Approche directe de L'estimation automatique de L'orientation 3D d'images. (A Direct Approach to Automatic Assessment of 3D Images Orientation)

Recemment, la geomatique grand public s'est emparee de la representation3D des bâtiments. Le besoin d'acquerir des images et de les restituer en3D, sous forme de maquettes parfaitement fideles a la realite, est ainsi devenu immense. On a donc vu, depuis une decennie, se construire des vehicules capables de photographier en stereoscopie des villes entieres, et il a fallu concevoir les algorithmes capables de traiter ces enormes quantites d'images. Tres naturellement, les industriels en charge de ces problemes se sont tournes vers les outils de vision par ordinateur et de robotique, tres bien adaptes aux calculs temps reel, oubliant l'essentiel de l'heritage de la photogrammetrie, orientee quant a elle vers une extreme precision, jugee ici commune une moindre priorite. Neanmoins, les algorithmes publies en vision par ordinateur presentaient de reels defauts lorsqu'ils etaient appliques a des surfaces planes et, manque de chance, ce cas est extremement courant dans des scenes urbaines (les facades …. ). Les recherches menees dans le cadre de cette these ont porte sur la recherche de solutions nouvelles, capables d'exploiter les specificites de telles images : tout d'abord, les travaux ont cherche a accelerer l'orientation relative des images, en tirant benefice des points de fuite figurant dans celles-ci. Pour ce faire, de nouvelles methodes d'extraction automatique de ces points ont ete mises au point, bien plus importantes que celles disponibles jusqu'ici. Ensuite, les recherches ont porte sur les moyens de corriger le defaut evoque precedemment pour les surfaces planes, et de nouveaux algorithmes capables de donner en temps quasi-reel de bonnes solutions d'orientation relative pour de telles scenes ont ete developpes. A cette fin, de nouveaux outils mathematiques ont ete utilises : les bases de Grobner. En rupture complete avec les solutions lineaires habituelles, ils permettent en effet une resolution directe des equations sous leur forme polynomiale. Ils evitent de passer par l'habituelle linearisation, qui necssitait une solution approchee parfois difficile a trouver dans les usages de photogrammetrie terrestre. Finalement, ces travaux ont porte sur des moyens d'accelerer les methodes d'orientation relative en exploitant oppurtunement la connaissance de la direction verticale, obtenue par exemple a l'aide du nouvel algorithme de detection des points de fuite. Au total, la these presentee represente une remise a plat generale des solutions permettant l'orientation et la localisation de tout un ensemble d'images.

[1]  Manolis I. A. Lourakis,et al.  The design and implementation of a generic sparse bundle adjustment software package based on the Le , 2004 .

[2]  Nick Barnes,et al.  Perspective Rectangle Detection , 2006 .

[3]  J. Awange,et al.  Exact solution of the nonlinear 7-parameter datum transformation by Groebner basis , 2004 .

[4]  Peter F. Sturm,et al.  Using geometric constraints through parallelepipeds for calibration and 3D modeling , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Edward J. Krakiwsky,et al.  Geodesy, the concepts , 1982 .

[6]  Robert M. Haralick,et al.  Review and analysis of solutions of the three point perspective pose estimation problem , 1994, International Journal of Computer Vision.

[7]  Ramakant Nevatia,et al.  Automatic pose estimation of complex 3D building models , 2002, Sixth IEEE Workshop on Applications of Computer Vision, 2002. (WACV 2002). Proceedings..

[8]  Rachid Deriche,et al.  From Noisy Edge Points to 3D Reconstruction of a Scene: A Robust Approach and its Uncertainty Analysis , 1992 .

[9]  Robert T. Collins,et al.  Vanishing point calculation as a statistical inference on the unit sphere , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[10]  D. Aguileraa,et al.  A NEW METHOD FOR VANISHING POINTS DETECTION IN 3 D RECONSTRUCTION FROM A SINGLE VIEW , 2005 .

[11]  Nicolas Paparoditis,et al.  ROBUST AND AUTOMATIC VANISHING POINTS DETECTION WITH THEIR UNCERTAINTIES FROM A SINGLE UNCALIBRATED IMAGE, BY PLANES EXTRACTION ON THE UNIT SPHERE , 2008 .

