Paper
8 December 2011 Combining shape and texture features for infrared pedestrian detection
Hao Cui, Biao Li, Zhenkang Shen
Author Affiliations +
Proceedings Volume 8002, MIPPR 2011: Multispectral Image Acquisition, Processing, and Analysis; 80021D (2011) https://doi.org/10.1117/12.902013
Event: Seventh International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2011), 2011, Guilin, China
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.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hao Cui, Biao Li, and Zhenkang Shen "Combining shape and texture features for infrared pedestrian detection", Proc. SPIE 8002, MIPPR 2011: Multispectral Image Acquisition, Processing, and Analysis, 80021D (8 December 2011); https://doi.org/10.1117/12.902013
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Infrared radiation

Infrared imaging

Infrared detectors

Binary data

Surveillance

Visualization

Thermography

Back to Top