A multi-object motion-trackdng method for video surveillance

被引：3

作者：

Dan, Jiang ^{[1
]}

Yuan, Yu ^{[1
]}

机构：

[1] Beihang Univ, Sch Elect Informat Engn, Beijing 100000, Peoples R China

来源：

SNPD 2007: EIGHTH ACIS INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING, ARTIFICIAL INTELLIGENCE, NETWORKING, AND PARALLEL/DISTRIBUTED COMPUTING, VOL 1, PROCEEDINGS | 2007年

关键词：

motion tracking; foreground detection; similarity function;

D O I：

10.1109/SNPD.2007.17

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, a multi-object motion-tracking method based both on region and feature tracking is proposed for the purpose of real-time tracking in video surveillance system. Moving object is detected through foreground detection. Then we extract three features of each moving objects such as centroid, area, and average luminance. At last, the similarity function is applied to tracking. It is proved that the method has good performance under dynamic circumstances for real-time tracking.

引用

页码：402 / +

页数：2

共 7 条

[1] Cardboard people: A parameterized model of articulated image motion [J].

Ju, SX ;

Black, MJ ;

Yacoob, Y .

PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, 1996, :38-44

[2]

KARAOULOVA I, P BRIT MACH VIS C, P352

[3] Tracking groups of people [J].

McKenna, SJ ;

Jabri, S ;

Duric, Z ;

Rosenfeld, A ;

Wechsler, H .

COMPUTER VISION AND IMAGE UNDERSTANDING, 2000, 80 (01) :42-56

[4]

Nelson R., 1994, WORKSHOP MOTION NONR, P77

[5]

Ostu N., 1979, IEEE T SYST MAN CYB, V9, P62, DOI DOI 10.1109/TSMC.1979.4310076

[6]

PETERFREUND N, 2000, IEEE T PATT ANAL MAC, V22

[7]

PONS NJ, 2002, IEEE T ELECT LETT, P409

← 1 →