Motion-based segmentation and region tracking in image sequences

被引：39

作者：

Badenas, J ^{[1
]}

Sanchiz, JM ^{[1
]}

Pla, F ^{[1
]}

机构：

[1] Univ Castellon, Castellon 12071, Spain

来源：

PATTERN RECOGNITION | 2001年 / 34卷 / 03期

关键词：

temporal integration; motion segmentation; Kalman filter; traffic monitoring; motion estimation;

D O I：

10.1016/S0031-3203(00)00014-5

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents an algorithm for segmenting and tracking moving objects in a scene. Temporal information provided by a region tracking strategy is integrated for improving frame-to-frame motion segmentation. The method has been applied to a traffic monitoring system and it provides facilities such as estimating trajectories of vehicles, detecting stopped vehicles, counting vehicles and estimating the mean velocity of the traffic. (C) 2001 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

引用

页码：661 / 670

页数：10

共 25 条

[1]

[Anonymous], P 8 BRIT MACH VIS C

[2]

Badenas Jorge, 1997, P INT C IM AN PROC I, P502

[3]

Bar-Shalom Y., 1988, Tracking and Data Association

[4] The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields [J].