Year: 2003
Type: book-chapter
Abstract: Consider a number of moving points, where each point is attached to a joint of the human body and projected onto an image plane. Johannson showed that humans can effortlessly detect and recognize the presence of other humans from such displays. This is true even when some of the body points are missing (e.g. because of occlusion) and unrelated clutter points are added to the display. We are interested in replicating this ability in a machine. To this end, we present a labelling and detection scheme in a probabilistic framework. Our method is based on representing the joint probability density of positions and velocities of body points with a graphical model, and using Loopy Belief Propagation to calculate a likely interpretation of the scene. Furthermore, we introduce a global variable representing the body’s centroid. Experiments on one motion-captured sequence suggests that our scheme improves on the accuracy a previous approach based on triangulated graphical models [3], especially when very few parts are visible. The improvement is due both to the more general graph structure we use and to the introduction of the centroid variable. 1
DOI: 10.7907/jf8y-tk36.
Authors: Claudio Fanti, Marzia Polito, Pietro Perona
Institutions: California Institute of Technology, Intel (United States)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2101927187