International Journal of Computer Vision

, Volume 107, Issue 2, pp 203–217

Multi-Target Tracking by Online Learning a CRF Model of Appearance and Motion Patterns

Article

DOI: 10.1007/s11263-013-0666-4

Cite this article as:
Yang, B. & Nevatia, R. Int J Comput Vis (2014) 107: 203. doi:10.1007/s11263-013-0666-4

Abstract

We introduce an online learning approach for multi-target tracking. Detection responses are gradually associated into tracklets in multiple levels to produce final tracks. Unlike most previous approaches which only focus on producing discriminative motion and appearance models for all targets, we further consider discriminative features for distinguishing difficult pairs of targets. The tracking problem is formulated using an online learned CRF model, and is transformed into an energy minimization problem. The energy functions include a set of unary functions that are based on motion and appearance models for discriminating all targets, as well as a set of pairwise functions that are based on models for differentiating corresponding pairs of tracklets. The online CRF approach is more powerful at distinguishing spatially close targets with similar appearances, as well as in tracking targets in presence of camera motions. An efficient algorithm is introduced for finding an association with low energy cost. We present results on four public data sets, and show significant improvements compared with several state-of-art methods.

Keywords

Multi-target trackingOnline learned CRFAppearance and motion patternsAssociation based tracking

Supplementary material

View video

Supplementary material 1 (avi 5068 KB)

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.Institute for Robotics and Intelligent SystemsUniversity of Southern CaliforniaLos AngelesUSA