Geometric neurocomputing for visually pose recognition
Eduardo Jose Bayro-Corrochano, R. Vallejo · 2003
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.