Paper
20 August 2013 Efficient spatiotemporal matching algorithm for stereo videos
Author Affiliations +
Proceedings Volume 8913, International Symposium on Photoelectronic Detection and Imaging 2013: Optical Storage and Display Technology; 89130I (2013) https://doi.org/10.1117/12.2033045
Event: ISPDI 2013 - Fifth International Symposium on Photoelectronic Detection and Imaging, 2013, Beijing, China
Abstract
An efficient stereo matching algorithm for computing stable disparity map sequence from video footage is presented. The algorithm is based on both the spatial and temporal consistency in the stereo sequences, and high quality disparity maps are achieved. Weber local descriptors (WLD) are extracted for each color channel from current stereo pairs, and the raw matching costs between the images are initialized by WLD. Orthogonal integral image (OII) technique along with minimum spanning tree (MST) is used to aggregate the similar pixels and preserve disparity edges adaptively. MST takes place of the process of voting support regions in OII technique and provides a specific support region for each pixel. The nodes of MST are all the image pixels, and the weight of edges are absolute difference between the nearest neighboring pixels. It’s a global method, and can achieve more accurate disparity maps than traditional OII technique. Three-frame subtraction is used to determine the temporal consistency between adjacent frames. The motion region is extracted and the disparity map of motive region is renewed. The disparity of current frame with the renewed disparity and the one for last frame is confirmed. The proposed approach has been tested on the real stereo sequences, and the results are satisfactory.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xin Fan, Xin-zhu Sang, Nan Guo, and Da-xiong Xu "Efficient spatiotemporal matching algorithm for stereo videos", Proc. SPIE 8913, International Symposium on Photoelectronic Detection and Imaging 2013: Optical Storage and Display Technology, 89130I (20 August 2013); https://doi.org/10.1117/12.2033045
Lens.org Logo
CITATIONS
Cited by 1 patent.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Video

Algorithm development

Visualization

3D modeling

Detection and tracking algorithms

Image processing algorithms and systems

Image segmentation

RELATED CONTENT


Back to Top