Title :
Learning 3D object descriptions from a set of stereo vision observations
Author :
De Jong, Johan J. ; Buurman, Johannes
Author_Institution :
Fac. of Appl. Phys., Delft Univ. of Technol., Netherlands
fDate :
30 Aug-3 Sep 1992
Abstract :
Describes a system for learning models of polyhedral objects. The system does not require exact knowledge about poses, instead only some course requirements are needed. The system obtains a 3D wireframe model of the object together with the statistical data. This is illustrated with an example
Keywords :
computer vision; image recognition; learning systems; 3D object descriptions; 3D wireframe model; computer vision; learning models; machine learning; polyhedral objects; stereo vision observations; Cameras; Clocks; Computer vision; Databases; Design automation; Learning systems; Pattern recognition; Physics; Stereo vision; Testing;
Conference_Titel :
Pattern Recognition, 1992. Vol.I. Conference A: Computer Vision and Applications, Proceedings., 11th IAPR International Conference on
Conference_Location :
The Hague
Print_ISBN :
0-8186-2910-X
DOI :
10.1109/ICPR.1992.201673
