Title :
A neurocomputing model based on radial basis functions for stereo matching
Author :
Jin, Jesse S. ; Yeap, Wai K. ; Cox, Brian G.
Author_Institution :
Dept. of Comput. Sci., Otago Univ., Dunedin, New Zealand
Abstract :
The authors describe a stereo model for combining the use of both monocular and binocular cues in stereo matching. The solution lies in mapping the two 2-D image planes onto a Gaussian sphere and working out the Jacobian determinant of such a mapping. Matching is then performed using zero-crossings associated with their orientation information. How such a model could be implemented using a neural network is discussed
Keywords :
feedforward neural nets; stereo image processing; 2-D image planes; Gaussian sphere; Jacobian determinant; binocular cues; monocular cues; neural network; neurocomputing model; radial basis functions; stereo matching; zero-crossings; Artificial intelligence; Computer science; Eyes; Geometrical optics; Humans; Jacobian matrices; Laboratories; Neural networks; Neurons; Solid modeling;
Conference_Titel :
Artificial Neural Networks and Expert Systems, 1993. Proceedings., First New Zealand International Two-Stream Conference on
Conference_Location :
Dunedin
Print_ISBN :
0-8186-4260-2
DOI :
10.1109/ANNES.1993.323073
