We present two contributions to human movement analysis: (a) a ballistic dynamical model for recognizing movements, and (b) a model for coupling edge continuity with contour matching.

We describe a Bayesian approach for visual analysis of ballistic hand movements, namely reaches and strikes. These movements are most commonly used for interacting with objects and the environment. One of the key challenges to recognizing them is the variability of the target-location of the hand~- people can reach above their heads, for something on the floor, etc. Our approach recognizes them independent of the movement's target-location and direction by modelling the ballistic dynamics. A video sequence is automatically segmented into ballistic subsequences without tracking the hands. The segments are then classified into strike and reach movements based on low-level motion features. Each ballistic segment is further analyzed to compute qualitative labels for the movement's target-location and direction. Tests are presented with a set of reach and strike movement sequences.

We present an approach for whole-body pose contour matching. Contour matching in natural images in the absence of foreground-background segmentation is difficult. Usually an asymmetric approach is adopted, where a contour is said to match well if it aligns with a subset of the image's gradients. This leads to problems as the contour can match with a portion of an object's outline and ignore the remainder. We present a model for using edge-continuity to address this issue. Pairs of edge elements in the image are linked with affinities if they are likely to belong to the same object. A contour that matches with a set of image gradients is constrained to also match with other gradients having high affinities with the chosen ones. A Markov Random Field framework is employed to couple edge continuity and contour matching into a joint optimization process. The approach is illustrated with applications to pose estimation and human detection.