Pedestrian detection is an important but challenging component of an Intelligent Transportation System. In this paper, we describe a pedestrian detection system based on a monocular vision with a Far-Infrared camera (FIR). We propose an original feature representation, called Intensity Self Similarity (ISS), adapted to pedestrian detection in FIR images. The ISS representation is based on the relative intensity self similarity within a pedestrian region of interest (ROI) hypothesis. Our system consists of two components. The first component generates pedestrian ROI hypothesis by exploiting the specific characteristics of FIR images, where pedestrian shapes may vary in large scale, but heads appear usually as light regions. Pedestrian ROI are detected, with high recall rate, due to a Hierarchical Codebook (HC) of Speeded-Up Robust Features (SURF) located in light head regions. The second component consists of pedestrian hypothesis validation, by using a pedestrian full-body classification based on the ISS representation, with Support Vector Machine (SVM). For classification, we retained two feature descriptors: the Histogram of Oriented Gradients (HOG) descriptor and the original ISS feature representation that we proposed for FIR images. The early fusion of these two features enhances significantly the system precision, attaining an F-measure for the pedestrian class of 97.7%. Moreover, this feature fusion outperforms the state-of-the-art SURF descriptor proposed previously. The experimental evaluation shows that our pedestrian detector is also robust, since it performs well in detecting pedestrians even in large scale and crowded real-world scenes.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Intensity self similarity features for pedestrian detection in Far-Infrared images


    Contributors:


    Publication date :

    2012-06-01


    Size :

    688239 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Intensity Self Similarity Features for Pedestrian Detection in Far-Infrared Images

    Miron, A. / Besbes, B. / Rogozan, A. et al. | British Library Conference Proceedings | 2012


    Pedestrian detection in infrared images

    Bertozzi, M. / Broggi, A. / Grisleri, P. et al. | IEEE | 2003


    Pedestrian Detection and Tracking in Far Infrared Images

    Yasuno, M. / Sasaki, R. / Yasuda, N. et al. | British Library Conference Proceedings | 2005


    Pedestrian Detection using Infrared images and Histograms of Oriented Gradients

    Suard, F. / Rakotomamonjy, A. / Bensrhair, A. et al. | IEEE | 2006


    Pedestrian Detection using Infrared images and Histograms of Oriented Gradients

    Suard, F. / Rakotomamonjy, A. / Bensrhair, A. et al. | British Library Conference Proceedings | 2006