Visual Hand Posture Recognition in Monocular Image Sequences

We present a model-based method for hand posture recognition in monocular image sequences that measures joint angles, viewing angle, and position in space. Visual markers in form of a colored cotton glove are used to extract descriptive and stable 2D features. Searching a synthetically generated database of 2.6 million entries, each consisting of 3D hand posture parameters and the corresponding 2D features, yields several candidate postures per frame. This ambiguity is resolved by exploiting temporal continuity between successive frames. The method is robust to noise, can be used from any viewing angle, and places no constraints on the hand posture. Self-occlusion of any number of markers is handled. It requires no initialization and retrospectively corrects posture errors when accordant information becomes available. Besides a qualitative evaluation on real images, a quantitative performance measurement using a large amount of synthetic input data featuring various degrees of noise shows the effectiveness of the approach.