Pedestrian Detection in Far-Infrared Daytime Images Using a Hierarchical Codebook of SURF

Sensors

Bassem Besbes¹  Alexandrina Rogozan²  Adela-Maria Rus²  Abdelaziz Bensrhair²  Alberto Broggi³ 

[1] Diotasoft, 15 Boulevard Emile Baudot, Massy 91300, France; E-Mail:;LITIS Laboratory, National Institute of Applied Sciences, 76801 Saint-Etienne-du-Rouvray Cedex, France; E-Mail:;Dipartimento di Ingegneria dell' Informazione, Universita di Parma, Parco Area delle Scienze, Parma 181/a 43124, Italy; E-Mail:

关键词: pedestrian detection;    far-infrared images;    scale-invariant feature matching;    SURF;    hierarchical codebook;    SVM;    pedestrian classification and tracking;   

DOI  :  10.3390/s150408570

来源: mdpi

【 摘 要 】

One of the main challenges in intelligent vehicles concerns pedestrian detection for driving assistance. Recent experiments have showed that state-of-the-art descriptors provide better performances on the far-infrared (FIR) spectrum than on the visible one, even in daytime conditions, for pedestrian classification. In this paper, we propose a pedestrian detector with on-board FIR camera. Our main contribution is the exploitation of the specific characteristics of FIR images to design a fast, scale-invariant and robust pedestrian detector. Our system consists of three modules, each based on speeded-up robust feature (SURF) matching. The first module allows generating regions-of-interest (ROI), since in FIR images of the pedestrian shapes may vary in large scales, but heads appear usually as light regions. ROI are detected with a high recall rate with the hierarchical codebook of SURF features located in head regions. The second module consists of pedestrian full-body classification by using SVM. This module allows one to enhance the precision with low computational cost. In the third module, we combine the mean shift algorithm with inter-frame scale-invariant SURF feature tracking to enhance the robustness of our system. The experimental evaluation shows that our system outperforms, in the FIR domain, the state-of-the-art Haar-like Adaboost-cascade, histogram of oriented gradients (HOG)/linear SVM (linSVM) and MultiFtrpedestrian detectors, trained on the FIR images.

【 授权许可】

CC BY   
© 2015 by the authors; licensee MDPI, Basel, Switzerland.