Paper in ICCV 2011: "Gaussian Process Regression Flow for Analysis of Motion Trajectories"


  • K. Kim, D. Lee, and I. Essa (2011), “Gaussian Process Regression Flow for Analysis of Motion Trajectories,” in IEEE International Conference on Computer Vision (ICCV), 2011. [PDF] [WEBSITE] [VIDEO] [BIBTEX]
    @InProceedings{ 2011-Kim-GPRFAMT,
    author  = {K. Kim and D. Lee and I. Essa},
    booktitle  = {{IEEE International Conference on Computer Vision
    month = {November},
    pdf = {},
    publisher  = {IEEE Computer Society},
    title = {Gaussian Process Regression Flow for Analysis of
    Motion Trajectories},
    url = {},
    video = {},
    year = {2011}


Analysis and Recognition of motions and activities of objects in videos requires effective representations for analysis and matching of motion trajectories. In this paper, we introduce a new representation specifically aimed at matching motion trajectories. We model a trajectory as a continuous dense flow field from a sparse set of vector sequences using Gaussian Process Regression. Furthermore, we introduce a random sampling strategy for learning stable classes of motions from limited data.

Our representation allows for incrementally predicting possible paths and detecting anomalous events from online trajectories. This representation also supports the matching of complex motions with acceleration changes and pauses or stops within a trajectory. We use the proposed approach for classifying and predicting motion trajectories in traffic monitoring domains and test on several data sets. We show that our approach works well on various types of complete and incomplete trajectories from a variety of video data sets with different frame rates

Leave a Reply

Your email address will not be published.

This site uses Akismet to reduce spam. Learn how your comment data is processed.