Face association across unconstrained video frames using conditional random fields
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Multiple target tracking using frame triplets
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Identification and tracking of players in sport videos
Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
Tracking with a mixed continuous-discrete Conditional Random Field
Computer Vision and Image Understanding
Multi-target tracking on confidence maps: An application to people tracking
Computer Vision and Image Understanding
People reidentification in surveillance and forensics: A survey
ACM Computing Surveys (CSUR)
Visual tracking via weakly supervised learning from multiple imperfect oracles
Pattern Recognition
Multi-Target Tracking by Online Learning a CRF Model of Appearance and Motion Patterns
International Journal of Computer Vision
Hi-index | 0.00 |
We propose a learning-based Conditional Random Field (CRF) model for tracking multiple targets by progressively associating detection responses into long tracks. Tracking task is transformed into a data association problem, and most previous approaches developed heuristical parametric models or learning approaches for evaluating independent affinities between track fragments (tracklets). We argue that the independent assumption is not valid in many cases, and adopt a CRF model to consider both tracklet affinities and dependencies among them, which are represented by unary term costs and pairwise term costs respectively. Unlike previous methods, we learn the best global associations instead of the best local affinities between tracklets, and transform the task of finding the best association into an energy minimization problem. A RankBoost algorithm is proposed to select effective features for estimation of term costs in the CRF model, so that better associations have lower costs. Our approach is evaluated on challenging pedestrian data sets, and are compared with state-of-art methods. Experiments show effectiveness of our algorithm as well as improvement in tracking performance.