Abstract
A robust visual tracking system requires an object appearance model that is able to handle occlusion, pose, and illumination variations in the video stream. This can be difficult to accomplish when the model is trained using only a single image. In this paper, we first propose a tracking approach based on affine subspaces (constructed from several images) which are able to accommodate the abovementioned variations. We use affine subspaces not only to represent the object, but also the candidate areas that the object may occupy. We furthermore propose a novel approach to measure affine subspace-to-subspace distance via the use of non-Euclidean geometry of Grassmann manifolds. The tracking problem is then considered as an inference task in a Markov Chain Monte Carlo framework via particle filtering. Quantitative evaluation on challenging video sequences indicates that the proposed approach obtains considerably better performance than several recent state-of-the-art methods such as Tracking-Learning-Detection and MILtrack.
Original language | English |
---|---|
Title of host publication | IEEE Workshop on Applications of Computer Vision (WACV) 2014 |
Editors | Walter Scheirer, Ruigang Yang, Charles Stewart |
Place of Publication | Piscataway NJ USA |
Publisher | IEEE, Institute of Electrical and Electronics Engineers |
Pages | 901-908 |
Number of pages | 8 |
ISBN (Electronic) | 9781479949854 |
ISBN (Print) | 9781479949847 |
DOIs | |
Publication status | Published - 2014 |
Externally published | Yes |
Event | IEEE Winter Conference on Applications of Computer Vision 2014 - Steamboat Springs, United States of America Duration: 24 Mar 2014 → 26 Mar 2014 http://www.wacv14.org/ https://ieeexplore.ieee.org/xpl/conhome/6823792/proceeding (Proceedings) |
Conference
Conference | IEEE Winter Conference on Applications of Computer Vision 2014 |
---|---|
Abbreviated title | WACV 2014 |
Country/Territory | United States of America |
City | Steamboat Springs |
Period | 24/03/14 → 26/03/14 |
Internet address |