We propose a new method to recognize 3D free-form objects from their apparent contours. It is the extension of our established method to recognize objects with fixed edges. Object models are compared with 3D boundaries which are extracted by segment-based stereo vision. Based on the local shapes of the boundaries, candidate transformations are generated. The candidates are verified and adjusted based on the whole shapes of the boundaries. The models are built from all-around range data of the objects. Experimental results show the effectiveness of the method.
Recognition of 3D free-form objects using segment-based stereo vision
01.01.1998
1115586 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Recognition of 3D Free-form Objects using Segment-Based Stereo Vision
British Library Conference Proceedings | 1998
|3D Object Recognition in Cluttered Environments by Segment-Based Stereo Vision
British Library Online Contents | 2002
|Reverse Engineering of Free-Form Configurations Using CAD, CMM and Stereo Vision
British Library Online Contents | 1998
|3D Face Recognition Using Passive Stereo Vision
British Library Conference Proceedings | 2005
|3D face recognition using passive stereo vision
IEEE | 2005
|