A Thin Line Power Increase Stereo Matching Method Used in High-Precision Three-Dimensional Measurement

2009 ◽  
Author(s):  
Limei Song ◽  
Long Wang
Keyword(s):  
High Precision ◽  
Stereo Matching ◽  
Three Dimensional ◽  
Matching Method ◽  
Dimensional Measurement ◽  
Thin Line ◽  
Power Increase ◽  
Three Dimensional Measurement

Pixel matching method in on-line three-dimensional measurement based on normalized equiphase plane

2017 ◽  
Vol 46 (7) ◽  
pp. 717004
Author(s):  
许幸芬 Xu Xingfen ◽  
曹益平 Cao Yiping ◽  
付光凯 Fu Guangkai ◽  
陈 澄 Chen Cheng ◽  
王亚品 Wang Yapin
Keyword(s):  
Three Dimensional ◽  
Matching Method ◽  
Dimensional Measurement ◽  
Pixel Matching ◽  
Three Dimensional Measurement ◽  
On Line

Improvement of Human Tracking in Stereoscopic Environment Using Subtraction Stereo with Shadow Detection

2011 ◽  
Vol 5 (6) ◽  
pp. 924-931 ◽  
Author(s):  
Kenji Terabayashi ◽  
◽  
Yuma Hoshikawa ◽  
Alessandro Moro ◽  
Kazunori Umeda ◽  
...  
Keyword(s):  
Stereo Matching ◽  
Tracking System ◽  
Three Dimensional ◽  
Shadow Detection ◽  
People Tracking ◽  
Matching Method ◽  
Search Range ◽  
Geometric Information ◽  
Three Dimensional Measurement ◽  
Crowded Environments

The combination of subtraction stereo with shadow detection we propose improves people tracking in stereoscopic environments. Subtraction stereo is a stereo matching method which is fast and robust for the correspondence problem – one of the most serious issues in computer vision – restricting the search range of matching to foreground regions. Shadow detection gives adequate foreground regions of tracked people by removing cast shadows. This leads to accurate three-dimensional measurement of positions in stereoscopic environment tracking. By focusing on disparity images obtained by subtraction stereo, we can detect people easily based on standard labeling. Objects can also be measured directly in size by subtraction stereo without geometric information about environments for tracking. This is important for installing the tracking system easily. To track multiple passing people, we use the extended Kalman filter to address the occlusion problem usually encountered in crowded environments. The proposed method is verified by experiments using unknown stereoscopic environments.

Sign in / Sign up

Export Citation Format

Share Document