Abstract
In many image processing applications, identification of nonlinear structures in image data is of particular interest. Examples include fitting multiple ellipse patterns to image data, estimation and segmentation of multiple motions in subsequent images in video, and fitting nonlinear patterns to cell images for cancer detection in biomedical applications. This chapter introduces a novel approach to calculate a first order approximation for point distances from general nonlinear structures. We also propose an accelerated sampling method for robust segmentation of multiple structures. Our sampling method is substantially faster than random sampling used in the well-known RANSAC method as it effectively makes use of the spatial proximity of the points belonging to each structure. A fast high-breakdown robust estimator called Accelerated-LKS (A-LKS) is devised using the accelerated search to minimize the kth order statistics of squared distances. A number of experiments on homography estimation problems are presented. Those experiments include cases with up to eight different motions and we benchmark the performance of the proposed estimator in comparison with a number of state-of-the-art robust estimators. We also show the result of applying A-LKS to solve ellipse fitting and motion segmentation in practical applications.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
It is important to note that the dimension of data space is not always equal to the dimension of the parameter space denoted by p in this chapter. More precisely, p is the minimum number of data points that can specify a unique model candidate, which is not necessarily equal to the dimension of the data points. For instance in the fundamental estimation problem, each data point includes a pair of matching pixels and the dimension of each data point is 4, but the dimension of the parameter space is 8.
- 2.
It is important to note that ε is the ratio of gross outliers and in the presence of several structures, it is far less than \({\epsilon }^{{\prime}}\) in Eqs. (9.27) and (9.28) which equals the sum of gross and pseudo outlier ratios. In the presence of n obj structures with an equal number of inliers, \({\epsilon }^{{\prime}} =\epsilon +(1-\epsilon )(1 - 1/n_{\mathrm{obj}})\). For instance, if ε = 5% of data are gross outliers and there are n obj = 8 structures, we have \({\epsilon }^{{\prime}} = 88\%.\)
References
Yu X, Bui TD, Krzyzak A (1994) Robust estimation for range image segmentation and reconstruction. IEEE Trans PAMI 16(5):530–538
Lee KM, Meer P, Park RH (1998) Robust adaptive segmentation of range images. IEEE Trans PAMI 20(2):200–205
Bab-Hadiashar A, Suter D (1999) Robust segmentation of visual data using ranked unbiased scale estimator. Robotica 17:649–660
Bab-Hadiashar A, Suter D (2000) Range and motion segmentation. In: Bab-Hadiashar A, Suter D (eds) Data segmentation and model selection for computer vision. Springer, New York, pp 119–142
Bab-Hadiashar A, Gheissari N (2004) Model selection for range segmentation of curved objects. In: Springer-Verlag lecture notes on computer science (LNCS), vol 3021 (European conference on computer vision - ECCV 2004). Springer, Prague, pp 83–94
Bab-Hadiashar A, Gheissari N (2006) Range image segmentation using surface selection criterion. IEEE Trans Image Process 15(7):2006–2018
Ding Y, Ping X, Hu M, Wang D (2005) Range image segmentation based on randomized Hough transform. Pattern Recogn Lett 26(13):2033–2041
Min J, Bowyer KW (2005) Improved range image segmentation by analyzing surface fit patterns. Comput Vis Image Understand 97(2):242–458
Wang H, Suter D (2004) MDPE: a very robust estimator for model fitting and range image segmentation. Int J Comput Vis 59(2):139–166
Han F, Tu Z, Zhu SC (2004) Range image segmentation by an effective jump-diffusion method. IEEE Trans Pattern Anal Mach Intell 26(9):1138–1153
Hesami R, Bab-Hadiashar A, Hoseinnezhad R (2010) Range segmentation of large building exteriors: a hierarchical robust approach. Comput Vis Image Understand 114(4):475–490
Ben MWYR X (2012) Dual-ellipse fitting approach for robust gait periodicity detection. Neurocomputing 79:173–178
Volkau I, Puspitasari F, Ng TT, Bhanu Prakash KN, Gupta V, Nowinski WL (2012) A simple and fast method of 3D registration and statistical landmark localization for sparse multi-modal/time-series neuroimages based on cortex ellipse fitting. Neuroradiol J 25(1):98–111
Sun JG, Zhou YC (2012) Skin color detection method based on direct least square ellipse fitting in CrCbCg space. Advanced Materials Research. 2012;366:28–31.
