Planification du placement de caméras pour des mesures 3D de précision. (Planning Camera Placement for Accurate 3D Measurements)

Les mesures tridimensionnelles peuvent etre obtenues a partir de plusieurs images par la methode de triangulation. Ce travail etudie le probleme du placement des cameras de facon a obtenir une erreur minimale lors des mesures tridimensionnelles. En photogrammetrie, on parlera du concept du reseau de cameras. Nous poserons le probleme en termes d'optimisation et nous le diviserons en deux parties : 1) une partie analytique dediee a l'analyse de l'erreur de propagation d'ou decoulera un critere. 2) Un processus global d'optimisation minimisera ce critere. De ce cote-la, l'approche consiste en une analyse d'incertitude appliquee au processus de reconstruction d’ou une matrice de covariance sera calculee. Cette matrice represente l'incertitude de la detection pour lequel le critere est derive. Par ailleurs, l'optimisation a des aspects discontinus essentiellement du a l'inobservabilite des points. Ce facteur va nous amener a utiliser un processus d'optimisation combinatoire que nous avons resolu en utilisant un algorithme genetique multicellulaire. Des resultats experimentaux sont inclus pour illustrer l’efficacite et la rapidite de la solution.

[1]  Glenn H. Tarbox,et al.  Planning for Complete Sensor Coverage in Inspection , 1995, Comput. Vis. Image Underst..

[2]  Bir Bhanu,et al.  CAD-Based 3D Object Representation for Robot Vision , 1987, Computer.

[3]  Clive S. Fraser.  Network design considerations for non-topographic photogrammetry , 1994 .

[4]  Pradeep K. Khosla,et al.  Dynamic Sensor Placement Using Controlled Active Vision , 1993 .

[5]  Lester A. Gerhardt,et al.  Registration of dissimilar featureless models for inspection , 1993, [1993] Proceedings IEEE International Conference on Robotics and Automation.

[6]  Scott Mason.  Expert system based design of photogrammetric networks , 1994 .

[7]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[8]  S. Mason.  Heuristic reasoning strategy for automated sensor placement , 1997 .

[9]  Jussi Paakkari,et al.  Computer aided measurement planning for 3-D machine vision , 1991 .

[10]  C S Fraser,et al.  DIMENSIONAL CHARACTERIZATION OF A LARGE AIRCRAFT STRUCTURE BY PHOTOGRAMMETRY , 1992 .

[11]  Roger Mohr,et al.  Projective Geometry and Computer Vision , 1993, Handbook of Pattern Recognition and Computer Vision.

[12]  Roger Y. Tsai,et al.  Analytical characterization of the feature detectability constraints of resolution, focus, and field-of-view for vision sensor planning , 1994 .

[13]  Cregg K. Cowan.  Model-based synthesis of sensor location , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[14]  Roger Y. Tsai,et al.  Real time versatile robotics hand/eye calibration using 3D machine vision , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[15]  Scott Joseph Mason.  Expert system-based design of close-range photogrammetric networks , 1995 .

[16]  Allen M. Waxman,et al.  Adaptive 3-D Object Recognition from Multiple Views , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Alan D. Jones.  Manual of Photogrammetry, eds C.C. Slama, C. Theurer and S.W. Hendrikson, American Society of Photogrammetry, Falls Church, Va., 1980, Fourth Edition, 180 × 260mm, xvi and 1056 pages (with index), 72 tables, 866 figures. ISBN 0 937294 01 2. , 1982 .

[18]  Roger Y. Tsai,et al.  Model-Based Planning of Sensor Placement and Optical Settings , 1990, Other Conferences.

[19]  Pradeep K. Khosla,et al.  Integrating Sensor Placement and Visual Tracking Strategies , 1993, ISER.

[20]  Hong Zhang.  Two-dimensional optimal sensor placement , 1995, IEEE Trans. Syst. Man Cybern..

[21]  Yoshiaki Shirai,et al.  Illumination setup planning for a hand-eye system based on an environmental model , 1991, Adv. Robotics.

[22]  Franc Solina,et al.  Planning the Optimal Set of Views Using the Max-Min Principle , 1994, ECCV.

[23]  Roger Mohr,et al.  Optimal camera placement to obtain accurate 3D point positions , 1997, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[24]  Alex Pentland,et al.  A New Sense for Depth of Field , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Roger Y. Tsai,et al.  Calibration of a computer controlled robotic vision sensor with a zoom lens , 1994 .

[26]  Masaru Ishii,et al.  Occlusion Avoidance of Visual Sensors based on a Hand-Eye Action Simulator System : HEAVEN , 1986 .

