Rapid stereo matching method and disparity map obtaining method both aiming at high-definition image pair

A stereo matching, high-definition image technology, applied in the field of computer vision

Active Publication Date: 2013-09-18
SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
View PDF2 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Most of the current stereo matching methods are for non-high-definition image pairs. High-definition video or high-definition pictures will be the mainstream media in the future. Since the number of pixels in high-definition images has increased significantly, stereo matching for high-definition images collected by binoculars is a bigger problem. challenges, the contradiction between fast acquisition and high quality of disparity maps is even more prominent

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Rapid stereo matching method and disparity map obtaining method both aiming at high-definition image pair
  • Rapid stereo matching method and disparity map obtaining method both aiming at high-definition image pair
  • Rapid stereo matching method and disparity map obtaining method both aiming at high-definition image pair

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be described in further detail below in conjunction with the accompanying drawings of the embodiments.

[0037] The stereo matching method of the embodiment of the present invention, such as figure 1 shown, including steps:

[0038] S101: selection of candidate points. Since the object of stereo matching is a high-definition image pair, using the original one-dimensional search method on the epipolar line will bring a large amount of calculation. In fact, the parallax of each pixel is within a certain range, and an estimation of the parallax value of the pixel can be made. In this method, instead of establishing a pixel-centered support window, the color information is directly used to search for pixels with similar colors on its corresponding polar line for each pixel, and a certain number of pixels are taken as Candidate matching points. Such as figure 2 As shown, in the target image, the color difference between the pixels in the ref...

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

No PUM Login to view more

Abstract

The invention relates to a stereo matching method aiming at the high-definition image pair and a high-precision disparity map obtaining method based on the method. Aiming at high-definition left and right eye images, a rapid stereo matching method and a disparity map obtaining method both aiming at a high-definition image pair are provided. Due to the estimation of the scope of the optical parallax, the search scope of the matched counter points is reduced greatly, and calculation redundancy and calculation amount in the method are reduced; as a reasonable matched cost function is constructed, a correct matched pair is selected, and post-treatment for the disparity map is finally carried out by aiming at the candidate matched point pairs, improvement for a plurality of common problems in the disparity map can be carried out, and a smooth and precise disparity map can be obtained.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a stereo matching method for high-definition image pairs, and a high-precision disparity map acquisition method based on the method. Background technique [0002] Stereo matching is a difficult point and a hotspot in binocular stereo vision, and it is also an important method for 3D reconstruction based on images. The current stereo matching methods are mainly divided into two categories. One is the local stereo matching method based on local constraints. This kind of method determines the matching point according to the calculation result of the local similarity measurement value. The process of finding the matching point for each pixel is mutual independent. This type of method has low complexity and can achieve real-time processing, but the quality of the obtained disparity map is not high. The other is the global stereo matching method based on global constraints. This type ...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00G06T7/00
Inventor 王好谦吴勉张永兵戴琼海
Owner SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap