Abstract
In this paper we address the correspondence problem, with its application to nonrigid tracking and unsupervised modelling, as a nonparametric, active-linking topology learning problem. Unlike existing soft competitive learning methods, Active Growing Neural Gas (A-GNG) has both global and local properties which allows part of the network to reconfigure while tracking. In addition, A-GNG uses a number of features (e.g. topographic product, local grey-level and map transformation) so that the topological relations are preserved and nodes correspondences are retained between tracked configurations. Experimental results in a sequence of hand gestures and artificial data have shown the superiority of our proposed method over the original GNG.
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
Angelopoulou, A., García, J., Psarrou, A.: Learning 2d hand shapes using the topology preservation model gng. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 313–324. Springer, Heidelberg (2006)
Bauer, H.U., Pawelzik, K.R.: Quantifying the neighbourhood preservation of self-organizing feature maps. IEEE Transactions on Neural Networks 3(4), 570–579 (1992)
Baumberg, A., Hogg, D.: Learning flexible models from image sequences. In: Eklundh, J.-O. (ed.) ECCV 1994. LNCS, vol. 800, pp. 299–308. Springer, Heidelberg (1994)
Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models - their training and application. Comp. Vision Image Underst. 61(1), 38–59 (1995)
Davies, H.R., Twining, J.C., Cootes, F.T., Waterton, C.J., Taylor, J.C.: A minimum description length approach to statistical shape modeling. IEEE Transaction on Medical Imaging 21(5), 525–537 (2002)
Fritzke, B.: A growing neural gas network learns topologies. In: NIPS 1994. Advances in Neural Information Processing Systems 7, pp. 625–632 (1995)
Furao, S., Hasegawa, O.: An incremental network for on-line unsupervised classification and topology learning. The Journal of Neural Networks 19(1), 90–106 (2005)
Hill, A., Taylor, C., Brett, A.: A framework for automatic landmark identification using a new method of nonrigid correspondence. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(3), 241–251 (2000)
Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. In: Proc. of the 1st Internationl Conference on Computer Vision, pp. 259–268. IEEE Computer Society Press, Los Alamitos (1987)
MacCormick, J., Isard, M.: Partitioned sampling, articulated objects, and interface quality hand tracking. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 3–19. Springer, Heidelberg (2000)
Sudderth, E.B., Mandel, M.I., Freeman, W.T., Willsky, A.S.: Distributed occlusion reasoning for tracking with nonparametric belief propagation. Advances in Neural Information Processing Systems 17, 1369–1376 (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Angelopoulou, A., Psarrou, A., Gupta, G., García-Rodríguez, J. (2007). Nonparametric Modelling and Tracking with Active-GNG. In: Lew, M., Sebe, N., Huang, T.S., Bakker, E.M. (eds) Human–Computer Interaction. HCI 2007. Lecture Notes in Computer Science, vol 4796. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75773-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-540-75773-3_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75772-6
Online ISBN: 978-3-540-75773-3
eBook Packages: Computer ScienceComputer Science (R0)