A survey on vision-based human action recognition

Ronald Walter Poppe

    Research output: Contribution to journalArticleAcademicpeer-review

    1865 Citations (Scopus)
    89 Downloads (Pure)


    Vision-based human action recognition is the process of labeling image sequences with action labels. Robust solutions to this problem have applications in domains such as visual surveillance, video retrieval and human–computer interaction. The task is challenging due to variations in motion performance, recording settings and inter-personal differences. In this survey, we explicitly address these challenges. We provide a detailed overview of current advances in the field. Image representations and the subsequent classification process are discussed separately to focus on the novelties of recent research. Moreover, we discuss limitations of the state of the art and outline promising directions of research.
    Original languageUndefined
    Article number10.1016/j.imavis.2009.11.014
    Pages (from-to)976-990
    Number of pages15
    JournalImage and vision computing
    Issue number6
    Publication statusPublished - Jun 2010


    • Action Detection
    • HMI-CI: Computational Intelligence
    • EC Grant Agreement nr.: FP6/033812
    • EWI-17706
    • METIS-270767
    • Motion analysis
    • IR-70470
    • Human action recognition

    Cite this