Person tracking using motion detection and optical flow
Contribuinte(s) |
Wysocki, B. Wisocki, T. |
---|---|
Data(s) |
2005
|
Resumo |
Person tracking systems to date have either relied on motion detection or optical flow as a basis for person detection and tracking. As yet, systems have not been developed that utilise both these techniques. We propose a person tracking system that uses both, made possible by a novel hybrid optical flow-motion detection technique that we have developed. This provides the system with two methods of person detection, helping to avoid missed detections and the need to predict position, which can lead to errors in tracking and mistakes when handling occlusion situations. Our results show that our system is able to track people accurately, with an average error less than four pixels, and that our system outperforms the current CAVIAR benchmark system. |
Formato |
application/pdf |
Identificador | |
Publicador |
Springer |
Relação |
http://eprints.qut.edu.au/24662/1/c24662.pdf http://www.dspcs-witsp.com/DSPCS2005/cfp_05.html Denman, Simon, Chandran, Vinod, & Sridharan, Sridha (2005) Person tracking using motion detection and optical flow. In Wysocki, B. & Wisocki, T. (Eds.) Proceedings of 8th International Symposium on DSP and Communication Systems (DSPCS'2005) and 4th Workshop on the Internet, Telecommunications and Signal Processing (WITSP'2005) Conference Porceedings, Springer, Sunshine Coast, QLD, pp. 1-6. |
Direitos |
Copyright 2005 [please consult the authors] |
Fonte |
Faculty of Built Environment and Engineering |
Palavras-Chave | #080104 Computer Vision #080106 Image Processing #Person Tracking, Motion Detection, Optical Flow |
Tipo |
Conference Paper |