Contributions aux méthodes directes d'estimation et de commande basées sur la vision.

Accueil || Parcours || Recherche || S'enregistrer || Mon Compte || Contacts || Aide || Langues

Silveira Filho, Geraldo (2008) Contributions aux méthodes directes d'estimation et de commande basées sur la vision. Doctorat Informatique temps réel robotique et automatique, INRIA- Sophia Antipolis, ENSMP p.144.

Plein texte disponible en tant que : - phd_silveira.pdf ( 6120 Kb )

Licence: Copyright

Résumé

Dans leur grande majorité les techniques d'estimation et de contrôle basées sur la vision s'appuient sur l'extraction d'informations géométriques dans les images. L'objectif de cette thèse est de développer une nouvelle approche exploitant directement l'intensité des pixels dans l'image en s'affranchissant de l'étape d'extraction de ces informations. Nous espèrons montrer que le fait d'utiliser toute l'information contenue dans l'image permet en outre d'augmenter la précision et le domaine d'application. Dans ce but, nous proposons un modèle générique de transformation prenant à la fois en compte les aspects géométriques et photométriques que l'on associe à une méthode efficace d'optimisation pour le recalage d'images, qui est valide pour des modes d'acquisition variés (incluant les images couleurs) et pour des classes d'objets rigides ou déformables. En particulier, le nouveau modèle photométrique assure une robustes aux variations d'éclairage quelconques, et il est indépendants des attributs des objets et des caractéristiques de la caméra. Ce cadre méthodologique est formulé, dans le cas d'un modèle sténopé, à la fois dans le cas calibré et non calibré, les différences portant principalement sur la nature de la paramétrisation choisie. Une méthode robuste de suivi visuel est proposée permettant le recalage d'une image de référence tout au long de la séquence. A partir des paramètres estimés liant l'image de référence à l'image courante, nous proposons une nouvelle stratégie d'asservissement visuel permettant de contrôler les six degrés de liberté du mouvement de la caméra pour l'amener dans la pose où a été acquise l'image de référence. Cette nouvelle approche ne nécessite pas de connaissance précise sur les paramètres de la caméra ni sur la géométrie de l'objet observé, permettant ainsi d'obtenir une méthode générique et fiable. Dans le cas de l'utilisation d'une caméra calibrée, la méthode de suivi robuste permet d'accéder directement à la pose de la caméra et à la structure géométrique de la scène. Elle peut donc être appliquée pour proposer une nouvelle solution au problème de SLAM (Simultaneous Localization and Mapping) visuel. Enfin, nous présentons une méthode d'asservissement visuel intégrant directement les estimées fournies par la méthode de suivi et permettant ainsi la navigation autonome de robot dans un environnement inconnu a priori. Les méthodes développées tout au long de cette thèse ont été confrontées aux approches classiques de la littérature, et ont montré des avantages certains. Elles ont également été testée en condition réelle sur des séquences caractéristiques de différentes applications et dans des conditions variées. Les conditions et compromis à faire pour obtenir performances temps réel et précision, sont également discutés dans le document.

Références Bibliographiques

Baillard, C. and Zisserman, A. (1999). Automatic reconstruction of piecewise

planar models from multiple views, Proc. of the IEEE Computer Vision

and Pattern Recognition, pp. 559–565.

Baker, S., Gross, R. and Matthews, I. (2003). Lucas-kanade 20 years on: A unifying

framework: Part 3, Technical Report CMU-RI-TR-03-35, Carnegie

Mellon University, USA.

Bartoli, A. (2006). Groupwise geometric and photometric direct image registration,

Proc. of the British Machine Vision Conference.

Basri, R., Rivlin, E. and Shimshoni, I. (1999). Visual homing: surfing on the

epipoles, International Journal of Computer Vision 33(2): 22–39.

Benhimane, S. and Malis, E. (2004). Real-time image-based tracking of planes

using Efficient Second-order Minimization, Proc. of the IEEE/RSJ International

Conference on Intelligent Robots and Systems.

Benhimane, S. and Malis, E. (2006a). Homography-based 2D visual servoing,

Proc. of the IEEE International Conf. on Robotics and Automation, USA.

Benhimane, S. and Malis, E. (2006b). Integration of Euclidean constraints

in template based visual tracking of piecewise-planar scenes, Proc. of the

IEEE/RSJ International Conference on Intelligent Robots and Systems,

China, pp. 1218–1223.

