Abstract
In this note, we consider the use of 3D models for visual tracking in controlled active vision. The models are used for a joint 2D segmentation/3D pose estimation procedure in which we automatically couple the two processes under one energy functional. Further, employing principal component analysis or locally linear embedding from statistical learning, one can train our tracker on a catalog of 3D shapes, giving a priori shape information. The segmentation itself is information based, which allows us to track in uncertain adversarial environments. Our methodology is demonstrated on realistic scenes, which illustrate its robustness on challenging scenarios.
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
References
Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput. 15, 1373–139615 (2003)
Chan, T., Sandberg, B., Vese, L.: Active contours without edges for vector-valued images. J. Visual Commun. Image Represent. 11(2), 130–141 (2000)
Cipolla, R., Blake, A.: Surface shape from the deformation of apparent contours. Int. J. Comp. Vis. 9(2), 83–112 (1992)
Dambreville, S., Sandhu, R., Yezzi, A., Tannenbaum, A.: Robust 3D pose estimation and efficient 2D region-based segmentation from a 3D shape prior. In: Proceedings of ECCV, pp. 169–182 (2008)
Dambreville, S., Sandhu, R., Yezzi, A., Tannenbaum, A.: A geometric approach to joint 2D region-based segmentation and 3D pose estimation using a 3D shape prior. SIAM Imaging Sci. 3, 110–132 (2010)
Donoho, D.L., Grimes, C.: "Hessian eigenmaps: new locally linear embedding techniques for high-dimensional data," Technical Report TR-2003-08. Stanford University, Department of Statistics (2003)
Flanders, H.: Differentiation under the integral sign. Am. Math. Monthly 80(6), 615–627 (1973)
Hein, M., Maier, M.: Manifold denoising. NIPS:561–568 (2006)
Leventon, M., Grimson, E., Faugeras, O.: Statistical shape influence in geodesic active contours. In: IEEE CVPR, pp. 1316–1324 (2000)
Ma, Y., Stefano, S., Kosecka, J., Sastry, S.: An invitation to 3-d vision: from images to geometric models. In: Springer Science and Business Media, p. 26 (2012)
Michailovich, O., Rathi, Y., Tannenbaum, A.: Image segmentation using active contours driven by the Bhattacharyya gradient flow. IEEE Trans. Image Process. 16, 2787–2801 (2007)
Osher, S., Fedkiw, R.: Level Set Methods and Dynamic Implicit Surfaces. Springer (2003)
Rathi, Y., Tannenbaum, A.: A generic framework for tracking using particle filter with dynamic shape prior. IEEE Trans. Image Process. 16, 1370–1382 (2007)
Rathi, Y., Vaswani, N., Tannenbaum, A.: A generic framework for tracking using particle filter with dynamic shape prior. IEEE Trans. Image Process. 16(5), 1370–1382 (2007)
Ridder, D., Duin, R.: Locally linear embedding for classification. Technical report. PH-2002-01, Pattern Recognition Group, Delft University of Technology (2002)
Roweis, S., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)
Sandhu, R., Dambreville, S., Tannenbaum, A.: Particle filtering for registration of 2D and 3D point sets with stochastic dynamics. In: IEEE CVPR (2008)
Sandhu, R., Dambreville, S., Yezzi, A., Tannenbaum, A.: Non-rigid 2D-3D pose estimation and 2D image segmentation. In: IEEE CVPR (2009)
Sethian, J.A.: Level Set Methods and Fast Marching Methods, 2nd edn. Cambridge University Press (1999)
Tenenbaum, J.B., de Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)
Yezzi, A., Soatto, S.: Deformotion: Deforming motion, shape average and the joint registration and approximation of structures in images. Int. J. Comput. Vis. 53, 153–167 (2003)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this chapter
Cite this chapter
Lerner, J., Sandhu, R., Chen, Y., Tannenbaum, A. (2018). Machine Learning for Joint Classification and Segmentation. In: Tempo, R., Yurkovich, S., Misra, P. (eds) Emerging Applications of Control and Systems Theory. Lecture Notes in Control and Information Sciences - Proceedings. Springer, Cham. https://doi.org/10.1007/978-3-319-67068-3_24
Download citation
DOI: https://doi.org/10.1007/978-3-319-67068-3_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67067-6
Online ISBN: 978-3-319-67068-3
eBook Packages: EngineeringEngineering (R0)