Key points are not available for this paper at this time.
Motion recognition via trajectory is important in motion analysis for many robotic tasks. A descriptor for motion trajectories plays an important role in the recognition algorithm. Existing invariant descriptors and discrete matching algorithms are not flexible enough under certain circumstances for recognition. In this paper we propose a new descriptor to solve this problem, with a modified data alignment method in the matching algorithm for motion recognition. Experimental results demonstrate the effectiveness of the method in the motion recognition.
Yang et al. (Sun,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: