Uncalibrated reconstruction: an adaptation to structured light vision

被引:28
作者
Fofi, D
Salvi, J
Mouaddib, EM
机构
[1] Univ Picardie, CREA, F-80000 Amiens, France
[2] Univ Girona, IIiA, Comp Vis & Robot Grp, Girona 17071, Spain
关键词
uncalibrated system; projective reconstruction; euclidean constraints; structured light; computer vision;
D O I
10.1016/S0031-3203(02)00288-1
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Euclidean reconstruction from two uncalibrated stereoscopic views is achievable from the knowledge of geometrical constraints about the environment. Unfortunately, these constraints may be quite difficult to obtain. In this paper, we propose an approach based on structured lighting, which has the advantage of providing geometrical constraints independent of the scene geometry. Moreover, the use of structured light provides a unique solution to the tricky correspondence problem present in stereovision. The projection matrices are first computed by using a canonical representation, and a projective reconstruction is performed. Then, several constraints are generated from the image analysis and the projective reconstruction is upgraded into an Euclidean one-as we will demonstrate, it is assumed that the sensor behaviour is affine without loss of generality so that the constraints generation is simplified. The method provides our sensor with adaptive capabilities and permits to be used in the measurement of moving scenes such as dynamic visual inspection or mobile robot navigation. Experimental results obtained from both simulated and real data are presented. (C) 2003 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.
引用
收藏
页码:1631 / 1644
页数:14
相关论文
共 20 条
[1]  
[Anonymous], 1993, Three-Dimensional Computer Vision: A Geometric Viewpoint
[2]  
ASTROM K, 1995, P 9 SCAND C IM AN, P1053
[3]   Recent progress in coded structured light as a technique to solve the correspondence problem: A survey [J].
Batlle, J ;
Mouaddib, E ;
Salvi, J .
PATTERN RECOGNITION, 1998, 31 (07) :963-982
[4]  
Boufama B., 1993, [1993] Proceedings Fourth International Conference on Computer Vision, P466, DOI 10.1109/ICCV.1993.378179
[5]  
FAUGERAS OD, 1992, LECT NOTES COMPUT SC, V588, P321
[6]  
FAUGERAS OD, 1992, LECT NOTES COMPUT SC, V588, P564
[7]  
FOFI D, 2001, THESIS U PJ VERNE
[8]  
HARTLEY R, 1992, STEREO UNCALIBRATED, P761
[9]   Kruppa's equations derived from the fundamental matrix [J].
Hartley, RI .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1997, 19 (02) :133-135
[10]  
HARTLEY RI, 1994, LNCS SERIES, V825, P237