View-invariant representation and recognition of actions

Analysis of human perception of motion shows that information for representing the motion is obtained from the dramatic changes in the speed and direction of the trajectory. In this paper, we present a computational representation of human action to capture these dramatic changes using spatio-temporal curvature of 2-D trajectory. This representation is compact, view-invariant, and is capable of explaining an action in terms of meaningful action units called dynamic instants and intervals. A dynamic instant is an instantaneous entity that occurs for only one frame, and represents an important change in the motion characteristics. An interval represents the time period between two dynamic instants during which the motion characteristics do not change. Starting without a model, we use this representation for recognition and incremental learning of human actions. The proposed method can discover instances of the same action performed by different people from different view points. Experiments on 47 actions performed by 7 individuals in an environment with no constraints shows the robustness of the proposed method.