Self-organizing maps
Learning and Recognizing Human Dynamics in Video Sequences
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
An Appearance-Based Representation of Action
ICPR '96 Proceedings of the 1996 International Conference on Pattern Recognition (ICPR '96) Volume I - Volume 7270
Clustering of the self-organizing map
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
This paper proposes a method for recognizing human motions from video sequences, based on the hypothesis that there exists a repertoire of movement primitives in biological sensory motor systems. First, a content-based image retrieval algorithm is used to obtain statistical feature vectors from individual images. A decimated magnitude spectrum is calculated from the Fourier transform of the edge images. Then, an unsupervised learning algorithm, self-organizing map, is employed to cluster these shape-based features. Motion primitives are recovered by searching the resulted time serials based on the minimum description length principle. Experimental results of motion recognition from a 37 seconds video sequence show that the proposed approach can efficiently recognize the motions, in a manner similar to human perception.