Previous [ 1] [ 2] [ 3] [ 4] [ 5] [ 6] [ 7] [ 8] [ 9] [ 10] [ 11] [ 12] [ 13]

@

Journal of Information Science and Engineering, Vol. 32 No. 1, pp. 47-61 (January 2016)


Tracking Pedestrian with Multi-Component Online Deformable Part-Based Model


ZHAO LIU1,2, YI XIE1,2, MINGTAO PEI1 AND YUNDE JIA1
1Beijing Lab of Intelligent Information
School of Computer Science and Technology
Beijing Institute of Technology
Beijing, 100081 P.R. China
2Peoples Public Security University of China
Beijing, 100038 P.R. China
E-mail: zhao.liu@ppsuc.edu.cn; yxie.lhi@gmail.com; {peimt; jiayunde}@bit.edu.cn

In this paper, we present a novel online algorithm to track single pedestrian by integrating the bottom-up and top-down models. Motivated by the observation that the appearance of a pedestrian varies a lot in different perspectives or poses, the bottom-up model incorporates multiple components to represent distinct groups of the pedestrian appearances. Each component uses an online deformable part-based model (OLDPM) with one root and several shared parts to represent the flexible structure and salient local patterns of one particular appearance. The top-down model extends the bottom-up model by introducing newly created OLDPMs for uncovered new appearances. To achieve long term tracking, our paper incorporates the following methods; (i) Through an incremental support vector machine (INCSVM) associated with each component, the OLDPM can effectively adapt to the pedestrian appearance variations; (ii) OLDPM can efficiently generate match penalty maps through robust real-time pattern matching algorithm, and can search over all possible configurations in linear time by distance transforms algorithm; (iii) Parts can be shared among components to reduce the computational complexity for matching; (iv) To handle the hard negatives, the potential distracting targets are located explicitly to prevent drifting. We compare our method with four cutting edge tracking algorithms over eight visual sequences and provide quantitative and qualitative performance comparisons.

Keywords: pedestrian tracking, and-or graph model, image parsing, bottom-up, top-down

Full Text () Retrieve PDF document (201601_03.pdf)

Received September 3, 2014; accepted October 30, 2014.
Communicated by Zhi-Hua Zhou.