Anomaly detection driven active learning for identifying suspicious tracks and events in WAMI video

David J. Miller, Aditya Natraj, Ryler Hockenbury, Katherine Dunn, Michael Sheffler, Kevin Sullivan

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

    1 Scopus citations

    Abstract

    We describe a comprehensive system for learning to identify suspicious vehicle tracks from wide-area motion (WAMI) video. First, since the road network for the scene of interest is assumed unknown, agglomerative hierarchical clustering is applied to all spatial vehicle measurements, resulting in spatial cells that largely capture individual road segments. Next, for each track, both at the cell (speed, acceleration, azimuth) and track (range, total distance, duration) levels, extreme value feature statistics are both computed and aggregated, to form summary (p-value based) anomaly statistics for each track. Here, to fairly evaluate tracks that travel across different numbers of spatial cells, for each cell-level feature type, a single (most extreme) statistic is chosen, over all cells traveled. Finally, a novel active learning paradigm, applied to a (logistic regression) track classifier, is invoked to learn to distinguish suspicious from merely anomalous tracks, starting from anomaly-ranked track prioritization, with ground-truth labeling by a human operator. This system has been applied to WAMI video data (ARGUS), with the tracks automatically extracted by a system developed in-house at Toyon Research Corporation. Our system gives promising preliminary results in highly ranking as suspicious aerial vehicles, dismounts, and traffic violators, and in learning which features are most indicative of suspicious tracks.

    Original languageEnglish (US)
    Title of host publicationEvolutionary and Bio-Inspired Computation
    Subtitle of host publicationTheory and Applications VI
    DOIs
    StatePublished - Dec 1 2012
    EventEvolutionary and Bio-Inspired Computation: Theory and Applications VI - Baltimore, MD, United States
    Duration: Apr 25 2012Apr 26 2012

    Publication series

    NameProceedings of SPIE - The International Society for Optical Engineering
    Volume8402
    ISSN (Print)0277-786X

    Other

    OtherEvolutionary and Bio-Inspired Computation: Theory and Applications VI
    CountryUnited States
    CityBaltimore, MD
    Period4/25/124/26/12

    All Science Journal Classification (ASJC) codes

    • Electronic, Optical and Magnetic Materials
    • Condensed Matter Physics
    • Computer Science Applications
    • Applied Mathematics
    • Electrical and Electronic Engineering

    Fingerprint Dive into the research topics of 'Anomaly detection driven active learning for identifying suspicious tracks and events in WAMI video'. Together they form a unique fingerprint.

    Cite this