Abstract
Deformable models are useful tools to extract shape information from images and video sequences. However, the model has to be initialized in the vicinity of the object boundary, in order to foster convergence towards the desired features. This chapter describes four methods which alleviate this restriction. Despite their differences, they share three common features: (i) they use middle level features (edge segments) instead of low level ones; (ii) they explicitly assume that the measured features contain outliers and assign confidence degrees to the detected features and (iii) they adopt robust model updates, taking the confidence degrees into account. These four methods are reviewed and their performance is illustrated with selected examples.
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
Bar-Shalom Y (1987) Tracking and data association. Academic Press, Boston
Bar-Shalom Y, Daum F, Huang J (2009) The probabilistic data association filter. IEEE Control Syst 29:82–100
Blake A, Michael I (1998) Active contours. Springer, London
Cohen LD, Cohen I (1993) Finite element methods for active contour models and balloons for 2-D and 3-D images. IEEE Trans Pattern Anal Mach Intell 15:1131–1147
Cootes TF, Cooper D, Taylor CJ, Graham J (1995) Active shape models—their training and application. Comput Vis Image Underst 61(1)38–59
DeCarlo D, Metaxas D (1996) The integration of optical flow and deformable models: applications to human face shape and motion estimation. IEEE computer vision and pattern recognition, pp 231–238
Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24(1981)
Gilles C, Marques JS, Nascimento JC (2004) Learning switching dynamic models for objects tracking. Pattern Recognit 37(9):1835–1840
Hervé D (1999) General object reconstruction based on simplex meshes. Int J Comput Vision 32:111–146
Jain AK, Zhong Y, Marie-Pierre Dubuisson-Jolly (1998) Deformable template models: a review. Signal Process 71:109–129
Kass M, Witkin A, Terzopoulos D (1988) Snakes: active contour models. Int J Comput Vis 1(4):321–331
Lei H, Zhigang P, Bryan E, Xun W, Chia YH, Kenneth LW, William GW (2008) Comparative study of deformable contour methods on medical image segmentation. Image Vis Comput 26:141–163
Marques JS, Lemos JM (2001) Optimal and Suboptimal Shape Tracking Based on Multiple Switched Dynamic Models, Image and Vision Comput 19:539–550
Meer P, Mintz D, Rosenfeld A, Kim DY (1991) Robust regression methods for computer vision: a review. Int J Comput Vision 6:59–70
Moreno-Noguer F, Sanfeliu A, Samaras D (2007) Integration of deformable contours and a multiple hypotheses Fisher color model for robust tracking in varying illuminant environments. Image Vis Comput 25:285296
Nascimento JC, Marques JS (2002) Improving the robustness of parametric shape tracking with switched multiple models. Pattern Recognit 35:2711–2718
Nascimento JC, Marques JS (2004) Robust shape tracking in the presence of cluttered background. IEEE Trans Multimedia 6(6):852–861
Nascimento JC, Marques JS (2005) Adaptive snakes using the EM algorithm. IEEE Trans Image Process 14(11):1678–1686
Nilanjan R, Acton ST (2004) Flow motion gradient vector: an external force for tracking rolling leukocytes with shape and size constrained active contour. IEEE Trans Med Imaging 23:1466–1477
Silveira M, Nascimento JC, Marques JS, Marçal AR, Mendonça T, Yamauchi S, Maeda J, Rozeira J (2009) Comparison of segmentation methods for melanoma diagnosis in dermoscopy images. IEEE J Sel Top Sign Proces 3:35–45
Terzopoulos D, Szeliski R (1992) Tracking with kalman snakes. In: Blake A, Yuille AL (eds) Active vision. MIT Press, Cambridge, pp 3–20
Xu C, Pham DL, Prince JL (2000) Medical image segmentation using deformable models. In: Handbook of medical imaging, vol 2. SPIE Press, Bellingham, pp 129–174
Xu C, Prince J (1998) Snakes, shapes, and gradient vector flow. IEEE Trans Image Process 7:359–369
Acknowledgments
Part of the work on multi-model tracking was done in collaboration with Profs. Gilles Celeux (Paris-Sud University) and João M. Lemos (IST). The dermoscopic image was kindly provided by Dr. Jorge Rozeira of Hospital Pedro Hispano. This work was partially supported by FCT under projects PTDC/EEA-CRO/098550/2008, PTDC/SAU-BEB/103471/2008 and PTDC/EEA-CRO/103462/2008.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Marques, J.S., Nascimento, J.C., Santiago, C. (2013). Robust Deformable Models for 2D and 3D Shape Estimation. In: González Hidalgo, M., Mir Torres, A., Varona Gómez, J. (eds) Deformation Models. Lecture Notes in Computational Vision and Biomechanics, vol 7. Springer, Dordrecht. https://doi.org/10.1007/978-94-007-5446-1_7
Download citation
DOI: https://doi.org/10.1007/978-94-007-5446-1_7
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-007-5445-4
Online ISBN: 978-94-007-5446-1
eBook Packages: EngineeringEngineering (R0)