Abstract
Tracking 3D models in image sequences essentially requires determining their initial position and orientation. Our previous work [14] identifies the objective function as a crucial component for fitting 2D models to images. We state preferable properties of these functions and we propose to learn such a function from annotated example images.
This paper extends this approach by making it appropriate to also fit 3D models to images. The correctly fitted model represents the initial pose for model tracking. However, this extension induces nontrivial challenges such as out-of-plane rotations and self occlusion, which cause large variation to the model’s surface visible in the image.
We solve this issue by connecting the input features of the objective function directly to the model. Furthermore, sequentially executing objective functions specifically learned for different displacements from the correct positions yields highly accurate objective values.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Allezard, N., Dhome, M., Jurie, F.: Recognition of 3D textured objects by mixing view-based and model-based representations. ICPR, 960–963 (September 2000)
Besl, P.J., McKay, N.D.: A method for registration of 3-D shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence 14(2), 239–256 (1992)
Cootes, T.F., Taylor, C.J., Lanitis, A., Cooper, D.H., Graham, J.: Building and using flexible models incorporating grey-level information. In: ICCV, pp. 242–246 (1993)
Cristinacce, D., Cootes, T.F.: Facial feature detection and tracking with automatic template selection. In: 7th IEEE International Conference on Automatic Face and Gesture Recognition, April 2006, pp. 429–434. IEEE Computer Society Press, Los Alamitos (2006)
Hanek, R.: Fitting Parametric Curve Models to Images Using Local Self-adapting Seperation Criteria. PhD thesis, Technische Universität München (2004)
Lepetit, V., Lagger, P., Fua, P.: Randomized trees for real-time keypoint recognition. In: CVPR 2005, Switzerland, pp. 775–781 (2005)
Lepetit, V., Pilet, J., Fua, P.: Point matching as a classification problem for fast and robust object pose estimation. In: CVPR 2004, June 2004, vol. 2, pp. 244–250 (2004)
Lienhart, R., Maydt, J.: An extended set of haar-like features for rapid object detection. In: IEEE ICIP, pp. 900–903. IEEE Computer Society Press, Los Alamitos (2002)
Marchand, E., Bouthemy, P., Chaumette, F., Moreau, V.: Robust real-time visual tracking using a 2D-3D model-based approach. In: ICCV, pp. 262–268 (September 1999)
Quinlan, R.: Learning with continuous classes. In: Proceedings of the 5th Australian Joint Conference on Artificial Intelligence, pp. 343–348 (1992)
Romdhani, S.: Face Image Analysis using a Multiple Feature Fitting Strategy. PhD thesis, University of Basel, Computer Science Department, Basel, CH (January 2005)
Simon, D., Hebert, M., Kanade, T.: Real-time 3-D pose estimation using a high-speed range sensor. In: ICRA 1994. Proceedings of IEEE International Conference on Robotics and Automation, vol. 3, pp. 2235–2241 (May 1994)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. Computer Vision and Pattern Recognition (CVPR) (2001)
Wimmer, M., Pietzsch, S., Stulp, F., Radig, B.: Learning robust objective functions with application to face model fitting. In: Proceedings of the 29th DAGM Symposium, Heidelberg, Germany, September 2007 (to appear)
Witten, I.H., Frank, E.: Data Mining: Practical machine learning tools and techniques, 2nd edn. Morgan Kaufmann, San Francisco (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wimmer, M., Radig, B. (2007). Initial Pose Estimation for 3D Model Tracking Using Learned Objective Functions. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds) Computer Vision – ACCV 2007. ACCV 2007. Lecture Notes in Computer Science, vol 4844. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76390-1_33
Download citation
DOI: https://doi.org/10.1007/978-3-540-76390-1_33
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76389-5
Online ISBN: 978-3-540-76390-1
eBook Packages: Computer ScienceComputer Science (R0)