Benhimane, S., Malis, E., Rives, P. and Azinheira, J. R. (2005). Vision-based

control for car platooning using homography decomposition, Proc. of the

IEEE International Conference on Robotics and Automation, Spain.

Berger, M.-O. and Simon, G. (1998). Robust image composition algorithms

for augmented reality, Proc. of the Asian Conference on Computer Vision,

China, pp. 360–367.

Black, M. J., Fleet, D. J. and Yacoob, Y. (2000). Robustly estimating changes

in image appearance, Computer Vision and Image Understanding 78: 8–31.

Blinn, J. F. (1977). Models of light reflection for computer synthesized pictures,

SIGGRAPH, pp. 192–198.

Broida, T. J., Chandrashekhar, S. and Chepalla, R. (1990). Recursive 3-D

motion estimation from a monocular image sequence, IEEE Transactions

on Aerospace and Electronic Systems 26(4): 639–656.

Brown, L. G. (1992). A survey of image registration techniques, ACM Computing

Surveys 24: 325–376.

Bruss, A. R. and Horn, B. K. P. (1983). Passive navigation, Computer Vision,

Graphics, and Image Processing 21: 3–20.

Bueno, S. S., Azinheira, J. R., Ramos, J. J. G., de Paiva, E. C., Carvalho, J.

R. H., Rives, P., Elfes, A. and Silveira, G. F. (2002). Project AURORA:

Towards an autonomous robotic airship, Workshop on Aerial Robotics,

IEEE/RSJ International Conference on Intelligent Robots and Systems,

Switzerland, pp. 43–53.

Carr, J., Fright, W. and Beatson, R. (1997). Surface interpolation with radial

basis functions for medical imaging, IEEE Transactions on Medical Imaging

16(1).

Chaumette, F. (1998). Potential problems of stability and convergence in imagebased

and position-based visual servoing, in D. J. Kriegman, G. D. Hager

and A. S. Morse (eds), The Confluence of Vision and Control, Vol. 237 of

LNCIS, Springer-Verlag, pp. 66–78.

Chaumette, F. and Hutchinson, S. (2006). Visual servo control part I: Basic

approaches, IEEE Robotics & Automation Magazine pp. 82–90.

Cobzas, D. and Sturm, P. (2005). 3D SSD tracking with estimated 3D planes,

Proc. Canadian Conf. on Comp. and Rob. Vision, pp. 129–134.

Collewet, C., Marchand, E. and Chaumette, F. (2008). Visual servoing set

free from image processing, Proc. of the IEEE International Conference on

Robotics and Automation, USA.

Comaniciu, D., Ramesh, V. and Meer, P. (2000). Real-time tracking of non-rigid

objects using mean-shift, Proc. of the IEEE Computer Vision and Pattern

Recognition.

Comport, A., Malis, E. and Rives, P. (2007). Accurate quadrifocal tracking for

robust 3D visual odometry, Proc. of the IEEE International Conference on

Robotics and Automation, Italy.

Cook, R. and Torrance, K. (1982). A reflectance model for computer graphics,

ACM Transactions on Graphics 1 pp. 7–24.

Davison, A. (2003). Real-time simultaneous localization and mapping with a

single camera, Proc. of the IEEE International Conference on Computer

Vision.

Dennis, J. E. and Schnabel, R. B. (1983). Numerical Methods for Unconstrained

Optimization and Nonlinear Equations, Classics in Applied Mathematics

16, SIAM.

Dick, A., Torr, P. and Cipolla, R. (2000). Automatic 3D modelling of architecture,

Proc. of the British Machine Vision Conference, pp. 372–381.

Eade, E. and Drummond, T. (2006). Scalable monocular SLAM, Proc. of the

IEEE Computer Vision and Pattern Recognition.

Espiau, B., Chaumette, F. and Rives, P. (1992). A new approach to visual servoing

in robotics, IEEE Transactions on Robotics and Automation 8(3): 313–

326.

Faugeras, O., Luong, Q.-T. and Papadopoulo, T. (2001). The geometry of

multiple images, The MIT Press.

Faugeras, O. and Lustman, F. (1988). Motion and structure from motion in a

piecewise planar environment, International Journal of Pattern Recognition

and Artificial Intelligence 2(3): 485–508.

Finlayson, G., Drew, M. and Funt, B. (1994). Color constancy: Generalized

diagonal transforms suffice, J. Opt. Soc. Am. A 11(11): 3011–3020.

