Abstract
In this chapter, we present how to learn regression models on Lie groups and apply our formulation to visual object tracking tasks. Many transformations used in computer vision, for example orthogonal group and rotations, have matrix Lie group structure. Unlike conventional methods that proceed by directly linearizing these transformations, thus, making an implicit Euclidean space assumption, we formulate a regression model on the corresponding Lie algebra that minimizes a first order approximation to the geodesic error. We demonstrate our method on affine motions , however, it generalizes to any matrix Lie group transformations.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
T. Albrecht, M. Luthi, T. Vetter, A statistical deformation prior for non-rigid image and shape registration, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008
S. Avidan. Ensemble tracking, in Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2005
S. Baker, I. Matthews, Equivalence and efficiency of image alignment algorithms. Proc. IEEE Conf. Comput. Vis. Pattern Recogn. Kauai, HI, 1, 1090–1097 (2001)
S. Baker, I. Matthews, Lucas-Kanade 20 years on: a unifying framework. Int. J. Comput. Vis. 56(3), 221–255 (2004)
E. Bayro-Corrochano, J. Ortegon-Aguilar. Lie algebra template tracking, in Proceedings of the 17th International Conference on Pattern Recognition, vol. 2, pp. 56–59, 2004
Y. Boykov, D. Huttenlocher, Adaptive Bayesian recognition in tracking rigid objects (In Proceedings of the IEEE Conf. on Computer Vision and Pattern Recognition, Hilton Head, SC, II, 2000), pp. 697–704
G. Chirikjian, Stochastic Models, Information Theory, and Lie Groups (Birkhauser, Boston, 2011)
T. Cootes, G. Edwards, C. Taylor, Active appearance models (In Proc. European Conf. on Computer Vision, Freiburg, Germany, 1998), pp. 484–498
T. Drummond, R. Cipolla, Application of Lie algebras to visual servoing. Int. J. Comp. Vis. 37, 21–41 (2000)
S. Hare, A. Saffari, P.H.S. Torr, Struck: Structured output tracking with kernels, in Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2011
T. Hastie, R. Tibshirani, J. Freidman. The Elements of Statistical Learning. (Springer, Berlin, 2001)
W. He, T. Yamashita, H. Lu, S. Lao, SURF tracking, in Proceedings of the International Conference on Computer Vision (ICCV), 2009
M. Isard, I. Blake, Condensation-conditional density propagation for visual tracking. Int. J. Comp. Vis. 29, 5–28 (1998)
F. Jurie, M. Dhome, Hyperplane approximation for template matching. IEEE Trans. Pattern Anal. Mach. Intell. 24, 996–1000 (2002)
J. Kwon, K. M. Lee, F. Park. Visual tracking via geometric particle filtering on the affine group with optimal importance functions, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009
D. Lowe, Distinctive image features from scale-invariant keypoints. Int. J. Comp. Vis. 60(2), 91–110 (2004)
R. Mahony, P.A. Absil, R. Sepulchre. Optimization algorithms on matrix manifolds. (Princeton University Press, Princeton, 2009)
I. Matthews, S. Baker, Active appearance models revisited. Int. J. Comp. Vis. 60, 135–164 (2004)
M. Ozuysal, P. Fua, V. Lepetit. Fast keypoint recognition in ten lines of code, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2007
F. Porikli, O. Tuzel, P. Meer. Covariance tracking using model update based on Lie algebra, in Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2006
W. Rossmann. Lie Groups: An Introduction Through Linear Groups. (Oxford Press, Oxford, 2002)
S.S. Sastry, J. Kosecka, Y. Ma, S. Sastry, An invitation to 3-d vision: from images to geometric models. (Springer, Berlin, 2003)
A.W.M. Smeulders, D.M. Chu, R. Cucchiara, S. Calderara, A. Dehghan, M. Shah. Visual tracking: an experimental survey. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1442–1468 (2014)
O. Tuzel, F. Porikli, P. Meer. Learning on Lie groups for invariant detection and tracking, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008
T. Vetter, T. Poggio, Linear object classes and image synthesis from a single example image. IEEE Trans. Pattern Anal. Machine Intell. 19, 733–742 (1997)
D. Wagner, T. Langlotz, D. Schmalstieg. Robust and unobtrusive marker tracking on mobile phones, in Proceedings of the ACM International Symposium on Mixed and Augmented Reality (ISMAR), 2008
N. Wang, S. Li, A. Gupta, and D. Yeung. Transferring rich feature hierarchies for robust visual tracking. CoRR, 2015
O. Williams, A. Blake, R. Cipolla, Sparse Bayesian learning for efficient visual tracking. IEEE Trans. Pattern Anal. Machine Intell. 27, 1292–1304 (2005)
Y. Wu, J. Lim, M.H. Yang. Online object tracking: a benchmark, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013
G. Zhu, F. Porikli, H. Li. Lie-Struck: affine tracking on Lie groups using structured SVM, in Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), 2015
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Porikli, F. (2016). Regression on Lie Groups and Its Application to Affine Motion Tracking. In: Minh, H., Murino, V. (eds) Algorithmic Advances in Riemannian Geometry and Applications. Advances in Computer Vision and Pattern Recognition. Springer, Cham. https://doi.org/10.1007/978-3-319-45026-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-45026-1_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-45025-4
Online ISBN: 978-3-319-45026-1
eBook Packages: Computer ScienceComputer Science (R0)