[12]  David Nistér,et al.  A Minimal Solution to the Generalised 3-Point Pose Problem , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[13]  Jorge Dias,et al.  Vision and Inertial Sensor Cooperation Using Gravity as a Vertical Reference , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Pascal Fua,et al.  On benchmarking camera calibration and multi-view stereo for high resolution imagery , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Soren W. Henriksen,et al.  Manual of photogrammetry , 1980 .

[16]  Franck Taillandier,et al.  Reconstruction de bâti en milieu urbain: une approche multi-vues. (Automatic buildings reconstruction in urban area: a multi-view approach) , 2004 .

[17]  Wenhan Xie,et al.  Multi-Image Based Camera Calibration Without Control Points , 2004 .

[18]  Christian Bräuer-Burchardt,et al.  Robust vanishing point determination in noisy images , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[19]  Rachid Deriche,et al.  Using Canny's criteria to derive a recursively implemented optimal edge detector , 1987, International Journal of Computer Vision.

[20]  Tomás Pajdla,et al.  Robust Rotation and Translation Estimation in Multiview Reconstruction , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Anders Heyden,et al.  Reconstruction from Calibrated Cameras—A New Proof of the Kruppa-Demazure Theorem , 1999, Journal of Mathematical Imaging and Vision.

[22]  Konrad Schindler,et al.  Towards Feature-Based Building Reconstruction from Images , 2003, WSCG.

[23]  Franck Jung,et al.  Détection automatique des points de fuite et calcul de leur incertitude à l'aide de la géomét rie projective Automatic detection of vanishing points and their uncertainty based on projective geometry , 2008 .

[24]  Bill Triggs,et al.  Camera pose and calibration from 4 or 5 known 3D points , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[25]  Charalampos Georgiadis,et al.  IMAGE ORIENTATION FOR INTERACTIVE TOURS OF VIRTUALLY-MODELED SITES , 2005 .

[26]  David Nistér,et al.  An efficient solution to the five-point relative pose problem , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[27]  Laureano González-Vega,et al.  Implicitization of Parametric Curves and Surfaces by Using Multidimensional Newton Formulae , 1997, J. Symb. Comput..

[28]  V. Cantoni,et al.  Vanishing point detection: representation analysis and new approaches , 2001, Proceedings 11th International Conference on Image Analysis and Processing.

[29]  David A. Cox,et al.  Using Algebraic Geometry , 1998 .

[30]  Roland Siegwart,et al.  A Lane Detection Vision Module for Driver Assistance , 2004 .

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

[32]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[33]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[34]  Ian D. Reid,et al.  Single View Metrology , 2000, International Journal of Computer Vision.

[35]  Stephen T. Barnard,et al.  Interpreting Perspective Image , 1983, Artif. Intell..

[36]  Thomas S. Huang,et al.  Theory of Reconstruction from Image Motion , 1992 .

[37]  Joseph L. Awange,et al.  Nonlinear analysis of the three-dimensional datum transformation [conformal group ℂ7(3)] , 2003 .

[38]  O. Faugeras,et al.  Motion from point matches: Multiplicity of solutions , 1989, [1989] Proceedings. Workshop on Visual Motion.

[39]  Cordelia Schmid,et al.  A Performance Evaluation of Local Descriptors , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[40]  Attention-Based Vanishing Point Detection , 2006, 2006 International Conference on Image Processing.

[41]  Long Quan,et al.  Determining perspective structures using hierarchical Hough transform , 1989, Pattern Recognit. Lett..

[42]  Takeo Kanade,et al.  Shape and motion from image streams under orthography: a factorization method , 1992, International Journal of Computer Vision.

[43]  F. Jung,et al.  Détection entièrement automatique de points de fuite dans des scènes architecturales urbaines , 2006 .

[44]  Jaime López-Krahe,et al.  Contribution to the Determination of Vanishing Points Using Hough Transform , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[45]  Long Quan,et al.  Linear N-Point Camera Pose Determination , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[46]  Richard Szeliski,et al.  Modeling the World from Internet Photo Collections , 2008, International Journal of Computer Vision.

[47]  Jake K. Aggarwal,et al.  Determining vanishing points from perspective images , 1984, Comput. Vis. Graph. Image Process..

