A joint sparsity model for video anomaly detection

Xuan Mo, Vishal Monga, Raja Bala, Zhigang Fan

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    2 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 upon object tracking and trajectory analysis. A key challenge is the ability to effectively handle occlusions among objects and their trajectories. Another challenge is the detection of joint anomalies between multiple moving objects. Recently sparse reconstruction techniques have been used for image classification, and shown to provide excellent robustness to occlusion. This paper proposes a new joint sparsity model for anomaly detection that effectively addresses both the robustness to occlusion and the detection of joint anomalies involving multiple objects. Experimental results on real and synthetic data demonstrate the effectiveness of our approach for both single-object and multi-object anomalies.

    Original languageEnglish (US)
    Title of host publicationConference Record of the 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012
    Pages1969-1973
    Number of pages5
    DOIs
    StatePublished - Dec 1 2012
    Event46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012 - Pacific Grove, CA, United States
    Duration: Nov 4 2012Nov 7 2012

    Other

    Other46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012
    CountryUnited States
    CityPacific Grove, CA
    Period11/4/1211/7/12

    Fingerprint

    Trajectories
    Highway accidents
    Crime
    Image classification

    All Science Journal Classification (ASJC) codes

    • Signal Processing
    • Computer Networks and Communications

    Cite this

    Mo, X., Monga, V., Bala, R., & Fan, Z. (2012). A joint sparsity model for video anomaly detection. In Conference Record of the 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012 (pp. 1969-1973). [6489384] https://doi.org/10.1109/ACSSC.2012.6489384
    Mo, Xuan ; Monga, Vishal ; Bala, Raja ; Fan, Zhigang. / A joint sparsity model for video anomaly detection. Conference Record of the 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012. 2012. pp. 1969-1973
    @inproceedings{08d31d445d2749bfbd0ddb81aa09382e,
    title = "A joint sparsity model 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 upon object tracking and trajectory analysis. A key challenge is the ability to effectively handle occlusions among objects and their trajectories. Another challenge is the detection of joint anomalies between multiple moving objects. Recently sparse reconstruction techniques have been used for image classification, and shown to provide excellent robustness to occlusion. This paper proposes a new joint sparsity model for anomaly detection that effectively addresses both the robustness to occlusion and the detection of joint anomalies involving multiple objects. Experimental results on real and synthetic data demonstrate the effectiveness of our approach for both single-object and multi-object anomalies.",
    author = "Xuan Mo and Vishal Monga and Raja Bala and Zhigang Fan",
    year = "2012",
    month = "12",
    day = "1",
    doi = "10.1109/ACSSC.2012.6489384",
    language = "English (US)",
    isbn = "9781467350518",
    pages = "1969--1973",
    booktitle = "Conference Record of the 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012",

    }

    Mo, X, Monga, V, Bala, R & Fan, Z 2012, A joint sparsity model for video anomaly detection. in Conference Record of the 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012., 6489384, pp. 1969-1973, 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012, Pacific Grove, CA, United States, 11/4/12. https://doi.org/10.1109/ACSSC.2012.6489384

    A joint sparsity model for video anomaly detection. / Mo, Xuan; Monga, Vishal; Bala, Raja; Fan, Zhigang.

    Conference Record of the 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012. 2012. p. 1969-1973 6489384.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    TY - GEN

    T1 - A joint sparsity model for video anomaly detection

    AU - Mo, Xuan

    AU - Monga, Vishal

    AU - Bala, Raja

    AU - Fan, Zhigang

    PY - 2012/12/1

    Y1 - 2012/12/1

    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 upon object tracking and trajectory analysis. A key challenge is the ability to effectively handle occlusions among objects and their trajectories. Another challenge is the detection of joint anomalies between multiple moving objects. Recently sparse reconstruction techniques have been used for image classification, and shown to provide excellent robustness to occlusion. This paper proposes a new joint sparsity model for anomaly detection that effectively addresses both the robustness to occlusion and the detection of joint anomalies involving multiple objects. Experimental results on real and synthetic data demonstrate the effectiveness of our approach for both single-object and multi-object anomalies.

    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 upon object tracking and trajectory analysis. A key challenge is the ability to effectively handle occlusions among objects and their trajectories. Another challenge is the detection of joint anomalies between multiple moving objects. Recently sparse reconstruction techniques have been used for image classification, and shown to provide excellent robustness to occlusion. This paper proposes a new joint sparsity model for anomaly detection that effectively addresses both the robustness to occlusion and the detection of joint anomalies involving multiple objects. Experimental results on real and synthetic data demonstrate the effectiveness of our approach for both single-object and multi-object anomalies.

    UR - http://www.scopus.com/inward/record.url?scp=84876206701&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84876206701&partnerID=8YFLogxK

    U2 - 10.1109/ACSSC.2012.6489384

    DO - 10.1109/ACSSC.2012.6489384

    M3 - Conference contribution

    AN - SCOPUS:84876206701

    SN - 9781467350518

    SP - 1969

    EP - 1973

    BT - Conference Record of the 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012

    ER -

    Mo X, Monga V, Bala R, Fan Z. A joint sparsity model for video anomaly detection. In Conference Record of the 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012. 2012. p. 1969-1973. 6489384 https://doi.org/10.1109/ACSSC.2012.6489384