深度圖像分割中的面元優(yōu)化描述

王國宇; 姬光榮; 李欣; 鄭冰; 張海燕

深度圖像分割中的面元優(yōu)化描述

計量
- 文章訪問數(shù): 2245
- HTML全文瀏覽量: 99
- PDF下載量: 726
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2001-01-15
- 修回日期: 2001-08-03
- 刊出日期: 2002-11-19

Optimal description of surface primitive for range image segmentation

摘要

摘要: 該文提出了一種新的參數(shù)化面元的優(yōu)化描述方法,基于二次型面表示模型,物體表面參數(shù)由深度圖像數(shù)據(jù)擬合得到,基于一種改進的糾偏曲面擬合方法,提出了一個正態(tài)分布概率模型來描述面元估計的統(tǒng)計性質,并顯式定義了面元描述的可靠性度量,以面元提取為目的,提出了一種新的基于參數(shù)估計的深度圖像分割方法,在建立區(qū)域一致性判別優(yōu)化準則的同時,使得區(qū)域增長總是收斂于所提取面元的最可靠描述,文中給出了實際深度圖像分割的實驗結果。
- 深度圖像分割; 面元; 優(yōu)化描述; 參數(shù)估計; 不確定性; 區(qū)域增長
Abstract: This paper proposes a new algorithm of optimal description of surface primitive. The 3-D surface parameters are estimated through fitting the range data to a quadric model. Based on an improved bias-corrected fitting algorithm, a probabilistic model with normal pdf to describe the statistical characteristics of the surface estimate is proposed. Consequently a metric defined as measure of reliability of the surface estimate is given. Towards reliable primitive extraction, a new method of estimation-based range image segmentation is thereby described. While the region homogeneity is defined on an optimal criterion, the region growing always converges to the state of the most reliable description of the extracted surface primitives. The experimental results with real range images are given.

HTML全文

參考文獻(1)

F. Arman, J. K. Aggarwal, Model-based object recognition in dense-range images-a review,ACM Computing Survey, 1993, 25 (1), 5-43.[2]R. Hoffman, A. K. Jain, Segmentation and classification of range images, IEEE Trans. on Pattern Analysis and Machine Intelligence, 1987, PAMI-9(5), 608-620.[3]A. Hoover, et al., An experimental comparison of range image segmentation algorithms, IEEE Trans. on Pattern Analysis and Machine Intelligence, 1996, PAMI-18(7), 673-689.[4]章毓晉,圖像分割,北京,科學出版社,2001,第七,第八章.[5]R.M. Bolle, B. C. Vemuri, On three-dimensional surface reconstruction methods, IEEE Trans.on Pattern Analysis and Machine Intelligence, 1991, PAMI-13(1), 1-13.[6]J. Subrahmonias, D. Cooper, D. Keren, Practical reliable Bayesian recognition of 2D and 3D objects using implicit polynomials and algebraic invariants, IEEE Trans. on Pattern Analysis and Machine Intelligence, 1996, PAMI-18(5), 505-519.[7]H. Zha.[J].T. Hoshide, T. Hasegawa, A Recursive fitting-and-splitting algorithm for 3-D object modeling using superquadrics, in Proc. ICPR98, Brisba, Austrilia.1998,:-[8]S. Kaveti, E. Khwang, H. Wang, Second-order implicit polynomials for segmentation of range images, Pattern Recognition, 1996, 29(6), 937-94.[9]S.M. LaValle, S. A. Hutchinson, A Bayesian segmentation methodology for parametric image models, IEEE Trans. on Pattern Analysis and Machine Intelligence, 1995, PAMI-17(2), 211-217.[10]B. Sabata, F. Arman, J. K. Aggarwal, Segmentation of 3D range images using pyramidal data structures, CVGIP: Image Understanding, 1993, 57(3), 373-387.[11]A.P. Davignon, Detecting orientation discontinuities in range images by use of directional derivatives, in Proc. IAPR 11th Int. Conf. Pattern Recognition, The Hague, Netherlands, 1992, 3,455-458.[12]M. Haindl.[J].P. Zid, Range image segmentation by curve grouping, in Proc. 7th Int. Workshop RAAD98, Smolenice Castle, Slovak Republic.1998,:-[13]Y. Zhang, Y. Sun, H. Sari-Sarraf, M. Abidi, Impact of intensity edge map on segmentation of noisy range images, Conference on Three-Dimensional Image Capture and Applications Ⅲ, San Jose, California, USA, Proc.[J]. SPIE.2000,3958:260-[14]S.G. Burgiss, R. T. Whitaker, M. A. Abidi, Range Image Segmentation Through Pattern Analysis of the Multiscale Wavelet Transform, Digital Signal Processing, Academic Press, 1998, 8, 267-276.[15]P. J. Besl, R. C. Jain, Segmentation through variable-order surface fitting, IEEE Trans. on Pattern Analysis and Machine Intelligence, 1988, PAMI-10(2), 167-192.[16]G. Taubin, Estimation of planar curves, surfaces, and nonplanar space curves defined by implicit equations with applications to edge and range image segmentation, IEEE Trans. on Pattern Analysis and Machine Intelligence, 1991, PAMI-13 (11), 1115-1138.[17]A.P. Ashbrook.[J].R. B. Fisher, C. Robertson, N. Werghi, Segmentation of range data into rigid subsets using planar surface patches, in Proc. ICCV98, Bombay, India.1998,:-[18]K. Koester, M. Spann, MIR: an approach to robust clustering-application to range image segmentation, IEEE Trans. on Pattern Analysis and Machine Intelligence, 2000, PAMI-22(5), 430-444.[19]D.P. Mital, E. K. Teon, A. W. T. Lim, A hybrid method towards segmentation of range images for 3-D object recognition, International Journal of Pattern Recognition and Artificial Intelligence,1994, 8(4), 969-995.[20]M.A. Wani, B. G. Batchelor, Edge-region-based segmentation of range images, IEEE Trans. on Pattern Analysis and Machine Intelligence, 1994, PAMI-16(3), 314-319.[21]J. Miller.[J].C. Steward, MUSE: robust surface fitting using unbiased scale estimates, in Proc.CVPR96, San Francisco, California, USA.1996,:-[22]P. Whaite, F. P. Ferrie, From uncertainty to visual exploration, IEEE Trans. on Pattern Analysis and Machine Intelligence, 1991, PAMI-13(10), 1038-1049.[23]Z. Zhang, Parameter estimation techniques: a tutorial with application to conic fitting, Image and Vision Computing, 1997, 15, 59-76.[24]K. Kanatani, Statistical bias of conic fitting and renormalization, IEEE Trans. on Pattern Analysis and Machine Intelligence, 1994, PAMI-16(3), 320-326.[25]G.Y. Wang, Recognition of man-made objects from range data: optimization of surface based (quadric) representation, Ph.D. thesis, University of Twente, the Netherlands, 2000.

施引文獻

資源附件(0)

訪問統(tǒng)計