Multi-target Tracking Using Hough Forest Random Field
Jun Xiang1, Nong Sang1, Jianhua Hou2, Rui Huang1, Changxin Gao1,*
1National Key Laboratory of Science and Technology on Multispectral Information Processing,
School of Automation, Huazhong University of Science and Technology, Wuhan, 430074, China
2Hubei Key Laboratory of Intelligent Wireless Communications,
South-central University for nationalities, Wuhan, 430074, China
Abstract
This paper presents a novel tracking-by-detection approach for multi-target tracking. There are two major steps in our framework: data association to form global tracklet association, followed by trajectory estimation to deal with the remaining gaps. In the first step, we formulate tracklet association as an inference problem in a Hough Forest Random Field (HFRF), which combines Hough Forest (HF) and Conditional Random Field (CRF), and allows us to model both local and global tracklet relationships in one unified model. In the second step, we improve the Reversible-Jump Markov Chain Monte Carlo (RJMCMC) particle filtering method with explicit mutualocclusion reasoning to fill in the remaining gaps from the first step and increase the overall tracking precision. Extensive experiments have been conducted on five public datasets, and the performance is comparable to the state of the art, if not better.
Related Paper
Jun Xiang, Nong Sang, Jianhua Hou, Rui Huang, Changxin Gao*, "Multi-target Tracking Using Hough Forest Random Field," IEEE Transactions on Circuits and Systems for Video Technology, to appear, 2016. (paper) (bibtex) DOI: 10.1109/TCSVT.2015.2489438
Video Results
1. Results on TUD-Stadtmitte, PETS S2.L1, ETH BAHNHOF, and ETH SUNNY DAY (Video)
2. Results on Parking Lot (Video)
3. Town Centre (Video)
_______________________
If you have any questions, please contact Changxin Gao, cgao at hust dot edu dot cn