Abstract
The aim of this study was to design an moving object detection, localization and tracking algorithm able to detect, localize and track especially humans and vehicles. We focused on triangulation techniques to calculate the position of the detected objects in a stereo vision rig coordinates frame. For objects detection and tracking the novel algorithm, based on statistical image processing methods, was proposed. Verification of a proper operation of the elaborated method was made by conducting series of experiments. Our results indicate that the algorithm localizes, detects and tracks objects accurately for the most tested conditions.
Publisher
Trans Tech Publications, Ltd.
Subject
Condensed Matter Physics,General Materials Science,Atomic and Molecular Physics, and Optics
Reference15 articles.
1. C. Micheloni, G. L. Foresti, A robust feature tracker for active surveillance of outdoor scenes, Electronic Letters on Computer Vision and Image Analysis (2003) 21-34.
2. R. Cucchiara, A. Prati, R. Vezzani R, Advanced video surveillance with pan tilt zoom cameras, Proc. of the 6th IEEE International Workshop on Visual Surveillance (2006) 334-352.
3. W. Hu, T. Tan, L. Wang, S. Maybank, A survey on visual surveillance of object motion and behaviors, IEEE Trans. on Systems, Man, and Cybernetics 34 (2004) 334-352.
4. I. Cohen, G. Medioni, Detecting and tracking moving objects for video surveillance, Proc. IEEE Computer Vision and Pattern Recognition (1999) 1-7.
5. A. Czyżewski, G. Szwoch, P. Dalka, P. Szczuko, A. Ciarkowski, D. Ellwart, T. Merta, K. Łopatka, Ł. Kulasek, J. Wolski, Multi-Stage Video Analysis Framework, Video Surveillance (2011) 161-216.
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献