Actively learning to distinguish suspicious from innocuous anomalies in a batch of vehicle tracks

Zhicong Qiu, David Jonathan Miller, Brian Stieber, Tim Fair

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

    1 Scopus citations

    Abstract

    We investigate the problem of actively learning to distinguish between two sets of anomalous vehicle tracks, innocuous and suspicious, starting from scratch, without any initial examples of suspicious and with no prior knowledge of what an operator would deem suspicious. This two-class problem is challenging because it is a priori unknown which track features may characterize the suspicious class. Furthermore, there is inherent imbalance in the sizes of the labeled innocuous and suspicious sets, even after some suspicious examples are identified. We present a comprehensive solution wherein a classifier learns to discriminate suspicious from innocuous based on derived p-value track features. Through active learning, our classifier thus learns the types of anomalies on which to base its discrimination. Our solution encompasses: i) judicious choice of kinematic p-value based features conditioned on the road of origin, along with more explicit features that capture unique vehicle behavior (e.g. U-turns); ii) novel semi-supervised learning that exploits information in the unlabeled (test batch) tracks, and iii) evaluation of several classifier models (logistic regression, SVMs). We find that two active labeling streams are necessary in practice in order to have efficient classifier learning while also forwarding (for labeling) the most actionable tracks. Experiments on wide-area motion imagery (WAMI) tracks, extracted via a system developed by Toyon Research Corporation, demonstrate the strong ROC AUC performance of our system, with sparing use of operator-based active labeling.

    Original languageEnglish (US)
    Title of host publicationGround/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR V
    PublisherSPIE
    ISBN (Print)9781628410167
    DOIs
    StatePublished - Jan 1 2014
    EventGround/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR V - Baltimore, MD, United States
    Duration: May 5 2014May 6 2014

    Publication series

    NameProceedings of SPIE - The International Society for Optical Engineering
    Volume9079
    ISSN (Print)0277-786X
    ISSN (Electronic)1996-756X

    Other

    OtherGround/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR V
    CountryUnited States
    CityBaltimore, MD
    Period5/5/145/6/14

    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 'Actively learning to distinguish suspicious from innocuous anomalies in a batch of vehicle tracks'. Together they form a unique fingerprint.

    Cite this