Fanti, Claudio (2005) An improved scheme for detection and labeling in Johansson displays. Master's thesis, California Institute of Technology. http://resolver.caltech.edu/CaltechETD:etd-05282004-144523
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 labeling 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 suggest that our scheme improves on the accuracy of a previous approach based on triangulated graphical models, especially when very few parts are visble. The improvement is due both to the more general graph structure we use and, more significantly, to the introduction of the centroid variable.
|Item Type:||Thesis (Master's thesis)|
|Subject Keywords:||conditional independence; expectation maximization; graphical models; Johansson display; Loopy Belief Propagation; moving light display|
|Degree Grantor:||California Institute of Technology|
|Division:||Engineering and Applied Science|
|Major Option:||Computer Science|
|Thesis Availability:||Public (worldwide access)|
|Defense Date:||11 June 2004|
|Default Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Imported from ETD-db|
|Deposited On:||01 Jun 2004|
|Last Modified:||26 Dec 2012 02:48|
- Final Version
See Usage Policy.
Repository Staff Only: item control page