Discriminative human action recognition using pairwise CSP classifiers

Ronald Walter Poppe, Mannes Poel

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    8 Citations (Scopus)

    Abstract

    We present a discriminative approach to human action recognition. At the heart of our approach is the use of common spatial patterns (CSP), a spatial filter technique that transforms temporal feature data by using differences in variance between two classes. Such a transformation focusses on differences between classes, rather than on modelling each class individually. As a results, to distinguish between two classes, we can use simple distance metrics in the low-dimensional transformed space. The most likely class is found by pairwise evaluation of all discriminant functions. Our image representations are silhouette boundary gradients, spatially binned into cells. We achieve scores of approximately 96% on a standard action dataset, and show that reasonable results can be obtained when training on only a single subject. Future work is aimed at combining our approach with automatic human detection.
    Original languageUndefined
    Title of host publicationIEEE International Conference on Automatic Face and Gesture Recognition (FG 2008)
    EditorsJ. Cohn, T.S Huang, Maja Pantic, N. Sebe
    Place of PublicationLos Alamitos
    PublisherIEEE Computer Society Press
    Pages1-8
    Number of pages8
    ISBN (Print)978-1-4244-2154-1
    DOIs
    Publication statusPublished - 17 Sep 2008
    Event8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008 - Amsterdam, Netherlands
    Duration: 17 Sep 200819 Sep 2008
    Conference number: 8

    Publication series

    Name
    PublisherIEEE Computer Society Press
    Number2008/14935

    Conference

    Conference8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008
    Abbreviated titleFG
    CountryNetherlands
    CityAmsterdam
    Period17/09/0819/09/08

    Keywords

    • EWI-14643
    • HMI-CI: Computational Intelligence
    • METIS-255025
    • EC Grant Agreement nr.: FP6/033812
    • IR-62627

    Cite this