24 January 2011 Target matching based on multi-view tracking
Author Affiliations +
A feature matching method is proposed based on Maximally Stable Extremal Regions (MSER) and Scale Invariant Feature Transform (SIFT) to solve the problem of the same target matching in multiple cameras. Target foreground is extracted by using frame difference twice and bounding box which is regarded as target regions is calculated. Extremal regions are got by MSER. After fitted into elliptical regions, those regions will be normalized into unity circles and represented with SIFT descriptors. Initial matching is obtained from the ratio of the closest distance to second distance less than some threshold and outlier points are eliminated in terms of RANSAC. Experimental results indicate the method can reduce computational complexity effectively and is also adapt to affine transformation, rotation, scale and illumination.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yahui Liu, Changsheng Zhou, "Target matching based on multi-view tracking", Proc. SPIE 7878, Intelligent Robots and Computer Vision XXVIII: Algorithms and Techniques, 78780I (24 January 2011); doi: 10.1117/12.872638; https://doi.org/10.1117/12.872638


Shaking video stabilization with content completion
Proceedings of SPIE (January 19 2009)
Moving object segmentation based on optical flow field
Proceedings of SPIE (November 14 2007)
Approach for counting vehicles in congested traffic flow
Proceedings of SPIE (February 25 2005)
Target tracking based on video sequences
Proceedings of SPIE (May 05 2011)
A dynamic path planning algorithm for UAV tracking
Proceedings of SPIE (May 11 2009)

Back to Top