feature points and the world coordinates is completed through the traversal of the breadth of the Graph in a priority manner (steps 1) to 3)); then, solving a homography transformation matrix between the calibration plate plane and the imaging plane by using an RANSAC method according to the sequencing matching result, and converting the pixel system coordinates of the characteristic points into a world system so as to avoid the influence caused by the distance between the points; finally, the index points converted from the pixel system to the world system are subjected to neighbor search and mapping sorting again to complete accurate sorting matching (step 4)).
The method can adapt to the condition of non-whole row and column arrangement, is not influenced by the distance between the characteristic points on the calibration plate, and effectively improves the stability and convenience of camera calibration.
The foregoing description of specific exemplary embodiments of the invention has been presented for the purposes of illustration and description, and the exemplary embodiments were chosen and described in order to explain certain principles of the invention and its practical application to enable others skilled in the art to make and use various exemplary embodiments of the invention and various alternatives and modifications thereof. It is intended that the scope of the invention be defined by the following claims and their equivalents.
Claims (6)
1. A camera collects images of a calibration board, a plurality of feature patterns are distributed on the calibration board, the centers or angular points of the feature patterns are marked as feature points, and the distances between any two adjacent feature points are equal;
the method is characterized in that the following processing is carried out on the calibration plate image:
1) extracting feature points in the calibration plate image, and optionally selecting one of the feature points as an initial point;
2) searching four characteristic points with the closest distance to the initial point and marking as a preselected point set A i ，i＝1,2,3,4；
Traverse the set of preselected points A i The following processing procedures are carried out on each pre-selected point:
I. recording the current traversal point as an undetermined point, and recording other three points as a point set B i ，i＝1,2,3；
The undetermined point is judged according to the following steps:
from point set B i Selecting one point, and marking as a point C; obtaining: the distance d between the initial point and the undetermined point, the distance d1 between the undetermined point and the point C, and the distance d2 between the initial point and the point C;
if d1< d and d2< d, the undetermined point is not considered as the adjacent point of the initial point; carrying out the step III;
otherwise, from the current point set B i Removing point C, proceeding step I, from point set B i Selecting one point from the points as a new point C, and continuing to judge the undetermined point until the point set is reachedB i If no point exists, storing the undetermined point as an adjacent point of the initial point; carrying out the step (III);
thirdly, switching the next preselected point to be a traversal point, returning to the step I, updating the undetermined point, and performing the same judgment process on the new undetermined point;
3) marking other feature points in the calibration plate image as initial points, and performing the step 2) again until all the feature points are traversed, and establishing an adjacency relation among the feature points;
taking the initial point marked in the step 1) as the origin of a coordinate system, establishing a world coordinate system, and matching world coordinates for each characteristic point according to the adjacency relation among the characteristic points; and finishing the sorting of the world coordinates of all the feature points.
2. The method for sorting the feature points in the camera calibration process as claimed in claim 1, wherein: the method further comprises a step 4) of solving a homography matrix between the plane of the calibration plate and the imaging plane of the camera by using a RANSAC method based on the pixel coordinates of the characteristic points and the world coordinates obtained in the step 3);
converting the pixel coordinates of each characteristic point into world coordinates by using the homography matrix, recording the converted world coordinate points as conversion coordinate points, and establishing an adjacent relation among the conversion coordinate points by adopting the method same as the steps 1) to 3) to match the world coordinates for each conversion coordinate point; and finishing the sorting of the world coordinates of all the conversion coordinate points.
3. The method for sorting the feature points in the camera calibration process as claimed in claim 1, wherein: in step 3), establishing a graph structure, traversing the graph structure by using a breadth-first traversal method, and matching world coordinates for each feature point; and finishing the sorting of the world coordinates of all the feature points.
4. The method for sorting the feature points in the camera calibration process as claimed in claim 1, wherein: before step 1), the following pre-treatments were carried out: and inwards constructing a rectangular area with the width of 5-10 pixels at the edge of the calibration plate image, wherein the gray value of the rectangular area is the same as that of the characteristic pattern, communicating the characteristic patterns at each edge, removing the area with the largest communicated area, and removing the incomplete characteristic patterns at each edge.
5. The method for sorting the feature points in the camera calibration process as claimed in claim 1, wherein: the characteristic patterns are checkerboards or characteristic circles, and the corner points of the checkerboards or the centers of the characteristic circles are marked as characteristic points.
