Conventional tracking approaches assume proximity in space, time and appearance of objects in successive observations. However, observations of objects are often widely separated in time and space when viewed from multiple non-overlapping cameras. To address this problem, we present a novel approach for establishing object correspondence across non-overlapping cameras. Our multicamera tracking algorithm exploits the redundance in paths that people and cars tend to follow, e.g. roads, walk-ways or corridors, by using motion trends and appearance of objects, to establish correspondence. Our system does not require any inter-camera calibration, instead the system learns the camera topology and path probabilities of objects using Parzen windows, during a training phase. Once the training is complete, correspondences are assigned using the maximum a posteriori (MAP) estimation framework. The learned parameters are updated with changing trajectory patterns. Experiments with real world videos are reported, which validate the proposed approach.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Tracking across multiple cameras with disjoint views


    Contributors:
    Javed, (author) / Rasheed, (author) / Shafique, (author) / Shah, (author)


    Publication date :

    2003-01-01


    Size :

    499436 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Tracking across Multiple Cameras with Disjoint Views

    Javed, O. / Rasheed, Z. / Shafique, K. et al. | British Library Conference Proceedings | 2003


    Tracking people across disjoint camera views by an illumination-tolerant appearance representation

    Madden, C. / Cheng, E. D. / Piccardi, M. | British Library Online Contents | 2007


    Continuously Tracking Objects Across Multiple Widely Separated Cameras

    Cai, Yinghao / Chen, Wei / Huang, Kaiqi et al. | Springer Verlag | 2007


    Persistent Objects Tracking Across Multiple Non Overlapping Cameras

    Kang, Jinman / Cohen, Isaac / Medioni, Gerard | IEEE | 2005