Abstract
In this work, we present an approach to jointly segment a rigid object in a 2D image and estimate its 3D pose, using the knowledge of a 3D model. We naturally couple the two processes together into a unique energy functional that is minimized through a variational approach. Our methodology differs from the standard monocular 3D pose estimation algorithms since it does not rely on local image features. Instead, we use global image statistics to drive the pose estimation process. This confers a satisfying level of robustness to noise and initialization for our algorithm, and bypasses the need to establish correspondences between image and object features. Moreover, our methodology possesses the typical qualities of region-based active contour techniques with shape priors, such as robustness to occlusions or missing information, without the need to evolve an infinite dimensional curve. Another novelty of the proposed contribution is to use a unique 3D model surface of the object, instead of learning a large collection of 2D shapes to accommodate for the diverse aspects that a 3D object can take when imaged by a camera. Experimental results on both synthetic and real images are provided, which highlight the robust performance of the technique on challenging tracking and segmentation applications.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Quan, L., Lan, Z.D.: Linear n-point camera pose determination. IEEE Transactions on Pattern Analysis and Machine Intelligence 21, 774–780 (1999)
Dhome, M., Richetin, M., Lapreste, J.T.: Determination of the attitude of 3d objects from a single perspective view. IEEE Trans. Pattern Anal. Mach. Intell. 11, 1265–1278 (1989)
Marchand, E., Bouthemy, P., Chaumette, F.: A 2d-3d model-based approach to real-time visual tracking. Image and Vision Computing 19, 941–955 (2001)
Zerroug, M., Nevatia, R.: Pose estimation of multi-part curved objects. In: ISCV 1995: Proceedings of the International Symposium on Computer Vision, p. 431 (1995)
Rosenhahn, B., Perwass, C., Sommer, G.: Pose estimation of free-form contours. IJCV 62, 267–289 (2005)
Drummond, T., Cipolla, R.: Real-time tracking of multiple articulated structures in multiple views. In: Proc. 6th European Conf.on Computer Vision, ECCV, pp. 20–36 (2000)
Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. IJCV, 22, 61–79 (1997)
Kichenassamy, S., Kumar, S., Olver, P., Tannenbaum, A., Yezzi, A.: Conformal curvature flow: From phase transitions to active vision. Archives for Rational Mechanics and Analysis 134, 275–301 (1996)
Zhu, S.C., Yuille, A.L.: Region competition: Unifying snakes, region growing, and Bayes/MDL for multiband image segmentation. IEEE Trans. PAMI 18, 884–900 (1996)
Chan, T., Vese, L.: Active contours without edges. IEEE TIP 10, 266–277 (2001)
Paragios, N., Deriche, R.: Geodesic active regions: A new paradigm to deal with frame partition problems in computer vision. Journal of Visual Communication and Image Representation 13, 249–268 (2002)
Dambreville, S., Yezzi, A., Niethammer, M., Tannenbaum, A.: A variational framework combining level-sets and thresholding. In: BMVC, pp. 266–280 (2007)
Michailovich, O., Rathi, Y., Tannenbaum, A.: Image segmentation using active contours driven by the bhattacharyya gradient flow. IEEE TIP, 2787–2801 (2007)
Kim, J., Fisher, J., Yezzi, A., Cetin, M., Willsky, A.: Nonparametric methods for image segmentation using information theory and curve evolution. In: Proc. ICIP, vol. 3, pp. 797–800 (2002)
Paragios, N., Deriche, R.: Geodesic active regions for supervised texture segmentation. In: ICCV (2), pp. 926–932 (1999)
Leventon, M., Grimson, E., Faugeras, O.: Statistical shape influence in geodesic active contours. In: Proc. IEEE CVPR, pp. 1316–1324 (2000)
Tsai, A., Yezzi, T., Wells, W., Tempany, C., Tucker, D., Fan, A., Grimson, E., Willsky, A.: A shape-based approach to the segmentation of medical imagery using level sets. IEEE Trans. on Medical Imaging 22, 137–153 (2003)
Cremers, D., Kohlberger, T., Schnoerr, C.: Shape statistics in kernel space for variational image segmentation. Pattern Recognition 36, 1292–1943 (2003)
Dambreville, S., Rathi, Y., Tannenbaum, A.: Shape-based approach to robust image segmentation using kernel pca. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 977–984 (2006)
Osher, S., Fedkiw, R.: Level Set Methods and Dynamic Implicit Surfaces. Springer, Heidelberg (2003)
Turk, G., Levoy, M.: Zippered polygon meshes from range images. In: Siggraph, pp. 311–318 (1994)
Yezzi, A., Soatto, S.: Structure from motion for scenes without features. In: Proc. IEEE CVPR, vol. 1, pp. 171–178 (2003)
Yezzi, A., Soatto, S.: Stereoscopic segmentation. International Journal of Computer Vision (IJCV) 53, 31–43 (2003)
Faugeras, O.D., Keriven, R.: Variational principles, surface evolution pdes, level set methods and the stereo problem. INRIA Tech. report 3021, 1–37 (1996)
Unal, G., Yezzi, A., Soatto, S., Slabaugh, G.: A variational approach to problems in calibration of multiple cameras. Trans. Pattern Analysis and Machine Intelligence 29, 1322–1338 (2007)
Rosenhahn, B., Brox, T., Weickert, J.: Three-dimensional shape knowledge for joint image segmentation and pose tracking. IJCV 73, 243–262 (2007)
Schmaltz, C., Rosenhahn, B., Brox, T., Cremers, D., Weickert, J., Wietzke, L., Sommer, G.: Region-based pose tracking. In: Pattern Recognition and Image Analysis, pp. 56–63 (2007)
DoCarmo, M.P.: Diferential Geometry of Curves and Surfaces. Prentice Hall, Englewood Cliffs (1976)
Lepetit, V., Fua, P.: Monocular model-based 3d tracking of rigid objects: A survey. Fundations and Trends in Computer Graphics and Vision 1, 1–89 (2005)
Forsyth, D., Ponce, J.: Computer Vision. Prentice Hall, Englewood Cliffs (2003)
Hartley, R., Zisserman, A.: Multiple view geometry in computer vision. Cambridge University Press, Cambridge (2000)
Ma, Y., Soatto, S., Kosecka, J., Sastry, S.: An invitation to 3D vision. Springer, Heidelberg
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dambreville, S., Sandhu, R., Yezzi, A., Tannenbaum, A. (2008). Robust 3D Pose Estimation and Efficient 2D Region-Based Segmentation from a 3D Shape Prior. In: Forsyth, D., Torr, P., Zisserman, A. (eds) Computer Vision – ECCV 2008. ECCV 2008. Lecture Notes in Computer Science, vol 5303. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88688-4_13
Download citation
DOI: https://doi.org/10.1007/978-3-540-88688-4_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88685-3
Online ISBN: 978-3-540-88688-4
eBook Packages: Computer ScienceComputer Science (R0)