6. The method for sorting the feature points in the camera calibration process as claimed in claim 1, wherein: in order to facilitate the distinction, a checkerboard or a feature circle with an area larger than that of other patterns is arranged on the calibration plate, and in the step 1), a corresponding feature point is selected as an initial point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010303979.5A CN111508032B (en) | 2020-04-17 | 2020-04-17 | Method for sorting feature points in camera calibration process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010303979.5A CN111508032B (en) | 2020-04-17 | 2020-04-17 | Method for sorting feature points in camera calibration process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111508032A CN111508032A (en) | 2020-08-07 |
| CN111508032B true CN111508032B (en) | 2022-09-27 |
Family
ID=71876143
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010303979.5A Active CN111508032B (en) | 2020-04-17 | 2020-04-17 | Method for sorting feature points in camera calibration process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111508032B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205558B (en) * | 2021-07-02 | 2021-10-12 | 杭州灵西机器人智能科技有限公司 | Camera calibration feature sorting method, calibration board and equipment |
| CN113591855B (en) * | 2021-08-18 | 2023-07-04 | 易思维（杭州）科技有限公司 | Adhesive VIN code segmentation method |
| CN113989386B (en) * | 2021-10-27 | 2023-05-30 | 武汉高德智感科技有限公司 | Infrared camera calibration method and system |
| CN114037774B (en) * | 2022-01-10 | 2022-03-08 | 雅安市人民医院 | Method and device for sequencing and transmitting images of cross sections of cranium and brain and storage medium |
| CN115222825B (en) * | 2022-09-15 | 2022-12-16 | 湖南视比特机器人有限公司 | Calibration method, computer storage medium and calibration system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008143523A1 (en) * | 2007-05-22 | 2008-11-27 | Metaio Gmbh | Camera pose estimation apparatus and method for augmented reality imaging |
| CN106485757A (en) * | 2016-10-13 | 2017-03-08 | 哈尔滨工业大学 | A kind of Camera Calibration of Stereo Vision System platform based on filled circles scaling board and scaling method |
| CN109598762A (en) * | 2018-11-26 | 2019-04-09 | 江苏科技大学 | A kind of high-precision binocular camera scaling method |
| CN110458898A (en) * | 2019-08-15 | 2019-11-15 | 北京迈格威科技有限公司 | Camera calibration plate, nominal data acquisition method, distortion correction method and device |
-
2020
- 2020-04-17 CN CN202010303979.5A patent/CN111508032B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008143523A1 (en) * | 2007-05-22 | 2008-11-27 | Metaio Gmbh | Camera pose estimation apparatus and method for augmented reality imaging |
| CN106485757A (en) * | 2016-10-13 | 2017-03-08 | 哈尔滨工业大学 | A kind of Camera Calibration of Stereo Vision System platform based on filled circles scaling board and scaling method |
| CN109598762A (en) * | 2018-11-26 | 2019-04-09 | 江苏科技大学 | A kind of high-precision binocular camera scaling method |
| CN110458898A (en) * | 2019-08-15 | 2019-11-15 | 北京迈格威科技有限公司 | Camera calibration plate, nominal data acquisition method, distortion correction method and device |
Non-Patent Citations (2)
| Title |
|---|
| 《Corner detection and sorting method based on improved Harris》;Ying Xiao 等;《Optical Metrology and Inspection for Industrial Applications》;20161231;第1-8页； * |
| 《一种基于matlab的特征点提取及排序的简单方法》;肖新跃 等;《福建电脑》;20111231;第28-34页； * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111508032A (en) | 2020-08-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111508032B (en) | Method for sorting feature points in camera calibration process | |
| CN111243032B (en) | Full-automatic detection method for checkerboard corner points | |
| CN102376089B (en) | Target correction method and system | |
| JP5775606B2 (en) | Alignment of microscope slide coordinate system | |
| WO2018196303A1 (en) | Projector calibration method and apparatus based on multi-directional projection | |
| CN110580724A (en) | method and device for calibrating binocular camera set and storage medium | |
| CN107392849B (en) | Target identification and positioning method based on image subdivision | |
| CN110033407B (en) | Shield tunnel surface image calibration method, splicing method and splicing system | |
| CN109035170B (en) | Self-adaptive wide-angle image correction method and device based on single grid image segmentation mapping | |
| CN107358628B (en) | Linear array image processing method based on target | |
| CN111640154B (en) | Vertical needle micro-plane sub-pixel level positioning method based on micro-vision | |
| CN113538583A (en) | Method for accurately positioning position of workpiece on machine tool and vision system | |
| CN114529613A (en) | Method for extracting characteristic point high-precision coordinates of circular array calibration plate | |
| CN116188544A (en) | Point cloud registration method combining edge features | |
| CN111724354A (en) | Image processing-based method for measuring spike length and small spike number of multiple wheat | |
| CN114187363A (en) | Method and device for obtaining radial distortion parameter value and mobile terminal | |
| CN114612412A (en) | Processing method of three-dimensional point cloud data, application of processing method, electronic device and storage medium | |
| CN110689586B (en) | Tongue image identification method in traditional Chinese medicine intelligent tongue diagnosis and portable correction color card used for same | |
| CN116524041A (en) | Camera calibration method, device, equipment and medium | |
| JP2008116207A (en) | Apparatus and method for image measurement, and program | |
| CN114140466B (en) | Plant root system measuring method, system and device based on image processing | |
| CN114152610B (en) | Slide cell scanning method based on visual target mark | |
| CN114463751A (en) | Corner positioning method and device based on neural network and detection algorithm | |
| CN114494316A (en) | Corner marking method, parameter calibration method, medium, and electronic device | |
| CN114235815A (en) | Method for detecting surface defects of outdoor electrical equipment of converter station based on scene filtering |
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 | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Room 495, building 3, 1197 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province 310051 Patentee after: Yi Si Si (Hangzhou) Technology Co.,Ltd. Address before: Room 495, building 3, 1197 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province 310051 Patentee before: ISVISION (HANGZHOU) TECHNOLOGY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |