A spatiotemporal tensor-based multi-object matching algorithm

A multi-object matching algorithm based on spatiotemporal tensor is proposed for stereo localization systems with binocular views. Multi-object matching is formulated as a graph matching problem, which forms an efficient and extensible framework for the various matching cases. Then, the spatiotemporal tensor, including appearance, geometric and temporal cues, is used to improve the reliability and accuracy rate of matching in various conditions. Also, a high-order graph matching algorithm is introduced and improved. The experimental evaluation shows that proposed algorithm is robust to various cases, accurate in terms of matching rate, while being time-consuming little.

[1]  Martial Hebert,et al.  Unsupervised Learning for Graph Matching , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Jean Ponce,et al.  A tensor-based algorithm for high-order graph matching , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Martial Hebert,et al.  A spectral technique for correspondence problems using pairwise constraints , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[4]  N. Alberto Borghese,et al.  Tracking densely moving markers , 2002, Proceedings. First International Symposium on 3D Data Processing Visualization and Transmission.

[5]  Ruifeng Yuan,et al.  Robust 3D Marker Localization Using Multi-spectrum Sequences , 2009, ISVC.

[6]  Jochen Willneff,et al.  A spatio-temporal matching algorithm for 3D particle tracking velocimetry , 2002 .

[7]  LI Xiu-xiu.  Fast and accurate stereo matching algorithm based on epipolar line restriction , 2008 .

[8]  Wei Han,et al.  A Fast and Accurate Stereo Matching Algorithm Based on Epipolar lLne Restriction , 2008, 2008 Congress on Image and Signal Processing.

[9]  Mario Vento,et al.  Thirty Years Of Graph Matching In Pattern Recognition , 2004, Int. J. Pattern Recognit. Artif. Intell..

[10]  Arcot Sowmya,et al.  Multiple Camera, Multiple Person Tracking with Pointing Gesture Recognition in Immersive Environments , 2008, ISVC.

[11]  Isaac Cohen,et al.  Continuous multi-views tracking using tensor voting , 2002, Workshop on Motion and Video Computing, 2002. Proceedings..