Object Pose: The Link between Weak Perspective, Paraperspective, and Full Perspective

International Journal of Computer Vision - Tập 22 Số 2 - Trang 173-189 - 1997
Horaud, Radu, Dornaika, Fadi, Lamiroy, Bart

Tóm tắt

Recently, DeMenthon and Davis (1992, 1995) proposed a method for determining the pose of a 3-D object with respect to a camera from 3-D to 2-D point correspondences. The method consists of iteratively improving the pose computed with a weak perspective camera model to converge, at the limit, to a pose estimation computed with a perspective camera model. In this paper we give an algebraic derivation of DeMenthon and Davis' method and we show that it belongs to a larger class of methods where the perspective camera model is approximated either at zero order (weak perspective) or first order (paraperspective). We describe in detail an iterative paraperspective pose computation method for both non coplanar and coplanar object points. We analyse the convergence of these methods and we conclude that the iterative paraperspective method (proposed in this paper) has better convergence properties than the iterative weak perspective method. We introduce a simple way of taking into account the orthogonality constraint associated with the rotation matrix. We analyse the sensitivity to camera calibration errors and we define the optimal experimental setup with respect to imprecise camera calibration. We compare the results obtained with this method and with a non-linear optimization method.

Từ khóa


Tài liệu tham khảo

citation_journal_title=Image and Vision Computing; citation_title=Perspective approximations; citation_author=Y. Aloimonos; citation_volume=8; citation_issue=3; citation_publication_date=1990; citation_pages=177-192; citation_id=CR1

citation_journal_title=IEEE Transactions on Pattern Analysis and Machine Intelligence; citation_title=Euclidean shape and motion from multiple perspective views by affine iterations; citation_author=S. Christy, R. Horaud; citation_volume=18; citation_issue=11; citation_publication_date=1996; citation_pages=1098-1104; citation_id=CR2

DeMenthon, D.F. 1993. De la Vision Artificielle àla RéalitéSynthétique: Système d'interaction avec un ordinateur utilisant l'analyse d'images vidéo. Ph.D. thesis, Universitè Joseph Fourier-Grenoble I, Laboratoire TIMC/IMAG.

citation_title=Model-based object pose in 25 lines of code; citation_inbook_title=Computer Vision-ECCV 92, Proceedings Second European Conference on Computer Vision; citation_publication_date=1992; citation_pages=335-343; citation_id=CR4; citation_author=D.F. DeMenthon; citation_author=L.S. Davis; citation_publisher=Springer Verlag

citation_journal_title=International Journal of Computer Vision; citation_title=Model-based object pose in 25 lines of code; citation_author=D.F. DeMenthon, L.S. Davis; citation_volume=15; citation_issue=1/2; citation_publication_date=1995; citation_pages=123-141; citation_id=CR5

citation_journal_title=IEEE Transactions on Pattern Analysis and Machine Intelligence; citation_title=Determination of the attitude of 3D objects from a single perspective view; citation_author=M. Dhome, M. Richetin, J.T. Lapreste, G. Rives; citation_volume=11; citation_issue=12; citation_publication_date=1989; citation_pages=1265-1278; citation_id=CR6

citation_title=Three Dimensional Computer Vision: A Geometric Viewpoint; citation_publication_date=1993; citation_id=CR7; citation_author=O.D. Faugeras; citation_publisher=MIT Press

citation_journal_title=Communications of the ACM; citation_title=Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography; citation_author=M.A. Fischler, R.C. Bolles; citation_volume=24; citation_issue=6; citation_publication_date=1981; citation_pages=381-395; citation_id=CR8

citation_title=Matching and clustering: two steps towards automatic model generation in computer vision; citation_inbook_title=Proceedings of the AAAI Fall Symposium Series: Machine Learning in Computer Vision: What, Why, and How?; citation_publication_date=1993; citation_pages=40-44; citation_id=CR9; citation_author=P. Gros; citation_publisher=Raleigh

citation_journal_title=IEEE Transactions on Systems, Man, and Cybernetics; citation_title=Pose estimation from corresponding point data; citation_author=R.B. Haralick, H. Joo, C.-N. Lee, X. Zhuang, V.G. Vaidya, M.B. Kim; citation_volume=19; citation_issue=6; citation_publication_date=1989; citation_pages=1426-1445; citation_id=CR10

citation_journal_title=Computer Vision, Graphics, and Image Processing; citation_title=An analytic solution for the perspective 4-point problem; citation_author=R. Horaud, B. Conio, O. Leboulleux, B. Lacolle; citation_volume=47; citation_issue=1; citation_publication_date=1989; citation_pages=33-44; citation_id=CR11

Horaud, R., Dornaika, F., Bard, C., and Espiau, B. 1995. Visually guided object grasping. Technical report, INRIA. Submitted to IEEE Trans. on Robotics & Automation.

citation_journal_title=IEEE Transactions on Pattern Analysis and Machine Intelligence; citation_title=Fitting parameterized three-dimensional models to images; citation_author=D. Lowe; citation_volume=13; citation_issue=5; citation_publication_date=1991; citation_pages=441-450; citation_id=CR13

citation_title=Iterative pose estimation using coplanar feature points; citation_inbook_title=Proceedings Computer Vision and Pattern Recognition; citation_publication_date=1993; citation_pages=626-627; citation_id=CR14; citation_author=D. Oberkampf; citation_author=D.F. DeMenthon; citation_author=L.S. Davis; citation_publisher=IEEE Computer Society Press

citation_title=Optimal estimation of object pose from a single perspective view; citation_inbook_title=Proceedings Fourth International Conference on Computer Vision; citation_publication_date=1993; citation_pages=534-539; citation_id=CR15; citation_author=T.Q. Phong; citation_author=R. Horaud; citation_author=A. Yassine; citation_author=D.T. Pham; citation_publisher=IEEE Computer Society Press

citation_journal_title=International Journal of Computer Vision; citation_title=Object pose from 2-D to 3-D point and line correspondences; citation_author=T.Q. Phong, R. Horaud, A. Yassine, D.T. Pham; citation_volume=15; citation_issue=3; citation_publication_date=1995; citation_pages=225-243; citation_id=CR16

citation_title=A paraperspective factorization method for shape and motion recovery; citation_inbook_title=Computer Vision-ECCV 94, Proceedings Third European Conference on Computer Vision; citation_publication_date=1994; citation_pages=97-108; citation_id=CR17; citation_author=C.J. Poelman; citation_author=T. Kanade; citation_publisher=Springer Verlag

citation_journal_title=IEEE Journal of Robotics and Automation; citation_title=A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses; citation_author=R.Y. Tsai; citation_volume=RA-3; citation_issue=4; citation_publication_date=1987; citation_pages=323-344; citation_id=CR18

citation_journal_title=IEEE Transactions on Robotics and Automation; citation_title=A general photogrammetric method for determining object position and orientation; citation_author=J.S.-C. Yuan; citation_volume=5; citation_issue=2; citation_publication_date=1989; citation_pages=129-142; citation_id=CR19

Thông tin
Thông tin xuất bản

International Journal of Computer Vision

Tập 22 Số 2

173-189

Thông tin tác giả