Title :
Geometric neurocomputing for visually pose recognition
Author :
Bayro-Corrochano, Eduardo ; Vallejo, Refugio
Author_Institution :
Dept. of Comput. Sci., Centro de Investigacion y de Estudios Avanzados, Guadalajara, Mexico
fDate :
6/24/1905 12:00:00 AM
Abstract :
This paper presents a geometric neurocomputing approach for 3D pose recognition using the framework of the geometric Clifford algebras. The type of geometric problems like pose recognition can be very efficiently handled using geometric neural networks. Our experimental part shows the computing of 3D pose using 2D image data and the computing of 3D pose of rigid objects using visual information captured by a trinocular head
Keywords :
computational geometry; computer vision; image recognition; neural nets; 2D image data; 3D pose recognition; geometric Clifford algebras; geometric neurocomputing; trinocular head; visual pose recognition; Algebra; Multidimensional systems; Neural networks; Neurons; Nonlinear equations; Solid modeling; Topology; Yttrium;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1005478
