Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Stereo matching method based on iterative guidance filtering

A technique for guiding filtering and stereo matching, which is applied in image data processing, instrumentation, calculation, etc., and can solve problems such as bonding

Active Publication Date: 2013-09-18
HARBIN ENG UNIV
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since this method uses a fixed window to calculate the matching cost using guidance filtering, this method has some "glue" phenomenon at the object boundary

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
  • Stereo matching method based on iterative guidance filtering
  • Stereo matching method based on iterative guidance filtering
  • Stereo matching method based on iterative guidance filtering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] Below in conjunction with accompanying drawing and example technical scheme of the present invention is described further:

[0044] The grayscale change of the image can approximately reflect the texture change of the image, the grayscale change of the image in the weak texture area is relatively small, and the grayscale change of the image in the texture area is relatively large; at the same time, the disparity map generated by the stereo matching method can be used To modify the matching cost to improve the robustness of the stereo matching method to noise and radiation differences. Aiming at these characteristics existing in stereo matching, the present invention proposes a stereo matching method based on iterative guided filtering, which can effectively improve the quality of disparity maps, and has a faster matching speed, and is an effective stereo matching method , the specific steps are as follows:

[0045] (1) Calculate the original matching cost;

[0046] In...

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 fields of computer vision, aerial photography measurement and industrial automation, in particular to a stereo matching method based on iterative guidance filtering. The method includes computing original matching cost; determining size of a supporting window for each point to be matched according to gray changes of instruction images; accumulating original matching cost through utilizing guidance filtering according to the sizes of the supporting windows; computing parallax; correcting the original matching cost according to computed parallax images; repeating execute step (3) till the determined maximum number of iterations is reached. The integral image technology is utilized to compute adaptive windows and the guidance filtering, and matching efficiency of the stereo matching method is improved effectively. The computed parallax is utilized to correct the original matching cost and the guidance filtering is utilized to accumulate, robustness of matching cost to noise and radiation difference in enhanced, and accordingly accuracy of vision matching is improved.

Description

technical field [0001] The invention relates to the fields of computer vision, aerial photogrammetry and industrial automation, in particular to a stereo matching method based on iterative guidance filtering. Background technique [0002] Stereo matching is a hot issue in the field of computer vision, which uses two or more images of the same scene to extract the three-dimensional information of the scene. So far, a large number of stereo matching methods have been proposed to solve the stereo correspondence problem. These stereo matching methods can be roughly divided into local stereo matching methods and global stereo matching methods according to different disparity selection methods. The local stereo matching method uses a "winner takes all" method to select the disparity, while the global stereo matching method selects the disparity through a global optimization method. These stereo matching methods ultimately choose the disparity by minimizing the matching cost, so d...

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
IPC IPC(8): G06T7/00
Inventor 门朝光边继龙李香田泽宇马宁李昌门宇博
Owner HARBIN ENG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com