This Article 
 Bibliographic References 
 Add to: 
Structure From Controlled Motion
May 1996 (vol. 18 no. 5)
pp. 492-504

Abstract—This paper deals with the recovery of 3D information using a single mobile camera in the context of active vision. First, we propose a general revisited formulation of the structure-from-known-motion issue. Within the same formalism, we handle various kinds of 3D geometrical primitives such as points, lines, cylinders, spheres, etc. We also aim at minimizing effects of the different measurement errors which are involved in such a process. More precisely, we mathematically determine optimal camera configurations and motions which lead to a robust and accurate estimation of the 3D structure parameters. We apply the visual servoing approach to perform these camera motions using a control law in closed-loop with respect to visual data. Real-time experiments dealing with 3D structure estimation of points and cylinders are reported. They demonstrate that this active vision strategy can very significantly improve the estimation accuracy.

[1] L. Abbott and N. Ahuja, "Active Surface Reconstruction by Integrating Focus, Vergence, Stereo, and Camera Calibration," Proc. Third ICCV, pp. 489-492,Osaka, Japan, Dec. 1990.
[2] G. Adiv, “Inherent Ambiguities in Recovering 3-D Motion and Structure from a Noisy Flow Field,” Trans. Pattern Analysis and Machine Intelligence, vol. 11, pp. 477–489, 1989.
[3] J. Aloimonos, I. Weiss, and A. Bandopadhay, "Active Vision," Proc. First ICCV,London, England, pp. 35-54, June 1987.
[4] R. Bajcsy, "Active Perception," Proc. IEEE, vol. 76, no. 8, pp. 996-1,005, Aug. 1988.
[5] D.H. Ballard, “Animate Vision,” Artificial Intelligence, vol. 48, pp. 57-86, 1991.
[6] A. Bandopadhay, B. Chandra, and D. Ballard, "Egomotion Using Active Vision," Proc. CVPR 86, pp. 498-503,Miami, June 1986.
[7] S. Boukir, P. Bouthemy, F. Chaumette, and D. Juvin, "Real-Time Contour Matching Over Time in an Active Vision Context," Proc. Eighth Scandinavian Conf. Image Analysis, vol. 1, pp. 113-120,Tromso, Norway, May 1993.
[8] S. Boukir, "Reconstruction 3D d'un Environnement Statique par Vision Active," PhD thesis, no. 1,074, IRISA, Univ. of Rennes I, France, Oct. 1993.
[9] C. Brown, "Issues in Selective Perception," Proc. 11th ICPR, pp. 21-24, The Hague, Netherlands, vol. 1, Aug. 1992.
[10] F. Chaumette, S. Boukir, P. Bouthemy, and D. Juvin, "Optimal Estimation of 3D Structures Using Visual Servoing," Proc. CVPR 94, pp. 347-354,Seattle, June 1994.
[11] C. Chien and J.K. Aggarwal,“Model reconstruction and shape recognition from occluding contours,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 11, pp. 372-389, 1989.
[12] J. Crowley, P. Bobet, and M. Mesrabi, "Layered Control of a Binocular Camera Head," Int'l J. Pattern Recognition and Artificial Intelligence, vol. 7, no. 1, pp. 109-116, Feb. 1993.
[13] K. Daniilidis and H.H. Nagel, "Analytical Results on Error Sensitivity of Motion Estimation From Two Views," Proc. First ECCV, pp. 199-208,Antibes, France, Apr. 1990.
[14] B. Espiau, F. Chaumette, and P. Rives, “A New Approach to Visual Servoing in Robotics,” IEEE T-Robotics and Automation, vol. 8, no. 3, 1992.
[15] B. Espiau and P. Rives, "Closed-Loop Recursive Estimation of 3D Features for a Mobile Vision System," IEEE Int'l Conf. Robotics and Automation,Raleigh, N.C., vol. 3, pp. 1,436-1,443, Apr. 1987.
[16] O.D. Faugeras, Three-Dimensional Computer Vision: A Geometric Viewpoint.Cambridge, Mass.: MIT Press, 1993.
[17] K. Hashimoto ed., Visual Servoing. World Scientific Series in Robotics and Automated Systems, vol. 7, Singapore, 1993.
[18] J. Herve and Y. Aloimonos, "Exploratory Active Vision: Theory," Proc. CVPR 92, pp. 10-15,Champaign, Ill., June 1992.
[19] B.K. Horn, Robot Vision. Cambridge, Mass.: MIT Press, 1986.
[20] L. Huang and J. Aloimonos, "Relative Depth From Motion Using Normal Flow: An Active and Purposive Solution," Proc. IEEE Workshop Visual Motion, pp. 196-204,Princeton, N.J., Oct. 1991.
[21] S. Li, I. Miyawaki, H. Ishiguro, and S. Tsuji, "Realizing Active Vision by a Mobile Robot," Proc. IEEE Workshop Visual Motion, pp. 205-210,Princeton, N.J., Oct. 1991.
