Efficient Upper Body Pose Estimation from a Single Image or a Sequence

We propose a method to find candidate 2D articulated model configurations by searching for locally optimal configurations under a weak but computationally manageable fitness function. This is accomplished by first parameterizing a tree structure by its joints. Candidate configurations can then efficiently and exhaustively be assembled in a bottom-up manner. Working from the leaves of the tree to its root, we maintain a list of locally optimal, yet sufficiently distinct candidate configurations for the body pose. We then adapt this algorithm for use on a sequence of images by considering configurations that are either near their position in the previous frame or overlap areas of interest in subsequent frames. This way, the number of partial configurations generated and evaluated significantly reduces while both smooth and abrupt motions can be accommodated. This approach is validated on test and standard datasets.

• Type: Conference
• Year: 2007
• Where: HUMO
• Authors: Matheen Siddiqui, Gérard G. Medioni
• Keywords: Candidate Configurations, Computer Animation, Configurations, HUMO 2007, Locally Optimal