A novel framework of multiview occlusion analysis is presented for tracking densely populated objects moving on two-dimensional plane. This paper explicitly models the spatial structure of the occlusion process between objects and its uncertainty, based on 2D silhouette-based visual angles from fixed viewpoints. The occlusion structure is defined as tangency combination between the objects and the edges of the visual angles, based on geometric constraints inherent in the visual angles. The problem is then formulated as recursive Bayesian estimation consisting of hypothesis generation/testing of the occlusion structure and the estimation of posterior probability distribution for the object states including position and posture, on each hypothesis of the occlusion structure. For implementing the proposed framework, we develop a novel type of particle filter that supports multiple state distributions. Experiments using synthetic and real data show the robustness of the framework even in the face of severe occlusions.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multiview occlusion analysis for tracking densely populated objects based on 2-D visual angles


    Contributors:
    Otsuka, K. (author) / Mukawa, N. (author)


    Publication date :

    2004-01-01


    Size :

    924140 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Multiview Occlusion Analysis for Tracking Densely Populated Objects Based on 2-D Visual Angles

    Otsuka, K. / Mukawa, N. / IEEE Computer Society | British Library Conference Proceedings | 2004



    Human Perception of Collision and Safety in Densely Populated Airspaces

    Zahed, Muhammad Junayed Hasan / Gonzalez, Bianca Selena / Langelaan, Jack W. et al. | AIAA | 2025



    Improving the Reliability of Street Networks in Highly Densely Populated Urban Areas

    Li, Y. / Tsukaguchi, H. | British Library Conference Proceedings | 2003