Video anomaly detection based on wake motion descriptors and perspective grids

Roberto Leyva, Victor Sanchez, Chang Tsun Li

    Research output: Book chapter/Published conference paperConference paperpeer-review

    10 Citations (Scopus)

    Abstract

    This paper proposes a video anomaly detection method based on wake motion descriptors. The method analyses the motion characteristics of the video data, on a video volume-by-video volume basis, by computing the wake left behind by moving objects in the scene. It then probabilistically identifies those never previously seen motion patterns in order to detect anomalies. The method also considers the perspective of the scene to compensate for the relative change in an object's size introduced by the camera's view angle. To this end, a perspective grid is proposed to define the size of video volumes for anomaly detection. Evaluation results against several state-of-the-art methods show that the proposed method attains high detection accuracies and competitive computational time.
    Original languageEnglish
    Title of host publicationProceedings of the 2014 IEEE International Workshop on Information Forensics and Security, WIFS 2014
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages209-214
    Number of pages6
    ISBN (Electronic)9781479988822
    DOIs
    Publication statusPublished - 2014
    Event2014 IEEE International Workshop on Information Forensics and Security - Georgia Tech Hotel & Conference Centre, Atlanta, United States
    Duration: 03 Dec 201405 Dec 2014
    https://web.archive.org/web/20140718162151/http://ieeewifs.org/

    Conference

    Conference2014 IEEE International Workshop on Information Forensics and Security
    Country/TerritoryUnited States
    CityAtlanta
    Period03/12/1405/12/14
    OtherThe IEEE International Workshop on Information Forensics and Security (WIFS) is the primary annual event organized by the IEEE Signal Processing Society?s Information Forensics and Security Technical Committee. The objective of WIFS is to provide the most prominent venue for researchers to exchange ideas and identify potential areas of collaboration. WIFS?14 will feature keynotes, tutorials, special sessions, and lecture & poster sessions. For the first time ever, WIFS is being organized with IEEE GlobalSIP, giving the WIFS community the opportunity to attend a rich selection of research symposia in addition to WIFS.
    Internet address

    Fingerprint

    Dive into the research topics of 'Video anomaly detection based on wake motion descriptors and perspective grids'. Together they form a unique fingerprint.

    Cite this