Description
In this paper, a novel fuzzy-clustering-basedmethod for 3D shape modeling is proposed. This method isintended for scenes involving multiple objects, where eachobject is replaced by a primitive model. The proposed method iscomposed of three stages. In the first stage, 3D data isreconstructed using stereo matching technique from a stereoimage taking multiple objects. Next, the 3D data is divided intoa single object by employing a Fuzzy c-Means augmented withPrincipal Component Analysis (PCA) and a criterion about thenumber of clusters. Finally, the shape of each object isextracted by Fuzzy c-Varieties with Noise Clustering.
Journal
-
- 2006 IEEE International Conference on Fuzzy Systems
-
2006 IEEE International Conference on Fuzzy Systems 609-614, 2006-07