Abstract.
Pose retrieval of a rigid object from monocular video sequences or images is addressed. Initially, the object pose is estimated in each image assuming flat depth maps. Shape-from-silhouette is then applied to make a 3-D model (volume), which is used for a new round of pose estimations, this time by a model-based method that gives better estimates. Before repeating this process by building a new volume, pose estimates are adjusted to reduce error by maximizing a novel quality factor for shape-from-silhouette volume reconstruction. The feedback loop is terminated when pose estimates do not change much, as compared with those produced by the previous iteration. Based on a theoretical study of the proposed system, a test of convergence to a given set of poses is devised. Reliable performance of the system is also proved by several experiments on both synthetic and real image sequences. No model is assumed for the object and no feature point is detected or tracked as there is no problematic feature matching or correspondence. Our method can be used for 3-D object tracking in video, 3-D modeling, and volume reconstruction from video.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aloimonos Y (1990) Perpective approximations. Image Vision Comput 8(3):177-192
Apostol TM (1967) Calculus, vol 2, chap 2.8.18. Blaisdell, Waltham, MA
Avanaki AN, Hamidzadeh B, Kossentini F (2000) Multi-objective retrieval of object pose from video. In: Proceedings of the IEEE conference on tools with artificial intelligence, Vancouver, BC, Canada, November 2000, pp 242-249
Barron J, Klette R (2002) Quantitative color optical flow. In: Proceedings of the 16th international conference on pattern recognition, Quebec City, QC, Canada, August 2002, 4:251-255
Bellman R (1964a) Perturbation techniques in mathematics, physics, and engineering, chap 1.22. Holt, Rinehart and Winston, New York, pp 41-42
Bellman R (1964b) Perturbation techniques in mathematics, physics, and engineering. Holt, Rinehart and Winston, New York, p 40
Bozdagi G(1994) 3-D motion estimation and wireframe adaptation including photometric effects for model-based coding of facial image sequences. IEEE Trans Circuits Sys Video Technol 4(3):246-256
Broadhurst A(2001) A probabilistic framework for space carving. In: Proceedings of the IEEE international conference on computer vision, Vancouver, BC, Canada, July 2001, pp 388-393
Chen L, Huang T, Ostermann J (1997) Animated talking head with personalized 3D head model. In: Proceedings of the 1st workshop on multimedia signal processing, Princeton, NJ, June 1997, pp 274-279
Chen S-C, Kashyap RL, Ghafoor A (2000) Semantic models for multimedia database searching and browsing. Kluwer, Dordrecht
Eckert G(2001) Shape refinement for reconstructing 3d objects using an analysis-systhesis approach. In: Proceedings of the IEEE international conference on image processing, Thessaloniki, Greece, October 2001, pp 903-906
Elagin E(1998) Automatic pose estimation system for human faces based on bunch graph matching technology. In: Proceedings of the 3rd IEEE international conference on automatic face and gesture recognition, Nara, Japan, April 1998, pp 136-141
Harville M(1999) 3D pose tracking with linear depth and brightness constraints. In: Proceedings of the IEEE international conference on computer vision, Kerkyra, Greece, September 1999, pp 206-213
Heinzmann J, Zelinsky A (1998) 3-D facial pose and gaze point estimation using a robust real-time tracking paradigm. In: Proceedings of the 3rd IEEE international conference on automatic face and gesture recognition, Nara, Japan, April 1998, pp 142-147
Hogg T, Talhami H(1997) Practical approach to view-based synergetic pose estimation. In: Proceedings of the IEEE TENCON conference, Brisbane, Australia, December 1997, 2:663-666
Horaud R(1997) Object pose: the link between weak perspective, paraperspective, and full perspective. Int J Comput Vision 22(2):173-189
Kutulakos KN, Seitz SM (2000) A theory of shape by space carving. Int J Comput Vision 38(3):199-218
Laurentini A (1994) The visual hull concept for silhouette-based image understanding. IEEE Trans Patt Recog Mach Intell 16(2):150-162
Levoy M, Hanrahan P (1996) Light field rendering. In: Proceedings of the 23rd annual conference on computer graphics and interactive techniques, New Orleans, LA, August 1996, pp 31-42
Lu C(2000) Fast and globally convergent pose estimation from video images. IEEE Trans Patt Recog Mach Intell 22(6):610-622
Mulligan J(2001) Trinocular stereo: a real-time algorithm and its evaluation. In: Proceedings of the IEEE workshop on stereo and multi-baseline vision, Kauai, HI, December 2001, pp 10-17
Pollefeys M(1999) Self-calibrartion and metric reconstruction inspite of varying and unknown camera parameters. Int J Comput Vision 32(1):7-25
Reed MK, Allen PK (1999) 3D modeling from range imagery: an incremental method with a planning component. Image Vision Comput 17:99-111
Szeliski R (1993) Rapid octree construction from image sequences. CVGIP Image Understand 58(1):23-32
Thomas JI, Oliensis J (1999) Dealing with noise in multi-frame structure from motion. Comput Vision Image Understand 76(2):109-123
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Avanaki, A.N., Hamidzadeh, B. & Kossentini, F. Multireference object pose retrieval with volume feedback. Multimedia Systems 9, 561–574 (2004). https://doi.org/10.1007/s00530-003-0128-x
Issue Date:
DOI: https://doi.org/10.1007/s00530-003-0128-x