Share Email Print

Proceedings Paper

Real-time object detection based on the improved boosted features
Author(s): Xiaomei Li; Fuguo Zhu
Format Member Price Non-Member Price
PDF $17.00 $21.00
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

In this paper we propose a scheme which uses the saliency-based top-down visual attention model in the rapid object detection scheme based on a boosted cascade of simple features proposed by Viola et al. It can selects conspicuous locations from complex scenes in real time and some background regions of the image can be quickly discarded while the classifier can spend more computation on promising object-like regions. We use the conspicuity map and the trained classifier to decide where the targets are. A set of experiments in the domain of face detection are presented. Test results show that with this improved scheme, the detection rate is improved and the computation speed can meet the real-time requirements.Y

Paper Details

Date Published: 30 October 2009
PDF: 7 pages
Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74950C (30 October 2009); doi: 10.1117/12.832482
Show Author Affiliations
Xiaomei Li, Beijing Univ. of Posts and Telecommunications (China)
Fuguo Zhu, Beijing Univ. of Posts and Telecommunications (China)

Published in SPIE Proceedings Vol. 7495:
MIPPR 2009: Automatic Target Recognition and Image Analysis
Tianxu Zhang; Bruce Hirsch; Zhiguo Cao; Hanqing Lu, Editor(s)

© SPIE. Terms of Use
Back to Top