Zhang C, Sun C, Pham TD, Vallotton P, Fenech M (2010) Detection of nuclear buds based on ellipse fitting. In: DICTA 2010, pp 178–183
Marhaban MH, Kaid RS, Mohd SB (2010) Automatic estimation of gestational age in ultrasound images based on direct least-squares fitting of ellipse. IEEJ Trans Electr Electron Eng 5(5):569–573
Torr PHS (1998) Geometric motion segmentation and model selection. Philos Trans R Soc A 1321–1340
Hajder L, Chetverikov D (2006) Weak-perspective structure from motion for strongly contaminated data. Pattern Recogn Lett 27(14):1581–1589
Vidal R, Ma Y, Soatto S, Sastry S (2006) Two-view multibody structure from motion. Int J Comput Vis 68(1):7–25
Qian G, Chellappa R, Zheng Q (2005) Bayesian algorithms for simultaneous structure from motion estimation of multiple independently moving objects. IEEE Trans Image Process 14(1):94–109
Schindler K, Suter D (2006) Two-view multibody structure-and-motion with outliers through model selection. IEEE Trans Pattern Anal Mach Intell 28(6):983–995
Basah SN, Bab-Hadiashar A, Hoseinnezhad R (2009) Conditions for motion-background segmentation using fundamental matrix. IET Comput Vis 3(4):189–200
Bartoli A, Sturm P (2004) Nonlinear estimation of the fundamental matrix with minimal parameters. IEEE Trans Pattern Anal Mach Intell 26(3):426–432
Tsui CC (2004) An overview of the applications and solutions of a fundamental matrix equation pair. J Franklin Inst 341(6):465–475
Chin TJ, Yu J, Suter D (2012) Accelerated hypothesis generation for multistructure data via preference analysis. IEEE Trans Pattern Anal Mach Intell 34(4):625–638
Hartley R, Zisserman A (2003) Multiple view geometry in computer vision. Cambridge University Press, New York
Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun Assoc Comput Mach 24(6):381–395
Hesami R, Bab-Hadiashar A, Hosseinnezhad R (2007) A novel hierarchical technique for range segmentation of large building exteriors. In: Bebis G (ed) Third international symposium on visual computing (ISVC07). LNCS, vol 4842/2007. Springer, Lake Tahoe, pp 75–85
Hoseinnezhad R, Bab-Hadiashar A (2007) A novel high breakdown M-estimator for visual data segmentation. In: ICCV. IEEE, Rio de Janeiro
Hoseinnezhad R, Bab-Hadiashar A (2011) An M-estimator for high breakdown robust estimation in computer vision. Computer vision and image understanding (CVIU) 115(8):1145–1156
Tordoff B, Murray DW (2002) Guided sampling and consensus for motion estimation. In: ECCV, Copenhagen, pp 82–69
Nister D (2005) Preemptive RANSAC for live structure and motion estimation. Mach Vis Appl 16(5):321–329
Subbarao R, Meer P (2006) Subspace estimation using Projection based M-estimators over Grassman manifolds. In: Horst Bischof ALAP (ed) 9th European conference on computer vision (ECCV’06). Springer, Graz, pp 301–312
Chum O, Matas J, Kittler J (2003) Locally optimized RANSAC. In: Michaelis B, Krell G (eds) 25th DAGM symposium. Lecture notes in computer science (LNCS), vol 2781. Springer, Magdeburg, pp 236–243
Chum O, Matas J (2008) Optimal randomized RANSAC. PAMI 30(8):1472–1482
Goshen L, Shimshoni H (2008) Balanced exploration and exploitation model search for efficient epipolar geometry estimation. PAMI 30(7):1230–1242
Comaniciu D, Meer P (2002) Mean shift: a robust approach toward feature space analysis. PAMI 24(5):603–619
Wang H, Suter D (2004) Robust adaptive-scale parametric model estimation for computer vision. IEEE Trans PAMI 26(11):1459–1474
Hoseinnezhad R, Bab-Hadiashar A (2007) Consistency of robust estimators in multi-structural visual data segmentation. Pattern Recogn 40:3677–3690
Hoseinnezhad R, Bab-Hadiashar A, Suter D (2010) Finite sample bias of robust estimators in segmentation of closely spaced structures: a comparative study. J Math Imaging Vis 37(1):66–84
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. IJCV 60(2):91–110
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this chapter
Cite this chapter
Hoseinnezhad, R., Bab-Hadiashar, A. (2014). Parametric Segmentation of Nonlinear Structures in Visual Data: An Accelerated Sampling Approach. In: Jazar, R., Dai, L. (eds) Nonlinear Approaches in Engineering Applications 2. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-6877-6_9
Download citation
DOI: https://doi.org/10.1007/978-1-4614-6877-6_9
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-6876-9
Online ISBN: 978-1-4614-6877-6
eBook Packages: EngineeringEngineering (R0)