SYMMETRICAL 3D OBJECTS ARE AN EASY CASE FOR 2D OBJECT RECOGNITION

被引:62
作者
VETTER, T
POGGIO, T
机构
[1] MIT,CTR COMPUTAT & BIOL LEARNING,CAMBRIDGE,MA 02139
[2] MIT,DEPT BRAIN SCI,CAMBRIDGE,MA 02139
来源
SPATIAL VISION | 1994年 / 8卷 / 04期
基金
美国国家科学基金会;
关键词
D O I
10.1163/156856894X00107
中图分类号
Q6 [生物物理学];
学科分类号
071011 ;
摘要
According to the 1.5-views theorem (Poggio, Technical Report #9005-03, IRST, Povo, 1990; Ullman and Basri, IEEE Trans. PAMI 13, 992-1006, 1991) recognition of a specific 3D object (defined in terms of pointwise features) from a novel 2D view can be achieved from at least two 2D model views (for each object, for orthographic projection). This note considers how recognition can be achieved from a single 2D model view by exploiting prior knowledge of an object's symmetry. It is proved that, for any bilaterally symmetric 3D object, one non-accidental 2D model view is sufficient for recognition since it can be used to generate additional 'virtual' views. It is also proved that, for bilaterally symmetric objects, the correspondence of four points between two views determines the correspondence of all other points. Symmetries of higher order allow the recovery of Euclidean structure from a single 2D view.1
引用
收藏
页码:443 / 453
页数:11
相关论文
共 23 条
[1]  
BEYMER D, 1993, A I MEMO, V1431
[2]  
Edelman S., 1992, International Journal of Pattern Recognition and Artificial Intelligence, V6, P37, DOI 10.1142/S0218001492000035
[3]  
FAUGERAS OD, 1992, P 2 EUR C COMP VIS S, P563
[4]  
Hartley R., 1992, Proceedings. 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.92CH3168-2), P761, DOI 10.1109/CVPR.1992.223179
[5]  
HUANG TS, 1989, IEEE T PATTERN ANAL, V2, P536
[6]   AFFINE STRUCTURE FROM MOTION [J].
KOENDERINK, JJ ;
VANDOORN, AJ .
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1991, 8 (02) :377-385
[7]   PAIRWISE COMPARISON TECHNIQUE - A SIMPLE SOLUTION FOR DEPTH RECONSTRUCTION [J].
KONTSEVICH, LL .
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1993, 10 (06) :1129-1135
[8]   EMULATING THE HUMAN INTERPRETATION OF LINE-DRAWINGS AS 3-DIMENSIONAL OBJECTS [J].
MARILL, T .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1991, 6 (02) :147-161
[9]  
MOSES Y, 1991, AI MEMO, V1301
[10]   A NETWORK THAT LEARNS TO RECOGNIZE 3-DIMENSIONAL OBJECTS [J].
POGGIO, T ;
EDELMAN, S .
NATURE, 1990, 343 (6255) :263-266