Fischler, M. and Bolles, R. (1981). Random sample consensus: A paradigm for

model fitting with applications to image analysis and automated cartography,

Communications of the ACM 24: 381–385.

Galambos, C., Matas, J. and Kittler, J. (1999). Progressive probabilistic Hough

transform for line detection, Proc. of the IEEE Computer Vision and Pattern

Recognition, pp. 554–560.

Gouiff`es, M., Collewet, C., Fernandez-Maloigne, C. and Tr´emeau, A. (2006).

Feature points tracking using photometric model and colorimetric invariants,

Proc. of the European Conference on Colour in Graphics, Imaging,

and Vision, pp. 18–23.

Hager, G. and Belhumeur, P. (1998). Efficient region tracking with parametric

models of geometry and illumination, IEEE PAMI 20(10): 1025–1039.

Hall, B. (2003). Lie Groups, Lie Algebras, and Representations: An Elementary

Introduction, Vol. 222 of Graduate Texts in Mathematics, Springer.

Hartley, R. and Zisserman, A. (2000). Multiple View Geometry in Computer

Vision, Cambridge Univ. Press.

Haussecker, H.W. and Fleet, D. J. (2001). Computing optical flow with physical

models of brightness variation, IEEE Transactions on Pattern Analysis and

Machine Intelligence 23(6).

Horst, R. and Pardalos, P. M. (eds) (1995). Handbook of Global Optimization,

Kluwer.

Huber, P. J. (1981). Robust Statistics, John Wiley & Sons.

Hummel, R. and Sundareswaran, V. (1993). Motion parameter estimation from

global flow field data, IEEE Transactions on Pattern Analysis and Machine

Intelligence 15(5): 459–476.

Irani, M. and Anandan, P. (1999). All about direct methods, Proc. of the

Workshop on Vision Algorithms: Theory and practice.

Isaacson, E. and Keller, H. (1966). Analysis of numerical methods, John Wiley

& Sons.

Jin, H., Favaro, P. and Soatto, S. (2003). A semi-direct approach to structure

from motion, The Visual Computer 6: 377–394.

Jurie, F. and Dhome, M. (2002). Real time robust template matching, Proc. of

the British Machine Vision Conference, UK, pp. 123–131.

Kallem, V., Dewan, M., Swensen, J., Hager, G. and Cowan, N. (2007). Kernelbased

visual servoing, Proc. of the IEEE/RSJ International Conference on

Intelligent Robots and Systems, USA.

La Cascia, M., Sclaroff, S. and Athitsos, V. (2000). Fast, reliable head tracking

under varying illumination: An approach based on robust registration of

texture-mapped 3d models, IEEE Transactions on Pattern Analysis and

Machine Intelligence 22: 322–336.

Lai, S.-H. and Fang, M. (1999). Robust and efficient image alignment with

spatially varying illumination models, Proc. of the IEEE Computer Vision

and Pattern Recognition.

Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints,

International Journal of Computer Vision pp. 91–110.

Lucas, B. and Kanade, T. (1981). An iterative image registration technique with

an application to stereo vision, Proc. of the International Joint Conference

on Artificial Intelligence, pp. 674–679.

Luenberger, D. G. (1984). Linear and Nonlinear Programming, Addison-Wesley.

Ma, Y., Soatto, S., Kosecka, J. and Sastry, S. S. (2003). An Invitation to 3-D

Vision: From images to Geometric Models, Springer-Verlag.

Maintz, J. B. and Viergever, M. A. (1998). A survey of medical image registration,

Med. Image Anal. 2(1): 1–36.

Malis, E. (2004). Improving vision-based control using Efficient Second-order

Minimization techniques, Proc. of the IEEE International Conference on

Robotics and Automation, USA.

Malis, E. (2007). An efficient unified approach to direct visual tracking of rigid

and deformable surfaces, Proc. of the IEEE/RSJ International Conference

on Intelligent Robots and Systems, USA.

Malis, E. and Chaumette, F. (2002). Theoretical improvements in the stability

analysis of a new class of model-free visual servoing methods, IEEE

Transactions on Robotics and Automation 18(2): 176–186.

Malis, E., Chaumette, F. and Boudet, S. (1999). 2D 1/2 visual servoing, IEEE

Transactions on Robotics and Automation 15(2): 238–250.

Malis, E. and Rives, P. (2003). Robustness of image-based visual servoing with

respect to depth distribution errors, Proc. of the IEEE International Conference

on Robotics and Automation.

