Feature selection for real-time tracking

被引：0
作者：
Hsu, D. Frank [1 ]
Lyons, Damian M. [1 ]
Ai, Jizhou [1 ]
机构：
[1] Fordham Univ, Dept Comp & Informat Sci, Robot & Comp Vis Lab, Bronx, NY 10458 USA
来源：
MULTISENSOR, MULTISOURCE INFORMATIN FUSION: ARCHITECTURES, ALGORITHMS, AND APPLICATIONS 2006 | 2006年 / 6242卷
关键词：
video surveillance; target tracking; feature selection; sensory fusion;
D O I：
10.1117/12.669177
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We address the problem of selecting features to improve automated video tracking of targets that undergo multiple mutual occlusions. As targets are occluded, different feature subsets and combinations of those features are effective in identifying the target and improving tracking performance. We use Combinatorial Fusion Analysis to develop a metric to dynamically select which subset of features will produce the most accurate tracking. In particular we show that the combination of a pair of features A and B will improve the accuracy only if (a) A and B have relative high performance, and (b) A and B are diverse. We present experimental results to illustrate the performance of the proposed metric.
引用
收藏
页数：8
相关论文
共 29 条
[1]  
Bar-Shalom Y., 1988, Tracking and Data Association
[2]  
Brown G., 2005, Information Fusion, V6, P5, DOI 10.1016/j.inffus.2004.04.004
[3]  
COLLINS B, 2003, IEEE INT C COMP VIS
[4]  
COX IJ, 1994, INT C PATT RECOG, P437, DOI 10.1109/ICPR.1994.576318
[5]  
DASARTHY BV, 2001, INFORM FUSION, V1, P5
[6]  
HO TK, 1994, IEEE T PATTERN ANAL, V16, P66, DOI 10.1109/34.273716
[7]   Comparing rank and score combination methods for data fusion in information retrieval [J].
Hsu D.F. ;
Taksa I. .
Information Retrieval, 2005, 8 (3) :449-480
[8]  
Hsu DF, 2004, I-SPAN 2004: 7TH INTERNATIONAL SYMPOSIUM ON PARALLEL ARCHITECTURES, ALGORITHMS AND NETWORKS, PROCEEDINGS, P557
[9]   RAF: A dynamic and efficient approach to fusion for multitarget tracking in CCTV surveillance [J].
Hsu, DF ;
Lyons, DM ;
Usandivaras, C ;
Montero, F .
PROCEEDINGS OF THE IEEE INTERNATIONAL CONFERENCE ON MULTISENSOR FUSION AND INTEGRATION FOR INTELLIGENT SYSTEMS, 2003, :269-274
[10]  
HSU DF, 2005, IN PRESS ADV DATA MI
123