[48]  Seth J. Teller,et al.  Automatic recovery of relative camera rotations for urban scenes , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[49]  Sunil Arya,et al.  An optimal algorithm for approximate nearest neighbor searching fixed dimensions , 1998, JACM.

[50]  Bill Triggs Routines for Relative Pose of Two Calibrated Cameras from 5 Points , 2000 .

[51]  E. S. Kennedy Al-Kāshī's "Plate of Conjunctions" , 1947, Isis.

[52]  Richard I. Hartley,et al.  Reconstruction from six-point sequences , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[53]  Roberto Cipolla,et al.  Camera Calibration from Vanishing Points in Image of Architectural Scenes , 1999, BMVC.

[54]  David Nister,et al.  Recent developments on direct relative orientation , 2006 .

[55]  Michael Bosse,et al.  Calibrated, Registered Images of an Extended Urban Area , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[56]  Siniša Šegvić,et al.  Performance evaluation of the five-point relative pose with emphasis on planar scenes , 2007 .

[57]  Andrew C. Gallagher Using vanishing points to correct camera rotation in images , 2005, The 2nd Canadian Conference on Computer and Robot Vision (CRV'05).

[58]  P. Wolf,et al.  Elements of Photogrammetry(with Applications in GIS) , 2000 .

[59]  Marc-André Ameller,et al.  Le Calcul de Pose: de nouvelles méthodes matricielles , 2002 .

[60]  J. Faugère A new efficient algorithm for computing Gröbner bases (F4) , 1999 .

[61]  Joseph L. Awange,et al.  Solving Algebraic Computaitonal problems in Geodesy and Geoinformatics : The Answer to Modern Challenges , 2005 .

[62]  W. Gander,et al.  Least-squares fitting of circles and ellipses , 1994 .

[63]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[64]  Sumanta N. Pattanaik,et al.  ATIP: A Tool for 3D Navigation inside a Single Image with Automatic Camera Calibration , 2006, TPCG.

[65]  Évelyne Lutton Reconnaissance du point de prise de vue d'une photographie a partir d'un partir d'un modele de scene , 1990 .

[66]  Nicolas Paparoditis,et al.  The Five Points Pose Problem : A New and Accurate Solution Adapted to any Geometric Configuration , 2008, PSIVT.

[67]  H. M. Karara,et al.  Direct Linear Transformation from Comparator Coordinates into Object Space Coordinates in Close-Range Photogrammetry , 2015 .

[68]  Jefferey A. Shufelt,et al.  Performance Evaluation and Analysis of Vanishing Point Detection Techniques , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[69]  F. A. Heuvel VANISHING POINT DETECTION FOR ARCHITECTURAL PHOTOGRAMMETRY , 1998 .

[70]  Luc Van Gool,et al.  The cascaded Hough transform as an aid in aerial image interpretation , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[71]  Christian Bräuer-Burchardt,et al.  Facade Reconstruction of Destroyed Buildings Using Historical Photographs , 2001 .

[72]  F. Jung,et al.  Estimation automatique de l'orientation relative: une approche directe basée sur la résolution de systèmes polynomiaux multivariables , 2008 .

[73]  Zuzana Kukelova,et al.  Polynomial Eigenvalue Solutions to the 5-pt and 6-pt Relative Pose Problems , 2008, BMVC.

[74]  Agnès Desolneux,et al.  Vanishing Point Detection without Any A Priori Information , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[75]  Carsten Rother,et al.  A New Approach for Vanishing Point Detection in Architectural Environments , 2000, BMVC.

[76]  Matthew A. Brown,et al.  Unsupervised 3D object recognition and reconstruction in unordered datasets , 2005, Fifth International Conference on 3-D Digital Imaging and Modeling (3DIM'05).

[77]  Mahzad Kalantari,et al.  IMPLEMENTATION OF A LOW-COST PHOTOGRAMMETRIC METHODOLOGY FOR 3D MODELLING OF CERAMIC FRAGMENTS , 2007 .

[78]  J. Philip A non-iterative algorithm for determining all essential matrices corresponding to five point pairs , 1996 .

[79]  Edward M. Riseman,et al.  An Error Analysis for Surface Orientation from Vanishing Points , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[80]  Fabrice Rouillier,et al.  Solving Zero-Dimensional Systems Through the Rational Univariate Representation , 1999, Applicable Algebra in Engineering, Communication and Computing.