Maya-Mendez, M., Morin, P. and Samson, C. (2006). Control of a nonholonomic

mobile robot via sensor-based target tracking and pose estimation,

IEEE/RSJ International Conference on Intelligent Robots and Systems,

pp. 5612–5618.

Meer, P. (2004). Emerging Topics in Computer Vision, Prentice Hall, chapter

Robust techniques for computer vision.

Mei, C., Benhimane, S., Malis, E. and Rives, P. (2006). Constrained multiple

planar template tracking for central catadioptric cameras, Proc. of the

British Machine Vision Conference.

Mezouar, Y. and Chaumette, F. (2002). Path planning for robust image-based

control, IEEE Transactions on Robotics and Automation 18: 534–549.

Molton, N. D., Davison, A. J. and Reid, I. D. (2004). Locally planar patch

features for real-time structure from motion, Proc. of the British Machine

Vision Conference.

Montemerlo, M., Thrun, S., Koller, D. and Wegbreit, B. (2003). FastSLAM 2.0:

An improved particle filtering algorithm for simultaneous localization and

mapping that provably converges, Proc. of International Joint Conference

on Artificial Intelligence, pp. 1151–1156.

Montesinos, P., Gouet, V., Deriche, R. and Pele, D. (1999). Matching color

uncalibrated images using differential invariants, Image and Vision Computing

18(9): 659–671.

Morin, P. (2004). Stabilisation de systèmes non linéaires critiques et application

à la commande de véhicules, Habilitation à diriger des recherches,

Université de Nice-Sophia Antipolis.

Nastar, C., Moghaddam, B. and Pentland, A. (1996). Generalized image matching:

Statistical learning of physically-based deformations, Proc. of the European

Conference on Computer Vision.

Negahdaripour, S. (1998). Revised definition of optical flow: Integration of

radiometric and geometric cues for dynamic scene analysis, IEEE Transactions

on Pattern Analysis and Machine Intelligence 20(9): 961–979.

Nister, D. (2003). An efficient solution to the five-point relative pose problem,

Proc. of the IEEE Computer Vision and Pattern Recognition, Vol. 2,

pp. 195–202.

Okada, K. et al. (2001). Plane segment finder: Algorithm, implementation and

applications, Proc. of the IEEE International Conference on Robotics and

Automation, pp. 2120–2125.

Rives, P. (2000). Visual servoing based on epipolar geometry, Proc. of the

IEEE/RSJ International Conference on Intelligent Robots and Systems

Robots and Systems, pp. 602–607.

Saeedi, P., Lawrence, P. D. and Lowe, D. G. (2006). Vision-based 3-D trajectory

tracking for unknown environments, IEEE Transactions on Robotics

22(1): 119–136.

Samson, C., Espiau, B. and le Borges, M. (1990). Robot Control: the Task

Function Approach, Oxford University Press.

Siciliano, B. and Khatib, O. (eds) (2008). Springer Handbook of Robotics,

Springer.

Silveira, G. F., Carvalho, J. R. H., Rives, P., Azinheira, J. R., Bueno, S. S.

and Madrid, M. K. (2002). Optimal visual servoed guidance of outdoor

autonomous robotic airships, Proc. of the American Control Conference,

USA, pp. 779–784.

Silveira, G. and Malis, E. (2007a). Direct visual servoing with respect to rigid

objects, Proc. of the IEEE/RSJ International Conference on Intelligent

Robots and Systems, USA.

Silveira, G. and Malis, E. (2007b). Direct visual servoing with respect to rigid

objects, Research Report 6265, INRIA.

URL: https://hal.inria.fr/inria-00166417/en

Silveira, G. and Malis, E. (2007c). Real-time visual tracking under arbitrary

illumination changes, Proc. of the IEEE Computer Vision and Pattern

Recognition, USA.

Silveira, G. and Malis, E. (2007d). Suivi visuel efficace et robuste aux changements

d’éclairage quelconques, Proc. of the Journées ORASIS, France.

Silveira, G. and Malis, E. (2008). L’asservissement visuel direct, Proc. of the

Reconnaissance des Formes et Intelligence Artificielle, France.

Silveira, G., Malis, E. and Rives, P. (2006a). Real-time robust detection of

planar regions in a pair of images, Proc. of the IEEE/RSJ International

Conference on Intelligent Robots and Systems, China, pp. 49–54.

