Differential geometry stereo vision space curve matching method
A space curve, stereo vision technology, applied in the field of differential geometry stereo vision space curve matching, can solve the problem that the matching effect is limited by the position, size and direction of the curve
Active Publication Date: 2020-11-24
SOUTH CHINA UNIV OF TECH +1
View PDF4 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003]
Most of the existing planar curve matching methods are based on the calculation of spatial geometric moments to achieve matching, and the matching effect is limited by the position, size and direction of the curve
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0042] The present invention will be further described in detail below in conjunction with the embodiments and the accompanying drawings, but the embodiments of the present invention are not limited thereto.
[0043] Such as figure 1 , a stereoscopic visual spatial curve matching method of differential geometry, comprising the following steps:
[0044] (1) Obtain the point cloud data of the target curve: convert the target curve into point cloud data through the calibrated stereo vision measurement system
[0045] (2) Setting the threshold: Considering that the spatial curve matching process is affected by the geometric feature extraction efficiency and matching accuracy of the curve, only when the distance between adjacent points on the curve is greater than the preset threshold is considered a valid point;
[0046]In order to avoid the disadvantages of using all sampling points for feature parameter extraction in the traditional method, the distance Δs between adjacent po...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a differential geometry stereo vision space curve matching method. The method comprises the following steps: (1) obtaining point cloud data of a target curve; (2) establishinga Frenet movable frame field, and calculating the curvature and flexibility of each point on the space curve by combining a curve Bouquet formula; and (3) defining a curve similarity function by usinga curve theory basic theorem in combination with a curve Frenet movable frame to perform space curve matching. In the process of realizing space curve matching, aiming at the defects of a conventional curve parameter equation-based matching method, a unit orthogonal Frenet frame is constructed at each point on a space curve, and a local standard form of the curve in a neighborhood of a certain point is utilized; according to the method, a differential geometry tool is combined with the field of pattern recognition, and the method has the advantages of being simple in calculation, high in accuracy, suitable for matching unknown or difficult-to-obtain parameter equation curves on a complex three-dimensional space curved surface and the like when the curves are matched in the three-dimensional space.
Description
technical field [0001] The invention relates to the field of stereo vision contour curve or template matching, in particular to a differential geometry stereo vision space curve matching method. Background technique [0002] In the field of three-dimensional measurement of machine vision, stereo vision has been widely used due to its advantages of high measurement accuracy and efficiency. The three-dimensional data of the binocular vision measurement system can intuitively display the shape of the object in a qualitative manner. Further, quantitative geometric description of the target object and machine vision target matching classification are necessary for the geometric characteristics of the shape of the measured object, so fast and accurate Extracting the geometric features of the measured object's shape is the main task of this type of vision application. As the spatial curve is uniquely determined by its curvature and torsion, using the Frenet orthogonal frame to com...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/653G06F18/22
Inventor 胡跃明曾勇章晓晗
Owner SOUTH CHINA UNIV OF TECH