Mask Particle Filter for Similar Objects Tracking

Authors:
Huaping Liu;Fuchun Sun;Meng Gao
Affiliations:
Department of Computer Science and Technology, Tsinghua University, Beijing, China 100084 and State Key Laboratory of Intelligent Technology and Systems, Beijing, China 100084;Department of Computer Science and Technology, Tsinghua University, Beijing, China 100084 and State Key Laboratory of Intelligent Technology and Systems, Beijing, China 100084;Shijiazhuang Railway Institute, Shijiazhung, China 050043
Venue:
ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part III
Year:
2009

Citing 6
Cited 0

Color-Based Probabilistic Tracking

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Integral Histogram: A Fast Way To Extract Histograms in Cartesian Spaces

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
MCMC-Based Particle Filtering for Tracking a Variable Number of Interacting Targets

IEEE Transactions on Pattern Analysis and Machine Intelligence
An integrated Monte Carlo data association framework for multi-object tracking

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 01
Vision-Based Preceding Vehicle Detection and Tracking

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 02
Real-Time Distributed Multi-Object Tracking Using Multiple Interactive Trackers and a Magnetic-Inertia Potential Model

IEEE Transactions on Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

Tracking appearance similar objects is very challenging. Conventional approaches often encounter "hijack" problem. That is to say, the tracking results for the smaller objects will be attracted to the larger one in the close vicinity. In this paper, we propose a decentralized particle filter approach for similar objects tracking. When the objects are close, the tracking results for the larger one will be masked and its influence will be eliminated. In principle, the tracker for the smaller object needs to be run two times, which increase the time costs. To tackle this, we construct the integral image for the mask region and dramatically decrease the calculation time of the evaluation of likelihood functions in the masked image. Experimental results show that the proposed approach effectively avoids "hijack" problems.