Common Spatial Patterns for Real-Time Classification of Human Actions

Ronald Walter Poppe

    Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

    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 focuses on differences between classes, rather than on modeling each class individually. As a result, 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, which can be done in real-time. Our image representations are silhouette boundary gradients, spatially binned into cells. We achieve scores of approximately 96% on the Weizmann human action dataset, and show that reasonable results can be obtained when training on only a single subject. We further compare our results with a recent examplar-based approach. Future work is aimed at combining our approach with automatic human detection.
    Original languageUndefined
    Title of host publicationMachine Learning for Human Motion Analysis
    EditorsLiang Wang, Li Cheng, Guoying Zhao
    Place of PublicationHershey
    PublisherIGI Global
    Pages55-73
    Number of pages19
    ISBN (Print)978-1-60566-900-7
    Publication statusPublished - Jan 2010

    Publication series

    Name
    PublisherIGI Global

    Keywords

    • IR-69956
    • METIS-270734
    • Human Motion Analysis
    • HMI-CI: Computational Intelligence
    • Machine Learning
    • EWI-17474
    • EC Grant Agreement nr.: FP6/033812
    • Computer Vision

    Cite this