Discriminatively trained particle filters for complex multi-object tracking
- 1 June 2009
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
This work presents a discriminative training method for particle filters in the context of multi-object tracking. We are motivated by the difficulty of hand-tuning the many model parameters for such applications and also by results in many application domains indicating that discriminative training is often superior to generative training methods. Our learning approach is tightly integrated into the actual inference process of the filter and attempts to directly optimize the filter parameters in response to observed errors. We present experimental results in the challenging domain of American football where our filter is trained to track all 22 players throughout football plays. The training method is shown to significantly improve performance of the tracker and to significantly outperform two recent particle-based multi-object tracking methods.Keywords
This publication has 10 references indexed in Scilit:
- On learning linear ranking functions for beam searchPublished by Association for Computing Machinery (ACM) ,2007
- Improved Video Registration using Non-Distinctive Local Image FeaturesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- CRF-Filters: Discriminative Particle Filters for Sequential State EstimationProceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (cat. No.01ch37164), 2007
- Mixture-of-Parts Pictorial Structures for Objects with Variable Part SetsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- A discriminative model for tree-to-tree translationPublished by Association for Computational Linguistics (ACL) ,2006
- MCMC-based particle filtering for tracking a variable number of interacting targetsIeee Transactions On Pattern Analysis and Machine Intelligence, 2005
- Learning as search optimizationPublished by Association for Computing Machinery (ACM) ,2005
- Support vector machine learning for interdependent and structured output spacesPublished by Association for Computing Machinery (ACM) ,2004
- Incremental parsing with the perceptron algorithmPublished by Association for Computational Linguistics (ACL) ,2004
- Discriminative training methods for hidden Markov modelsPublished by Association for Computational Linguistics (ACL) ,2002