Abstract
The fundamental task of visual tracking is considered in this work as an incremental direct image registration problem. Direct methods refer to those that exploit the pixel intensities without resorting to image features. We propose new transformation models and optimization methods for directly and robustly registering images (including color ones) of rigid and deformable objects, all in a unified manner. We also show that widely adopted models are in fact particular cases of the proposed ones. Indeed, the proposed general models combine various classes of image warps and ensure robustness to generic lighting changes. Finally, the proposed optimization method together with the exploitation of all possible image information allow the algorithm to achieve high levels of accuracy. Extensive experiments are reported to demonstrate that visual tracking can indeed be highly accurate and robust despite deforming objects and severe illumination changes.
Similar content being viewed by others
References
Baker, S., & Matthews, I. (2001). Equivalence and efficiency of image alignment algorithms. In IEEE computer vision and pattern recognition (pp. 1090–1097).
Baker, S., & Matthews, I. (2004). Lucas-Kanade 20 years on: A unifying framework. International Journal of Computer Vision, 56(3), 221–255.
Bartoli, A. (2008). Groupwise geometric and photometric direct image registration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(12), 2098–2108.
Bartoli, A., & Zisserman, A. (2004). Direct estimation of non-rigid registration. In Proc. of the British machine vision conference (pp. 899–908).
Benhimane, S., & Malis, E. (2007). Homography-based 2D visual tracking and servoing. International Journal of Robotics Research, 26(7), 661–676. Special Issue on Vision and Robotics joint with the International Journal of Computer Vision.
Black, M. J., Fleet, D. J., & 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. In SIGGRAPH (pp. 192–198).
Brown, L. G. (1992). A survey of image registration techniques. ACM Computing Surveys, 24, 325–376.
Carr, J., Fright, W., & Beatson, R. (1997). Surface interpolation with Radial Basis Functions for medical imaging. IEEE Transactions on Medical Imaging, 16(1).
Comaniciu, D., Ramesh, V., & Meer, P. (2000). Real-time tracking of non-rigid objects using mean-shift. In IEEE computer vision and pattern recognition.
Cook, R., & Torrance, K. (1982). A reflectance model for computer graphics. ACM Transactions on Graphics, 1, 7–24.
Faugeras, O., Luong, Q.-T., & Papadopoulo, T. (2001). The geometry of multiple images. Cambridge: MIT.
Finlayson, G., Drew, M., & Funt, B. (1994). Color constancy: Generalized diagonal transforms suffice. Journal of the Optical Society of America A, 11(11), 3011–3020.
Gouiffès, M., Collewet, C., Fernandez-Maloigne, C., & Trémeau, A. (2006). Feature points tracking using photometric model and colorimetric invariants. In Proc. Eur. conf. on colour in graph., imag., and vis. (pp. 18–23).
Hager, G., & Belhumeur, P. (1998). Efficient region tracking with parametric models of geometry and illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(10), 1025–1039.
Hartley, R., & Zisserman, A. (2000). Multiple view geometry in computer vision. Cambridge: Cambridge Univ. Press.
Haussecker, H. W., & 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., & Pardalos, P. M. (Eds.) (1995). Handbook of global optimization. Dordrecht: Kluwer.
Huber, P. J. (1981). Robust statistics. New York: Wiley.
Irani, M., & Anandan, P. (1999). All about direct methods. In Proc. workshop on vision alg.: theory and practice.
Jin, H., Favaro, P., & Soatto, S. (2001). Real-time feature tracking and outlier rejection with changes in illumination. In Proc. of the IEEE international conference on computer vision (pp. 684–689).
Jin, H., Favaro, P., & Soatto, S. (2003). A semi-direct approach to structure from motion. The Visual Computer, 6, 377–394.
Jurie, F., & Dhome, M. (2002). Real time robust template matching. In Proc. of the British machine vision conference (pp. 123–131).
Klinker, G. J., Shafer, S. A., & Kanade, T. (1990). The measurement of highlights in color images. International Journal of Computer Vision, 2, 7–32.
La Cascia, M., Sclaroff, S., & 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., & Fang, M. (1999). Robust and efficient image alignment with spatially varying illumination models. In IEEE computer vision and pattern recognition.
Lucas, B., & Kanade, T. (1981). An iterative image registration technique with an application to stereo vision. In Proc. of the int. joint conf. on art. intell. (pp. 674–679).
Maintz, J. B., & Viergever, M. A. (1998). A survey of medical image registration. Medical Image Analysis, 2(1), 1–36.
Malis, E. (2004). Improving vision-based control using efficient second-order minimization techniques. In Proc. of the IEEE int. conf. on robotics and automation, USA.
Malis, E. (2007). An efficient unified approach to direct visual tracking of rigid and deformable surfaces. In Proc. of the IEEE/RSJ int. conf. on intell. robots and syst., USA.
Montesinos, P., Gouet, V., Deriche, R., & Pele, D. (1999). Matching color uncalibrated images using differential invariants. Image and Vision Computing, 18(9), 659–671.
Mégret, R., Authesserre, J.-B., & Berthoumieu, Y. (2008). The bi-directional framework for unifying parametric image alignment approaches. In Proc. of the European conference on computer vision.
Nastar, C., Moghaddam, B., & Pentland, A. (1996). Generalized image matching: Statistical learning of physically-based deformations. In Proc. Eur. conf. on comp. 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.
Shum, H. Y., & Szeliski, R. (2000). Construction of panoramic image mosaics with global and local alignment. International Journal of Computer Vision, 16(1), 63–84.
Silveira, G., & Malis, E. (2007a). Direct visual servoing with respect to rigid objects. In Proc. of the IEEE/RSJ int. conf. on intelligent robots and systems, USA.
Silveira, G., & Malis, E. (2007b). Real-time visual tracking under arbitrary illumination changes. In IEEE computer vision and pattern recognition, USA.
Silveira, G., Malis, E., & Rives, P. (2008). An efficient direct approach to visual SLAM. IEEE Transactions on Robotics, 24, 969–979.
Szeliski, R. (2005). Image alignment and stitching. In Paragios, N., Chen, Y., & Faugeras, O. (Eds.) Handbook of math. models in comp. vision (pp. 273–292). Berlin: Springer.
Tan, R., & Ikeuchi, K. (2005). Separating reflection components of textured surfaces using a single image. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(2), 178–193.
Varadarajan, V. (1974). Lie groups, Lie algebras, and their representations. New York: Prentice-Hall.
Warner, F. W. (1987). Foundations of differential manifolds and Lie groups. Berlin: Springer.
Author information
Authors and Affiliations
Corresponding author
Electronic Supplementary Material
Below is the link to the electronic supplementary material. (3577KB)
Below is the link to the electronic supplementary material. (24170KB)
Below is the link to the electronic supplementary material. (16757KB)
Below is the link to the electronic supplementary material. (20219KB)
Below is the link to the electronic supplementary material. (1139KB)
Below is the link to the electronic supplementary material. (6023KB)
Below is the link to the electronic supplementary material. (19308KB)
Below is the link to the electronic supplementary material. (3831KM)
Below is the link to the electronic supplementary material. (1357KB)
Rights and permissions
About this article
Cite this article
Silveira, G., Malis, E. Unified Direct Visual Tracking of Rigid and Deformable Surfaces Under Generic Illumination Changes in Grayscale and Color Images. Int J Comput Vis 89, 84–105 (2010). https://doi.org/10.1007/s11263-010-0324-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11263-010-0324-z