Navigation

    Action Recognition

    Action Recognition Based on Multi-Level Representation of a Space Time Shape

    This approach considers human actions as space time shapes which is a concatenation of silhouettes, and uses a combination of shape descriptors to extract features suitable for recognition. The current algorithm uses a 3D Euclidean distance transform as one shape descriptor, the purpose of which is to give interior values in accordance to the shape boundary which is different for different human actions. By using the values obtained, the space time shape is dissected inwards to get coarser and coarser representation. At each level of the coarser representation, the R-Transform and R-Translation which is a variant of the Radon transform, is extracted and these provide the action features. R-Transform gives the variation of the posture of the human silhouette at every instant of the space time shape while the R-Translation discriminates between actions which involves a large translation of the body with those which does not. The figure below gives the flow diagram of the algorithm along with sample space time shapes of jumping jack and walking.

    Jumping JackFlowchartWalking

    Jumping Jack ST                                                                                                                                         Walking ST

    Distance Transform Values

    Distance Transform Values

    Gradient of the Distance Transform

    Gradient of the Distance Transform

    Segmentation of the Space Time Shape

    Segmentation of the Space Time Shape

    R-Transform Feature 

    Jumping JackJumping Jack

    WalkWalk


    Video Demonstration

    Action Recognition

    (Research Demonstrated at Old Dominion University Vision Lab)

    Segmentation for Human Activity Recognition

    << Back

    Related Links

    Contact

    Vision Lab, Dr. Vijayan Asari, Director

    Kettering Lab 461-464 
    300 College Park 
    Dayton, Ohio 45469 - 0232

    937-229-1779