The automatic detection and tracking of pedestrians in imagery constitute important and challenging problems both in computer vision and driver assistance systems. We address these problems for the case of a forward looking monocular infrared camera under strong vehicle induced camera motion. An integrated detection & tracking strategy is introduced based on a state-of-the-art feature based object detector originally developed for images in the visual spectrum. The proposed pedestrian detection algorithm can be applied to both infrared and visual imagery. We show the difficulties arising from the specifics of infrared data under strong camera motion and how to tackle these problems by replacing common motion models like the Kalman filter by a feature matching approach.


    Access

    Download


    Export, share and cite



    Title :

    Pedestrian tracking in infrared from moving vehicles


    Contributors:
    Jüngling, K. (author) / Arens, M. (author)

    Conference:

    2010


    Publication date :

    2010


    Size :

    8 pages



    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Pedestrian Tracking in Infrared from Moving Vehicles, pp. 470-477

    Jungling, K. / Arens, M. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2010


    Pedestrian tracking from a moving vehicle

    Philomin, V. / Duraiswami, R. / Davis, L. | IEEE | 2000


    Pedestrian tracking from a moving vehicle

    Philomin, V. / Duraiswami, R. / Davis, L. et al. | British Library Conference Proceedings | 2000


    Pedestrian tracking using thermal infrared imaging

    Goubet, Emmanuel / Katz, Joseph / Porikli, Fatih | SPIE | 2006


    Multi-cue Pedestrian Detection and Tracking from a Moving Vehicle

    Gavrila, D. M. / Munder, S. | British Library Online Contents | 2007