Monocular 3-D Gait Tracking in Surveillance Scenes
GrĂ©gory Rogez, Jonathan Rihan, J.J. Guerrero, Carlos Orrite
icon Gait recognition can potentially provide a noninvasive and effective biometric authentication from a distance. However, the performance of gait recognition systems will suffer in real surveillance scenarios with multiple interacting individuals and where the camera is usually placed at a significant angle and distance from the floor. We present a methodology for view-invariant monocular 3D human pose tracking in man-made environments in which we assume that observed people move on a known ground plane. First, we model 3D body poses and camera viewpoints with a low dimensional manifold and learn a generative model of the silhouette from this manifold to a reduced set of training views. During the online stage, 3D body poses are tracked using recursive Bayesian sampling conducted jointly over the scene's ground plane and the pose- viewpoint manifold. For each sample, the homography that relates the corresponding training plane to the image points is calculated using the dominant 3D directions of the scene, the sampled location on the ground plane and the sampled camera view. Each regressed silhouette shape is projected using this homographic transformation and matched in the image to estimate its likelihood. Our framework is able to track 3D human walking poses in a 3D environment exploring only a 4 dimensional state space with success. In our experimental evaluation, we demonstrate the significant improvements of the homographic alignment over a commonly used similarity transformation and provide quantitative pose tracking results for the monocular sequences with high perspective effect from the CAVIAR dataset.

Download: pdf

Text Reference

Grégory Rogez, Jonathan Rihan, J.J. Guerrero, and Carlos Orrite. Monocular 3-d gait tracking in surveillance scenes. Cybernetics, IEEE Transactions on, 2013. doi:10.1109/TCYB.2013.2275731.

BibTeX Reference

@article{RogezRGO_Cybernetics_2013,
    author = "Rogez, Gr{\'e}gory and Rihan, Jonathan and Guerrero, J.J. and Orrite, Carlos",
    title = "Monocular 3-D Gait Tracking in Surveillance Scenes",
    journal = "Cybernetics, IEEE Transactions on",
    volume = "PP",
    number = "99",
    year = "2013",
    doi = "10.1109/TCYB.2013.2275731",
    publisher = "IEEE",
    tag = "people"
}