Silveira, G., Malis, E. and Rives, P. (2006b). Visual servoing over unknown, unstructured,

large-scale scenes, Proc. of the IEEE International Conference

on Robotics and Automation, USA, pp. 4142–4147.

Silveira, G., Malis, E. and Rives, P. (2007). An efficient direct method for

improving visual SLAM, Proc. of the IEEE International Conference on

Robotics and Automation, Italy.

Silveira, G., Malis, E. and Rives, P. (2008a). An efficient direct approach to

visual SLAM, IEEE Transactions on Robotics 24(5): 969–979. Special issue

on Visual SLAM.

Silveira, G., Malis, E. and Rives, P. (2008b). The efficient E-3D visual servoing,

International Journal of Optomechatronics 2(3): 166–184. Special Issue on

Visual Servoing.

Silveira, G., Malis, E. and Rives, P. (2008c). Une approche de SLAM visuel

direct, Proc. of the Reconnaissance des Formes et Intelligence Artificielle,

France.

Simon, G. and Berger, M.-O. (2002). Pose estimation for planar structures,

IEEE Comput. Graph. Appl. 22(6): 46–53.

Simon, G. and Berger, M.-O. (2008). Reconstruction et augmentation simultanées de scènes planes par morceaux, Proc. of the Reconnaissance des

Formes et Intelligence Artificielle, France.

Smith, R. C. and Cheeseman, P. (1986). On the representation and estimation

of spatial undertainty, Int. J. of Rob. Res. 5(4): 56–68.

Stein, G. and Shashua, A. (2000). Model-based brightness constraints: On direct

estimation of structure and motion, Transactions on Pattern Analysis and

Machine Intelligence 22: 992–1015.

Stewart, C. V. (1999). Robust parameter estimation in computer vision, SIAM

Rev. 41: 513–537.

Szeliski, R. (2005). Image alignment and stitching, in N. Paragios, Y. Chen and

O. Faugeras (eds), Handbook of Mathematical Models in Computer Vision,

Springer, pp. 273–292.

Szeliski, R. and Torr, P. H. S. (1998). Geometrically constrained structure from

motion: Points on planes, Proc. of the Workshop on 3D Structure from

Multiple Images of Large-Scale Environments, pp. 171 – 186.

Thuilot, B., Martinet, P., Cordesses, L. and Gallice, J. (2002). Position based

visual servoing: Keeping the object in the field of vision, Proc. of the IEEE

International Conference on Robotics and Automation, pp. 1624–1629.

Tomasi, C. and Kanade, T. (1992). Shape and motion from image streams under

orthography: A factorization method, International Journal on Computer

Vision 9(2): 137–154.

Torr, P. H. S. and Zisserman, A. (1999). Feature based methods for structure and

motion estimation, Workshop on Vision Algorithms: Theory and Practice,

pp. 278–294.

Tsai, R. (1987). Versatile camera calibration technique for high-accuracy 3D

machine vision metrology using off-the-shelf TV cameras and lenses, IEEE

Journal of Robotics and Automation 3(4): 323–344.

Tuytelaars, T. and Van Gool, L. J. (2004). Matching widely separated views

based on affine invariant regions, International Journal of Computer Vision

59(1): 61–85.

Varadarajan, V. (1974). Lie groups, Lie algebras, and their representations,

Prentice-Hall.

Vargas, M. and Malis, E. (2005). Visual servoing based on an analytical homography

decomposition, Proc. of the Joint IEEE Conference on Decision

and Control and European Control Conference, Spain.

144 Geraldo Silveira

Warner, F. W. (1987). Foundations of differential manifolds and Lie groups,

Springer Verlag.

Weiss, L. E. and Anderson, A. C. (1987). Dynamic sensor-based control of

robots with visual feedback, IEEE Journal of Robotics and Automation

3(5): 404–417.

Wilson, W. J., Hulls, C. C. W. and Bell, G. S. (1996). Relative end-effector

control using Cartesian position based visual servoing, IEEE Transactions

on Robotics and Automation 12(5): 684–696.

Xu, L. and Oja, E. (1993). Randomized Hough Transform (RHT): Basic mechanisms,

algorithms, and computational complexities, CVGIP: Image Understanding

57(2): 131–154.

Zhang, Z. (2000). A flexible new technique for camera calibration, IEEE Transactions

on Pattern Analysis and Machine Intelligence 22: 1330–1334.

Statistiques de consultation

Administrateurs de l'archive uniquement : éditer cet enregistrement