Adaptive sparse representations for video anomaly detection

Xuan Mo, Vishal Monga, Raja Bala, Zhigang Fan

    Research output: Contribution to journalArticle

    52 Citations (Scopus)

    Abstract

    Video anomaly detection can be used in the transportation domain to identify unusual patterns such as traffic violations, accidents, unsafe driver behavior, street crime, and other suspicious activities. A common class of approaches relies on object tracking and trajectory analysis. Very recently, sparse reconstruction techniques have been employed in video anomaly detection. The fundamental underlying assumption of these methods is that any new feature representation of a normal/anomalous event can be approximately modeled as a (sparse) linear combination prelabeled feature representations (of previously observed events) in a training dictionary. Sparsity can be a powerful prior on model coefficients but challenges remain in the detection of anomalies involving multiple objects and the ability of the linear sparsity model to effectively allow for class separation. The proposed research addresses both these issues. First, we develop a new joint sparsity model for anomaly detection that enables the detection of joint anomalies involving multiple objects. This extension is highly nontrivial since it leads to a new simultaneous sparsity problem that we solve using a greedy pursuit technique. Second, we introduce nonlinearity into, that is, kernelize. The linear sparsity model to enable superior class separability and hence anomaly detection. We extensively test on several real world video datasets involving both single and multiple object anomalies. Results show marked improvements in detection of anomalies in both supervised and unsupervised scenarios when using the proposed sparsity models.

    Original languageEnglish (US)
    Article number6587741
    Pages (from-to)631-645
    Number of pages15
    JournalIEEE Transactions on Circuits and Systems for Video Technology
    Volume24
    Issue number4
    DOIs
    StatePublished - Apr 2014

    Fingerprint

    Highway accidents
    Crime
    Glossaries
    Trajectories

    All Science Journal Classification (ASJC) codes

    • Media Technology
    • Electrical and Electronic Engineering

    Cite this

    @article{4e9b21dc67234a7ba3cbc6186ef7a862,
    title = "Adaptive sparse representations for video anomaly detection",
    abstract = "Video anomaly detection can be used in the transportation domain to identify unusual patterns such as traffic violations, accidents, unsafe driver behavior, street crime, and other suspicious activities. A common class of approaches relies on object tracking and trajectory analysis. Very recently, sparse reconstruction techniques have been employed in video anomaly detection. The fundamental underlying assumption of these methods is that any new feature representation of a normal/anomalous event can be approximately modeled as a (sparse) linear combination prelabeled feature representations (of previously observed events) in a training dictionary. Sparsity can be a powerful prior on model coefficients but challenges remain in the detection of anomalies involving multiple objects and the ability of the linear sparsity model to effectively allow for class separation. The proposed research addresses both these issues. First, we develop a new joint sparsity model for anomaly detection that enables the detection of joint anomalies involving multiple objects. This extension is highly nontrivial since it leads to a new simultaneous sparsity problem that we solve using a greedy pursuit technique. Second, we introduce nonlinearity into, that is, kernelize. The linear sparsity model to enable superior class separability and hence anomaly detection. We extensively test on several real world video datasets involving both single and multiple object anomalies. Results show marked improvements in detection of anomalies in both supervised and unsupervised scenarios when using the proposed sparsity models.",
    author = "Xuan Mo and Vishal Monga and Raja Bala and Zhigang Fan",
    year = "2014",
    month = "4",
    doi = "10.1109/TCSVT.2013.2280061",
    language = "English (US)",
    volume = "24",
    pages = "631--645",
    journal = "IEEE Transactions on Circuits and Systems for Video Technology",
    issn = "1051-8215",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    number = "4",

    }

    Adaptive sparse representations for video anomaly detection. / Mo, Xuan; Monga, Vishal; Bala, Raja; Fan, Zhigang.

    In: IEEE Transactions on Circuits and Systems for Video Technology, Vol. 24, No. 4, 6587741, 04.2014, p. 631-645.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Adaptive sparse representations for video anomaly detection

    AU - Mo, Xuan

    AU - Monga, Vishal

    AU - Bala, Raja

    AU - Fan, Zhigang

    PY - 2014/4

    Y1 - 2014/4

    N2 - Video anomaly detection can be used in the transportation domain to identify unusual patterns such as traffic violations, accidents, unsafe driver behavior, street crime, and other suspicious activities. A common class of approaches relies on object tracking and trajectory analysis. Very recently, sparse reconstruction techniques have been employed in video anomaly detection. The fundamental underlying assumption of these methods is that any new feature representation of a normal/anomalous event can be approximately modeled as a (sparse) linear combination prelabeled feature representations (of previously observed events) in a training dictionary. Sparsity can be a powerful prior on model coefficients but challenges remain in the detection of anomalies involving multiple objects and the ability of the linear sparsity model to effectively allow for class separation. The proposed research addresses both these issues. First, we develop a new joint sparsity model for anomaly detection that enables the detection of joint anomalies involving multiple objects. This extension is highly nontrivial since it leads to a new simultaneous sparsity problem that we solve using a greedy pursuit technique. Second, we introduce nonlinearity into, that is, kernelize. The linear sparsity model to enable superior class separability and hence anomaly detection. We extensively test on several real world video datasets involving both single and multiple object anomalies. Results show marked improvements in detection of anomalies in both supervised and unsupervised scenarios when using the proposed sparsity models.

    AB - Video anomaly detection can be used in the transportation domain to identify unusual patterns such as traffic violations, accidents, unsafe driver behavior, street crime, and other suspicious activities. A common class of approaches relies on object tracking and trajectory analysis. Very recently, sparse reconstruction techniques have been employed in video anomaly detection. The fundamental underlying assumption of these methods is that any new feature representation of a normal/anomalous event can be approximately modeled as a (sparse) linear combination prelabeled feature representations (of previously observed events) in a training dictionary. Sparsity can be a powerful prior on model coefficients but challenges remain in the detection of anomalies involving multiple objects and the ability of the linear sparsity model to effectively allow for class separation. The proposed research addresses both these issues. First, we develop a new joint sparsity model for anomaly detection that enables the detection of joint anomalies involving multiple objects. This extension is highly nontrivial since it leads to a new simultaneous sparsity problem that we solve using a greedy pursuit technique. Second, we introduce nonlinearity into, that is, kernelize. The linear sparsity model to enable superior class separability and hence anomaly detection. We extensively test on several real world video datasets involving both single and multiple object anomalies. Results show marked improvements in detection of anomalies in both supervised and unsupervised scenarios when using the proposed sparsity models.

    UR - http://www.scopus.com/inward/record.url?scp=84898017675&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84898017675&partnerID=8YFLogxK

    U2 - 10.1109/TCSVT.2013.2280061

    DO - 10.1109/TCSVT.2013.2280061

    M3 - Article

    AN - SCOPUS:84898017675

    VL - 24

    SP - 631

    EP - 645

    JO - IEEE Transactions on Circuits and Systems for Video Technology

    JF - IEEE Transactions on Circuits and Systems for Video Technology

    SN - 1051-8215

    IS - 4

    M1 - 6587741

    ER -