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.
|出版ステータス||Published - 1998 12 1|
|イベント||Proceedings of the 1998 IEEE 6th International Conference on Computer Vision - Bombay, India|
継続期間: 1998 1 4 → 1998 1 7
|Other||Proceedings of the 1998 IEEE 6th International Conference on Computer Vision|
|Period||98/1/4 → 98/1/7|
ASJC Scopus subject areas
- コンピュータ ビジョンおよびパターン認識