Share Email Print

Optical Engineering

Robust object detection with real-time fusion of multiview foreground silhouettes
Author(s): Ming Xu; Dongyong Chen; Tianyuan Jia; Jie Ren; Jeremy S. Smith; Zhechi Liu
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

An object detection algorithm using multiple cameras is proposed. The information fusion is based on homography mapping of the foreground information from multiple cameras and for multiple parallel planes. Unlike the most recent algorithms, which transmit and project foreground bitmaps, it approximates each foreground silhouette with a polygon and projects the polygon vertices only. In addition, an alternative approach to estimating the homographies for multiple parallel planes is presented. It is based on the observed pedestrians and does not resort to vanishing-point estimation. The ability of this algorithm to remove cast shadows in moving object detection is also investigated. The results on open video datasets are presented as well.

Paper Details

Date Published: 6 April 2012
PDF: 14 pages
Opt. Eng. 51(4) 047202 doi: 10.1117/1.OE.51.4.047202
Published in: Optical Engineering Volume 51, Issue 4
Show Author Affiliations
Ming Xu, Xi'an Jiaotong Univ. (China)
Dongyong Chen, Xi'an Jiaotong Univ. (China)
Tianyuan Jia, Xi'an Jiaotong Univ. (China)
Jie Ren, Univ. of Liverpool (United Kingdom)
Jeremy S. Smith, Univ. of Liverpool (United Kingdom)
Zhechi Liu, Univ. of Liverpool (United Kingdom)

© SPIE. Terms of Use
Back to Top