[81]  Daniel Lazard,et al.  Gröbner-Bases, Gaussian elimination and resolution of systems of algebraic equations , 1983, EUROCAL.

[82]  Franck Jung,et al.  Precise, automatic and fast method for vanishing point detection , 2009 .

[83]  Beatrice Brillault-O'Mahony,et al.  New method for vanishing point detection , 1991, CVGIP Image Underst..

[84]  Konrad Schindler,et al.  Metropogis: a city information system , 2002, Proceedings. International Conference on Image Processing.

[85]  Nick Barnes,et al.  Insect Inspired Three Dimensional Centring , 2008 .

[86]  Martin Byröd,et al.  Fast and Stable Polynomial Equation Solving and Its Application to Computer Vision , 2009, International Journal of Computer Vision.

[87]  Amir Hashemi,et al.  A Hybrid Algorithm for Solving 7 Parameters Transformation , 2009, 2009 11th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing.

[88]  L. Grammatikopoulos,et al.  A UNIFIED APPROACH FOR AUTOMATIC CAMERA CALIBRATION FROM VANISHING POINTS , 2006 .

[89]  Fabrice Rouillier,et al.  On solving the direct kinematics problem for parallel robots , 2006 .

[90]  W. Föstner Reliability analysis of parameter estimation in linear models with application to mensuration problems in computer vision , 1987 .

[91]  M. A. R. Cooper,et al.  Control Surveys In Civil Engineering , 1987 .

[92]  Berthold K. P. Horn,et al.  Closed-form solution of absolute orientation using unit quaternions , 1987 .

[93]  A. Cayley Sur quelques propriétés des déterminants gauches. , 1846 .

[94]  Larry S. Davis,et al.  Exact and Approximate Solutions of the Perspective-Three-Point Problem , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[95]  B. Caprile,et al.  Using vanishing points for camera calibration , 1990, International Journal of Computer Vision.

[96]  H. C. Longuet-Higgins,et al.  A computer algorithm for reconstructing a scene from two projections , 1981, Nature.

[97]  J. G. Semple,et al.  Algebraic Projective Geometry , 1953 .

[98]  Rud Sturm,et al.  Das Problem der Projectivität und seine Anwendung auf die Flächen zweiten Grades , 1869 .

[99]  Matthijs C. Dorst Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[100]  Mohamed Benallal,et al.  Système de calibration de caméra Localisation de forme polyédrique par vision monoculaire , 2002 .

[101]  Hongdong Li,et al.  Five-Point Motion Estimation Made Easy , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[102]  Nicolas Simond,et al.  Trajectography of an uncalibrated stereo rig in urban environments , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[103]  P. Grussenmeyer,et al.  SOLUTIONS FOR EXTERIOR ORIENTATION IN PHOTOGRAMMETRY: A REVIEW , 2002 .

[104]  J. M. Rojas,et al.  The Exact Rational Univariate Representation and Its Application , 2003 .

[105]  Bart C. Nabbe,et al.  An Alternative Formulation for Five Point Relative Pose Problem , 2007, 2007 IEEE Workshop on Motion and Video Computing (WMVC'07).

[106]  Eva Savina Malinverni,et al.  PHOTOINTERPRETATION AND SMALL SCALE STEREOPLOTTING WITH DIGITALLY RECTIFIED PHOTOGRAPHS WITH GEOMETRICAL CONSTRAINTS 1 , 2001 .

[107]  D. W. Murray,et al.  Camera Calibration using Vanishing Points , 1992 .

[108]  Luis Salgado,et al.  Robust multiple lane road modeling based on perspective analysis , 2008, 2008 15th IEEE International Conference on Image Processing.

[109]  David A. Cox,et al.  Ideals, Varieties, and Algorithms: An Introduction to Computational Algebraic Geometry and Commutative Algebra, 3/e (Undergraduate Texts in Mathematics) , 2007 .

[110]  Amnon Shashua,et al.  Off-road Path Following using Region Classification and Geometric Projection Constraints , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[111]  E. H. Thompson A RATIONAL ALGEBRAIC FORMULATION OF THE PROBLEM OF RELATIVE ORIENTATION , 2006 .