We present an unsupervised technique for detecting unusual activity in a large video set using many simple features. No complex activity models and no supervised feature selections are used. We divide the video into equal length segments and classify the extracted features into prototypes, from which a prototype-segment co-occurrence matrix is computed. Motivated by a similar problem in document-keyword analysis, we seek a correspondence relationship between prototypes and video segments which satisfies the transitive closure constraint. We show that an important sub-family of correspondence functions can be reduced to co-embedding prototypes and segments to N-D Euclidean space. We prove that an efficient, globally optimal algorithm exists for the co-embedding problem. Experiments on various real-life videos have validated our approach.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Detecting unusual activity in video


    Contributors:
    Hua Zhong, (author) / Jianbo Shi, (author) / Visontai, M. (author)


    Publication date :

    2004-01-01


    Size :

    624718 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Detecting Unusual Activity in Video

    Zhong, H. / Shi, J. / Visontai, M. et al. | British Library Conference Proceedings | 2004


    UNUSUAL TRAVEL POINT DETECTION DEVICE AND METHOD FOR DETECTING UNUSUAL TRAVEL POINT

    KASHIWAI TADAHIRO / NEYAMA AKIRA | European Patent Office | 2015

    Free access

    Method and apparatus for detecting unusual behavior in satellite

    YANG SEUNG EUN | European Patent Office | 2021

    Free access