Share Email Print

Proceedings Paper

Combining shape and texture features for infrared pedestrian detection
Author(s): Hao Cui; Biao Li; Zhenkang Shen
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper presents a robust pedestrian detection algorithm that works on infrared imageries. Our algorithm is applicable to images captured from surveillance infrastructure as well as moving platforms. Firstly, we introduce a local binary pattern (LBP) texture feature for infrared pedestrian representation. Secondly, motivated by the recent success of multiple cues pedestrian detection in visual imagery, we combine both shape and binary pattern texture features for effective infrared pedestrian description, providing a level of robustness to variations in pedestrian shape and appearance in infrared images. Finally, a support vector machine (SVM) classifier is utilized to classify sub-windows into pedestrians or background. Experimental results demonstrate the robustness and effectiveness of our method.

Paper Details

Date Published: 8 December 2011
PDF: 7 pages
Proc. SPIE 8002, MIPPR 2011: Multispectral Image Acquisition, Processing, and Analysis, 80021D (8 December 2011); doi: 10.1117/12.902013
Show Author Affiliations
Hao Cui, National Univ. of Defense Technology (China)
Biao Li, National Univ. of Defense Technology (China)
Zhenkang Shen, National Univ. of Defense Technology (China)

Published in SPIE Proceedings Vol. 8002:
MIPPR 2011: Multispectral Image Acquisition, Processing, and Analysis
Faxiong Zhang; Faxiong Zhang, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?