Position estimation of multiple objects in a 3D environment poses a challenging task, even more so in the presence of occlusions due to infrastructure. In this paper we present a method to accurately localize up to 10 moving pedestrians by fusing the output of a Sparsity Driven Detector with volumes generated by a Shape-from-Silhouette approach. We also show how occlusion information from a 3D map of the environment can be integrated into our algorithm to further improve performance. We investigate the influence of different camera heights and image sizes on the optimization problem and demonstrate real-time capability for certain configurations. Additionally, our code is made publicly available under an open source license.1


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Fusing Shape-from-Silhouette and the Sparsity Driven Detector for Camera-Based 3D Multi-Object Localization with Occlusions


    Contributors:


    Publication date :

    2019-10-01


    Size :

    782000 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Shape-from-Silhouette with Two Mirrors and an Uncalibrated Camera

    Forbes, K. / Nicolls, F. / de Jager, G. et al. | British Library Conference Proceedings | 2006


    Shape from inconsistent silhouette

    Landabaso, J. L. / Pardas, M. / Casas, J. R. | British Library Online Contents | 2008


    Simulating object occlusions

    DOLAN JAMES GRAHAM | European Patent Office | 2024

    Free access


    Octree-Based Fusion of Shape from Silhouette and Shape from Structured Light

    Kampel, M. / Tosovic, S. / Sablatnig, R. | British Library Conference Proceedings | 2002