Real-time object detection based on the improved boosted features

Xiaomei Li; Fuguo Zhu

doi:10.1117/12.832482

30 October 2009 Real-time object detection based on the improved boosted features

Xiaomei Li, Fuguo Zhu

Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74950C (2009) https://doi.org/10.1117/12.832482
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China

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

Citation Download Citation

Xiaomei Li and Fuguo Zhu "Real-time object detection based on the improved boosted features", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74950C (30 October 2009); https://doi.org/10.1117/12.832482

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available