[27]  Konstantinos A. Tarabanis,et al.  The MVP sensor planning system for robotic vision tasks , 1995, IEEE Trans. Robotics Autom..

[28]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[29]  Hugh F. Durrant-Whyte,et al.  Uncertain geometry , 1989 .

[30]  Peter Kovesi,et al.  Automatic Sensor Placement from Vision Task Requirements , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Dieter Fritsch,et al.  First order design strategies for industrial photogrammetry , 1990, ISPRS International Conference on Computer Vision and Remote Sensing.

[32]  Erik W. Grafarend,et al.  Optimization of Geodetic Networks , 1974 .

[33]  John H. Holland,et al.  When will a Genetic Algorithm Outperform Hill Climbing , 1993, NIPS.

[34]  J. K. Kinnear,et al.  Advances in Genetic Programming , 1994 .

[35]  Tomomasa Sato,et al.  Automatic planning of light source and camera placement for an active photometric stereo system , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[36]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1992, Artificial Intelligence.

[37]  Armin Gruen,et al.  Automating the sensor-placement task for accurate dimensional inspection , 1994, Other Conferences.

[38]  O. Faugeras.  Three-dimensional computer vision: a geometric viewpoint , 1993 .

[39]  H. Beyer.  Geometric and radiometric analysis of a CCD-camera based photogrammetric close-range system , 1992 .

[40]  Thomas P. Kersten,et al.  Sequential estimation in robot vision , 1995 .

[41]  S. Mason.  Conceptual model of the convergent multistation network configuration task , 1995 .

[42]  Bharath Modayur,et al.  Automatic light-source placement for detecting object features , 1992, Other Conferences.

[43]  Steven D. Blostein,et al.  Error Analysis in Stereo Determination of 3-D Point Positions , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Besma Abidi.  Automatic sensor placement , 1995, Other Conferences.

[45]  Roger Y. Tsai,et al.  Techniques for calibration of the scale factor and image center for high accuracy 3D machine vision metrology , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[46]  Robert M. Haralick,et al.  Optimal Sensor and Light Source Positioning for Machine Vision , 1995, Comput. Vis. Image Underst..

[47]  David B. Fogel,et al.  Evolutionary computation - toward a new philosophy of machine intelligence (3. ed.) , 1995 .

[48]  Roger Y. Tsai,et al.  A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses , 1987, IEEE J. Robotics Autom..

[49]  Roger Mohr,et al.  Camera Network Design by Natural Selection , 1998 .

[50]  Anil K. Jain,et al.  A Survey of Automated Visual Inspection , 1995, Comput. Vis. Image Underst..

[51]  Hong Zhang,et al.  Optimal sensor placement , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[52]  C. Fraser.  Photogrammetric measurement to one part in a million , 1992 .

[53]  R. Mohr,et al.  Optimal 3D Sensor Placement to Obtain Accurate 3D Point Positions , 1997 .

[54]  Konstantinos A. Tarabanis,et al.  Computing viewpoints that satisfy optical constraints , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[55]  Roger Y. Tsai,et al.  Automated sensor planning for robotic vision tasks , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[56]  Takeo Kanade,et al.  Sensor placement design for object pose determination with three light-stripe range finders , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[57]  A. Gruen.  ADAPTIVE LEAST SQUARES CORRELATION: A POWERFUL IMAGE MATCHING TECHNIQUE , 1985 .

[58]  Melanie Mitchell,et al.  The royal road for genetic algorithms: Fitness landscapes and GA performance , 1991 .

[59]  Andrew M. Wallace,et al.  Model-based planning of optimal sensor placements for inspection , 1997, IEEE Trans. Robotics Autom..

[60]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[61]  Su-Shing Chen.  A Geometric Approach To Multisensor Fusion , 1988, Defense, Security, and Sensing.

[62]  Sabry F. El-Hakim,et al.  Multicamera vision-based approach to flexible feature measurement for inspection and reverse engineering , 1993 .

[63]  Armin Grün,et al.  Automatic Sensor Placement for Accurate Dimensional Inspection , 1995, Comput. Vis. Image Underst..

[64]  Konstantinos A. Tarabanis,et al.  A survey of sensor planning in computer vision , 1995, IEEE Trans. Robotics Autom..

[65]  Thomas Bäck,et al.  Evolutionary computation: comments on the history and current state , 1997, IEEE Trans. Evol. Comput..

[66]  R. Kories,et al.  Adaptive control of cooperating sensors: focus and stereo ranging with an agile camera system , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[67]  Aviv Bergman,et al.  Determining the camera and light source location for a visual task , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

[68]  Bill Triggs,et al.  Automatic Task Planning for Robot Vision , 1996 .