by Zang, Q and Klette, R
Abstract:
A video surveillance system combines three phases of data processing: moving object extraction, moving object recognition and tracking, and decisions about actions. The extraction of moving objects, followed by object tracking and recognition, can often be defined in very general terms. The final component is largely depended upon the application context, such as pedestrian counting or traffic monitoring. Occlusion is the common problem in object tracking and counting. We propose a hybrid method that uses feature-based object tracking in traffic surveillance. This is to identify partially occluded vehicles and track them continuously. In this paper, we review previous research on moving object tracking techniques, analyze some experimental results, and finally provide our conclusions to improve performances of traffic surveillance systems. One stationary camera has been used.
Reference:
Object classification and tracking in traffic scenes (Zang, Q and Klette, R), In IASTED International Conference on Computer Graphics and Imaging (Hamza, MH, ed.), 2003.
Bibtex Entry:
@inproceedings{zang2003objectscenes,
author = "Zang, Q and Klette, R",
booktitle = "IASTED International Conference on Computer Graphics and Imaging",
editor = "Hamza, MH",
pages = "232--237",
title = "Object classification and tracking in traffic scenes",
year = "2003",
abstract = "A video surveillance system combines three phases of data processing: moving object extraction, moving object recognition and tracking, and decisions about actions. The extraction of moving objects, followed by object tracking and recognition, can often be defined in very general terms. The final component is largely depended upon the application context, such as pedestrian counting or traffic monitoring. Occlusion is the common problem in object tracking and counting. We propose a hybrid method that uses feature-based object tracking in traffic surveillance. This is to identify partially occluded vehicles and track them continuously. In this paper, we review previous research on moving object tracking techniques, analyze some experimental results, and finally provide our conclusions to improve performances of traffic surveillance systems. One stationary camera has been used.",
isbn = "0889863768",
keyword = "Gaussian mixture",
keyword = "Image segmentation",
keyword = "Vehicle tracking",
language = "eng",
}