Model based human motion tracking using probability evolutionary algorithm

被引：17

作者：

Shen, Shuhan ^{[1
]}

Tong, Minglei ^{[1
]}

Deng, Haolong ^{[1
]}

Liu, Yuncai ^{[1
]}

Wu, Xiaojun ^{[2
]}

Wakabayashi, Kaoru ^{[2
]}

Koike, Hideki ^{[2
]}

机构：

[1] Shanghai Jiao Tong Univ, Inst Image Proc & Pattern Recognit, Shanghai, Peoples R China

[2] NTT Corp, NTT Cyber Space Labs, Hikarinooka Yokosuka, Kanagawa, Japan

来源：

PATTERN RECOGNITION LETTERS | 2008年 / 29卷 / 13期

基金：

中国国家自然科学基金;

关键词：

tracking; human tracking; probability evolutionary algorithm;

D O I：

10.1016/j.patrec.2008.06.014

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A novel evolutionary algorithm called probability evolutionary algorithm (PEA), and a method based on PEA for visual tracking of human motion are presented. PEA is inspired by estimation of distribution algorithms and quantum-inspired evolutionary algorithm, and it has a good balance between exploration and exploitation with very fast computation speed. The individual in PEA is encoded by the probability vector, defined as the smallest unit of information, for the probabilistic representation. The observation step is used in PEA to obtain the observed states of the individual, and the update operator is used to evolve the individual. In the PEA based human tracking framework, tracking is considered to be a function optimization problem, so the aim is to optimize the matching function between the model and the image observation. Since the matching function is a very complex function in high-dimensional space, PEA is used to optimize it. Experiments on 2D and 3D human motion tracking demonstrate the effectiveness, significance and computation efficiency of the proposed human tracking method. (C) 2008 Elsevier B.V. All rights reserved.

引用

页码：1877 / 1886

页数：10

共 31 条

[1] [Anonymous], 2000, P GENETIC EVOLUTIONA
[2] Balan A. O., 2005, Proceedings. 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance (VS-PETS) (IEEE Cat. No. 05EX1178), P349
[3] BALAN AO, 2006, P 2006 IEEE COMP SOC, V1, P758
[4] Baluja S., 1997, Proceedings of the 14'th International Conference on Machine Learning, P30
[5] Baluja S., 1994, CMUCS94163
[6] BREIT H, 2003, P IEEE INT C IM PROC, V3, P133
[7] Collins R., 2000, VSAM FINAL REP, V5, P1
[8] Deutscher J, 2001, PROC CVPR IEEE, P669
[9] 3-D model-based tracking of humans in action: A multi-view approach
Gavrila, DM
Davis, LS
[J]. 1996 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1996, : 73 - 80
[10] Quantum-inspired evolutionary algorithm for a class of combinatorial optimization
Han, KH
Kim, JH
[J]. IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2002, 6 (06) : 580 - 593

← 1 2 3 4 →