Pair normalized channel feature and statistics-based learning for high-performance pedestrian detection

Bobo Zeng; Guijin Wang; Zhiwei Ruan; Xinggang Lin; Long Meng

doi:10.1117/1.OE.51.7.077206

17 July 2012 Pair normalized channel feature and statistics-based learning for high-performance pedestrian detection

Bobo Zeng, Guijin Wang, Zhiwei Ruan, Xinggang Lin, Long Meng

Author Affiliations +

Optical Engineering, Vol. 51, Issue 7, 077206 (July 2012). https://doi.org/10.1117/1.OE.51.7.077206

Abstract

High-performance pedestrian detection with good accuracy and fast speed is an important yet challenging task in computer vision. We design a novel feature named pair normalized channel feature (PNCF), which simultaneously combines and normalizes two channel features in image channels, achieving a highly discriminative power and computational efficiency. PNCF applies to both gradient channels and color channels so that shape and appearance information are described and integrated in the same feature. To efficiently explore the formidably large PNCF feature space, we propose a statistics-based feature learning method to select a small number of potentially discriminative candidate features, which are fed into the boosting algorithm. In addition, channel compression and a hybrid pyramid are employed to speed up the multiscale detection. Experiments illustrate the effectiveness of PNCF and its learning method. Our proposed detector outperforms the state-of-the-art on several benchmark datasets in both detection accuracy and efficiency.

Citation Download Citation

Bobo Zeng, Guijin Wang, Zhiwei Ruan, Xinggang Lin, and Long Meng "Pair normalized channel feature and statistics-based learning for high-performance pedestrian detection," Optical Engineering 51(7), 077206 (17 July 2012). https://doi.org/10.1117/1.OE.51.7.077206

Published: 17 July 2012

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