A Color Structured Light Strip Detection Method Based on Hierarchical Clustering and Confidence Propagation
A technology of belief propagation and hierarchical clustering, applied in the field of 3D reconstruction, it can solve the problems of slow decoding speed, high error rate, limited density of light strips, etc., and achieve the effect of ensuring accuracy and increasing density.
Active Publication Date: 2022-07-01
中国空气动力研究与发展中心超高速空气动力研究所
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
There is a single peak in the gray scale of the line structured light image, and the foreground and background are easy to separate, while the light strips of the surface structured light have their own characteristics, such as the existence of multiple brightness peaks, dense light strips, etc. Therefore, the above detection method cannot be simply transplanted
[0004] There are two main types of decoding methods for color stripe structured light tags: the tag decoding method based on de Bruijn sequence, which has fast decoding speed and high accuracy, but the light stripe density is limited; the tag decoding method based on multi-view geometry, the light stripe density High, but the decoding speed is slower and the error rate is higher
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
[0092] The present invention will be further described in detail below with reference to the accompanying drawings, so that those skilled in the art can refer to the description and implement accordingly.
[0093] It should be understood that terms such as "having", "comprising" and "including" as used herein do not assign the presence or addition of one or more other elements or combinations thereof.
[0094] like Figure 1-4 Shown: a color structured light strip detection method based on hierarchical clustering and confidence propagation of the present invention includes the following steps:
[0095] Step 1, using a projector to project the colored striped structured light onto the surface of the object, and using a camera to collect the colored striped structured light modulated by the surface of the object;
[0096] Step 2: Convert the color stripe structured light image into a grayscale image, perform rough positioning on the center point of the color structured light st...
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 color structured light light strip detection method based on hierarchical clustering and belief propagation. Striped structured light; Coarse positioning and fine positioning of the center point of the color structured light light bar; Attribution discrimination of the center line of the light bar corresponding to the center point of the color structured light light bar; Realize the extraction of the center line of the full image structured light bar; The center line of the structured light strip performs label decoding; completes the dense 3D reconstruction of the surface of the object; fuses and splices the point clouds of the object surface obtained from different viewing angles to complete the overall reconstruction of the object surface. While ensuring the precision, speed and accuracy of the color structured light strip detection, the invention increases the density of the structured light strip, is not limited by the length of the de Bruijn sequence, and helps to realize online and dense object surface topography. Three-dimensional reconstruction.
Description
technical field [0001] The invention belongs to the technical field of three-dimensional reconstruction, and more particularly, the invention relates to a color structured light strip detection method based on hierarchical clustering and belief propagation. Background technique [0002] Light strip detection is one of the core key technologies of the color stripe structured light 3D reconstruction system, which directly determines the accuracy and stability of its topography measurement. Light bar detection mainly includes two parts: light bar center line extraction and light bar center line label decoding. [0003] The light strip centerline extraction methods can be divided into two categories: (1) The light strip centerline extraction method based on gray distribution information, extracts the light strip centerline according to the distribution characteristics of the light strip neighborhood, such as extreme value method, edge method, center of gravity (2) The method of...
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 Patents(China)
IPC IPC(8): G06T17/00G06T7/90G06T5/50G06T3/40G06V10/762G06K9/62
CPCG06T17/00G06T7/90G06T5/50G06T3/4038G06T2200/08G06T2200/32G06T2207/10024G06T2207/20221G06F18/231
Inventor 刘进博杜百合罗跃杨远剑
Owner 中国空气动力研究与发展中心超高速空气动力研究所