[22] L. Matthies, T. Kanade, and R. Szelisli, "Kalman Filter-Based Algorithms for Estimating Depth From Image Sequences," IJCV, vol. 3, pp. 209-236, 1989.
[23] E. Marchand and F. Chaumette, "Active Visual 3D Perception," IEEE Int'l Workshop Vision for Robots, pp. 10-17,Pittsburgh, Pa., Aug. 1995.
[24] E. Milios, M. Jenkin, and J. Tsotsos, "Design and Performance of Trish, a Binocular Robot Head With Torsional Eye Movements," Int'l J. Pattern Recognition and Artificial Intelligence, vol. 7, no. 1, pp. 51-68, Feb. 1993.
[25] A. Mitiche and G. Habelrih, "Interpretation of Straight Line Correspondences Using Angular Relations," Pattern Recognition, vol. 22, no. 3, pp. 299-308, 1989.
[26] S. Negahdaripour and B.K.P. Horn, “Direct Passive Navigation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 1, pp. 168-176, Jan. 1987.
[27] J. Oliensis and J.I. Thomas, "Incorporating Motion Error in Multi-Frame Structure From Motion, IEEE Workshop on Visual Motion, pp. 8-13, Princeton, N.J., Los Alamitos, Calif.: CS Press, Oct. 1991.
[28] K. Pahlavan and J. Eklundh, “A Head-Eye System—Analysis and Design,” CVGIP: Image Understanding, vol. 56, no. 1, July 1992.
[29] R. Safaee-Rad, I. Tchoukanov, K.C. Smith, and B. Benhabib, "Three-Dimensional Location Estimation of Circular Features for Machine Vision," IEEE Trans. Robotics and Automation, vol. 8, no. 5, pp. 624-639, Oct. 1992.
[30] P. Rives and M. Xie, "Towards Dynamic Vision," Proc. IEEE Workshop Interpretation of 3D Scenes,Austin, Tex., Nov. 1989.
[31] G. Sandini and M. Tistarelli, "Recovery of Depth Information: Camera Motion as an Integration to Stereo," Proc. IEEE Workshop Motion, pp. 39-43,Charleston, S.C., May 1986.
[32] G. Sandini and M. Tistarelli,“Active tracking strategy for monocular depth inference over multiple frames,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 1, pp. 13-27, 1990.
[33] A. Shashua,“Projective depth: A geometric invariant for 3D reconstruction from two perspective/orthographic views and for visual recognition,” Proc. Int’l Conf. Computer Vision, pp. 583-590,Berlin, May 1993.
[34] W.B. Thompson, P. Lechleider, and E.R. Stuck, "Detectng Moving Objects Using the Rigidity Constraint," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 2, Feb. 1993.
[35] M. Tistarelli and G. Sandini,“Dynamic aspects in active vision,” CVGIP: Image Understanding, vol. 56, no. 1, pp. 108-192, 1992.
[36] C. Tomasi and T. Kanade, "Shape and Motion From Image Streams Under Orthography: A Factorization Method," Int'l J. Computer Vision, vol. 9, no. 2, pp. 137-154, 1992.
[37] D. Vernon and M. Tistarelli, "Using Camera Motion to Estimate Range for Robotic Part Manipulation," IEEE Trans. on Robotics and Automation, vol. 6, no. 5, pp. 509-521, Oct. 1990.
[38] M. Viala, C. Faye, J.-P. Guérin, and D. Juvin, "Cylindrical Object Reconstruction From a Sequence of Images," Proc. SPIE Intelligent Robots and Visual Communications,Boston, Nov. 1992.
[39] T. Viéville, J.-O. Ekhlund, K. Pahlavan, and T. Uhlin, "An Example of Artificial Oculomotor Behavior," Proc. Seventh IEEE Symp. Intelligent Control, pp. 348-353,Glasgow, Scotland, Aug. 1992.
[40] A. Waxman, B. Parsi, and M. Subbarao, "Closed-Form Solutions to Image Flow Equations for 3D Structure and Motion," IJCV, vol. 1, no. 3, pp. 239-258, Oct. 1987.
[41] A.C. Sanderson, L.E. Weiss, and C.P. Neumann, “Dynamic Sensor Based Control of Robots with Visual Feedback,” IEEE J. Robotics and Automation, vol. 3, pp. 404-417, 1987.
[42] J. Weng, T.S. Huang, and N. Ahuja, Motion and Structure from Line Correspondences: Closed-Form Solution, Uniqueness, and Optimization Trans. Pattern and Machine Intelligence, vol. 14, no. 3, pp. 318-336, Mar. 1992.

Index Terms:
Computer vision, robotics, active vision, structure from motion, vision-based control.
François Chaumette, Samia Boukir, Patrick Bouthemy, Didier Juvin, "Structure From Controlled Motion," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 5, pp. 492-504, May 1996, doi:10.1109/34.494639
Usage of this product signifies your acceptance of the Terms of Use.