A top-down event-driven approach for concurrent activity recognition
We present a new method for extracting and classifying motion patterns to recognize hand gestures. First, motion segmentation of the image sequence is generated based on a multiscale transform and attributed graph matching of regions across frames. This produces region correspondences and their aane transformations. Second, color information of motion regions is used to determine skin regions. Third, human head and palm regions are identiied based on the shape and size of skin areas in motion. Finally, aane transformations deening a region's motion between successive frames are concatenated to construct the region's motion trajectory. Gestural motion trajec-tories are then classiied by a time-delay neural network trained with backpropagation learning algorithm. Our experimental results show that hand gestures can be recognized well using motion patterns.