In this paper, we address the problem of detecting pedestrians in crowded real-world scenes with severe overlaps. Our basic premise is that this problem is too difficult for any type of model or feature alone. Instead, we present an algorithm that integrates evidence in multiple iterations and from different sources. The core part of our method is the combination of local and global cues via probabilistic top-down segmentation. Altogether, this approach allows examining and comparing object hypotheses with high precision down to the pixel level. Qualitative and quantitative results on a large data set confirm that our method is able to reliably detect pedestrians in crowded scenes, even when they overlap and partially occlude each other. In addition, the flexible nature of our approach allows it to operate on very small training sets.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Pedestrian detection in crowded scenes


    Contributors:
    Leibe, B. (author) / Seemann, E. (author) / Schiele, B. (author)


    Publication date :

    2005-01-01


    Size :

    992620 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Pedestrian Detection and Counting in Crowded Scenes

    Li, Juan / He, Qinglian / Yang, Liya et al. | British Library Conference Proceedings | 2018


    Pedestrian Detection and Counting in Crowded Scenes

    Li, Juan / He, Qinglian / Yang, Liya et al. | Springer Verlag | 2017


    Robust pedestrian detection and tracking in crowded scenes

    Kelly, P. / O'Connor, N. E. / Smeaton, A. F. | British Library Online Contents | 2009


    Occlusion-Robust Pedestrian Tracking in Crowded Scenes

    Gastel, Jeroen S. van / Zwemer, Matthijs H. / Wijnhoven, Rob G. J. et al. | IEEE | 2015