Foreground and background stereo matching method based on belief propagation and self-similar difference measure
A technology of belief propagation and stereo matching, applied in the field of computer vision, can solve problems such as defects in the boundaries of discontinuous areas, and achieve good precision results
Active Publication Date: 2019-01-22
CHONGQING UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In view of the above-mentioned problems, the purpose of the present invention is to provide a foreground and background stereo matching method based on belief propagation and self-similar difference measure, to solve the problems existing in large-scale low-texture regions and discontinuous region boundaries in existing guided filtering stereo matching methods. defect problem
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
[0013] In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more embodiments. It may be evident, however, that these embodiments may be practiced without these specific details. In other instances, well-known structures and devices are shown in block diagram form in order to facilitate describing one or more embodiments.
[0014] The self-similar disparity measure has a better advantage over the foreground information in the disparity map because of the detailed detail information, and the belief propagation algorithm has better background mapping due to the belief propagation inference. Therefore, the present invention proposes based on the idea of segmentation, by combining the belief propagation algorithm and the self-similar difference measurement algorithm, the effect of the disparity map can be improved, thereby improving the stereo matching accuracy, especially in disc...
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 provides a foreground and background stereo matching method based on belief propagation and self-similarity difference measurement. The method comprises the following steps: first of all, performing stereo matching on images respectively by use of a belief propagation algorithm and a self-similarity difference measurement algorithm to obtain respective disparity maps; and then, by use of a subsection function fused belief propagation algorithm and a self-similarity difference measurement algorithm, obtaining foreground information and background information in the disparity maps through matching. The foreground and background stereo matching method based on the belief propagation and the self-similarity difference measurement, provided by the invention has quite good stereo matching precision.
Description
technical field [0001] The present invention relates to the technical field of computer vision, and more specifically, to a foreground and background stereo matching method based on belief propagation and self-similar difference measure. Background technique [0002] Stereo matching is one of the hottest computer vision directions at present. Its goal is to find corresponding points in one or several pictures at different viewpoints and different times and locations, and then obtain a dense depth or disparity map. [0003] Currently common stereo matching methods include local methods and global methods. Global methods mainly include graph cut (GC) and belief propagation (BP) methods. The global method has high precision, but the speed is relatively slow, and it is difficult to meet real-time, accurate and fast applications, especially in 3D reconstruction, stereoscopic video, robot navigation and other fields that require high real-time performance. Local algorithms are ...
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): G06T7/30
CPCG06T2207/10012
Inventor 王晓峰苏盈盈李明臻赵轶
Owner CHONGQING UNIVERSITY OF SCIENCE AND TECHNOLOGY