Detecting moving objects using stationary cameras is an important precursor to many activity recognition, object recognition and tracking algorithms. In this paper, three innovations are presented over existing approaches. Firstly, the model of the intensities of image pixels as independently distributed random variables is challenged and it is asserted that useful correlation exists in the intensities of spatially proximal pixels. This correlation is exploited to sustain high levels of detection accuracy in the presence of nominal camera motion and dynamic textures. By using a non-parametric density estimation method over a joint domain-range representation of image pixels, multi-modal spatial uncertainties and complex dependencies between the domain (location) and range (color) are directly modeled. Secondly, temporal persistence is proposed as a detection criteria. Unlike previous approaches to object detection which detect objects by building adaptive models of the only background, the foreground is also modeled to augment the detection of objects (without explicit tracking) since objects detected in a preceding frame contain substantial evidence for detection in a current frame. Third, the background and foreground models are used competitively in a MAP-MRF decision framework, stressing spatial context as a condition of pixel-wise labeling and the posterior function is maximized efficiently using graph cuts. Experimental validation of the proposed method is presented on a diverse set of dynamic scenes.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Bayesian object detection in dynamic scenes


    Contributors:
    Sheikh, Y. (author) / Shah, M. (author)


    Publication date :

    2005-01-01


    Size :

    381366 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Dropped object detection in crowded scenes

    Bhatnagar, Deepti, S.M. Massachusetts Institute of Technology | DSpace@MIT | 2009

    Free access

    Interpretation of complex scenes using dynamic tree-structure Bayesian networks

    Todorovic, S. / Nechyba, M. C. | British Library Online Contents | 2007


    Multi-object reconstruction from dynamic scenes: An object-centered approach

    Shin, Y. M. / Cho, M. / Lee, K. M. | British Library Online Contents | 2013


    Detection of Extended Object Images in Optical Scenes

    Furman, Y. A. / Khafizov, R. G. | British Library Online Contents | 1998