Patches-based Markov random field model for multiple object tracking under occlusion

In multiple object tracking, it is challenging to maintain the correct tracks of objects in the presence of occlusions. The paper proposes a new method to this problem, building on the patch representation of object appearance. We formulate multiple object tracking as classification tasks which comp...

Full description

Saved in:
Bibliographic Details
Published in:Signal processing 2010-05, Vol.90 (5), p.1518-1529
Main Authors: Wu, Mingjun, Peng, Xianrong, Zhang, Qiheng, Zhao, Rujin
Format: Article
Language:English
Subjects:
Appearance model
Applied sciences
Classification
Dealing
Detection, estimation, filtering, equalization, prediction
Exact sciences and technology
Information, signal and communications theory
Markov random field
Mathematical models
Multiple object tracking
Occlusion
Optimization
Pattern recognition
Representations
Signal and communications theory
Signal processing
Signal, noise
Tasks
Telecommunications and information theory
Tracking
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In multiple object tracking, it is challenging to maintain the correct tracks of objects in the presence of occlusions. The paper proposes a new method to this problem, building on the patch representation of object appearance. We formulate multiple object tracking as classification tasks which competitively use the appearance models of the interacting objects. To obtain the optimal configuration of classification, a patches-based MAP-MRF decision framework is presented to make a global inference based on local spatial information existing between adjacent patches and the maximum a posteriori solution is evaluated exactly with graph cuts. As a result, accurate object identification is achieved. Extensive experiments on several difficult sequences validate that the proposed method is effective in dealing with multiple object occlusion, and comparative results show that our method outperforms the previous methods.
ISSN:0165-1684
1872-7557
DOI:10.1016/j.sigpro.2009.10.023