|
Interacting
Object Tracking in Crowded Urban Areas
Chieh-Chih Wang,
Tzu-Chien Lo and Shao-Wen Yang
Abstract |
Tracking
in crowded urban areas is a daunting task. High crowdedness causes
challenging data association problems. Different motion patterns from a
wide variety of moving objects make motion modeling difficult.
Accompanying with traditional motion modeling techniques, this paper
introduces a scene interaction model and a neighboring object
interaction model to respectively take long-term and short-term
interactions between the tracked objects and its surroundings into
account. With the use of the interaction models, anomalous activity
recognition is accomplished easily. In addition, move-stop hypothesis
tracking is applied to deal with move-stop-move maneuvers. All these
approaches are seamlessly intergraded under the variable-structure
multiple-model estimation framework. The proposed approaches have been
demonstrated using data from a laser scanner mounted on the PAL1 robot
at a crowded intersection. Interacting pedestrians, bicycles,
motorcycles, cars and trucks are successfully tracked in difficult
situations with occlusion.
|
Download |
|
The full paper is available in PDF.
The video is available here.
The datasets
|
Bibtex |
@inproceedings{Wang07a,
author = {Chieh-Chih Wang and Tzu-Chien Lo and
Shao-Wen Yang},
title = {Interacting Object Tracking in Crowded
Urban Areas},
booktitle = {Proceedings of the IEEE International Conference on Robotics
and
Automation (ICRA'07)},
address = {Roma, Italy},
month = {April},
year = {2007},
}
|
|
|
Copyright ©
Chieh-Chih
(Bob) Wang 2007. All right reserved.
Last Updated: Feb. 9, 2007.
|
|