Title :
Geometric-imprints: a significant points extraction method for the Scan&Track virtual environment
Author :
Semwal, Sudhanshu K. ; Ohya, Jun
Author_Institution :
ATR Media Integration & Commun. Res. Labs., Kyoto, Japan
Abstract :
We have implemented a new algorithm, called the geometric imprints method for extracting key features of a given contour. A series of points on the curve are used to find a geometric imprint set of the contour. The algorithm is based upon the assumption that an articulated human and other figures have mostly cylindrical body parts. The algorithm recursively partitions the contour based upon the cylindrical nature of human silhouettes, and a starting point. Similar topological contours are expected to produce similar geometric imprints. Thus the correspondence problem is somewhat simplified. Results of our implementation are presented
Keywords :
computational geometry; feature extraction; user interfaces; virtual reality; Scan&Track; articulated human; contours; correspondence problem; curves; cylindrical body parts; feature extraction; geometric imprints; human silhouettes; recursive partitioning; significant point extraction method; virtual environment; Data mining; Humans; Image analysis; Image motion analysis; Information analysis; Magnetic analysis; Magnetic sensors; Motion analysis; Springs; Virtual environment;
Conference_Titel :
Automatic Face and Gesture Recognition, 1998. Proceedings. Third IEEE International Conference on
Conference_Location :
Nara
Print_ISBN :
0-8186-8344-9
DOI :
10.1109/AFGR.1998.670994