Surface Feature Extraction Based on Curvelet Transform from Point Cloud Data

Abstract:

Aiming at multi directions analysis problem of surface feature extraction from point cloud data, Curvelet transform is introduced to multi directions analysis of point cloud data. Based on the preprocessing of location and expansion, second-generation discrete Curvelet transform is used to analyze point cloud data. Curvelet transform coefficients are processed to enhance the contour of point cloud data. Nonlinear function is used to process Curvelet transform coefficients of coarse layer. Compromise for soft and hard thresholds is used to process Curvelet transform coefficients of detail layer. Piecewise nonlinear function is used to process Curvelet transform coefficients of fine layer. The data point is reconstructed from the enhanced Curvelet transform coefficient with Curvelet inverse transformation. Initial surface feature is achieved with edge detection. The precise surface feature is achieved with morphological dilation and erosion to filter edge without real shape significance. Example of part point cloud data of brake shell shows the proposed surface feature extraction method can accurately extract surface feature from data point.

• Periodical: Applied Mechanics and Materials (Volumes 719-720)
• Pages: 1236-1243
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.719-720.1236
• Online since: January 2015
• Authors: Hong Juan Yang*, Ji Wen Chen, Yun Chu Zhang, Xiao Dong Xu
• Keywords: Curvelet Transform, Feature Extraction, Multi-Scale Geometric Analysis (MGA), Point Cloud Data

References

[1] Xiuzi Ye, Hongzheng Liu, et al. Reverse innovative design - an integrated product design methodology[J]. Computer- Aided Design, 2008, 40(7): 812–827.

DOI: 10.1016/j.cad.2007.07.006

[2] Basilio Ramos Barbero. The recovery of design intent in reverse engineering problems[J]. Computers & Industrial Engineering, 2009, 56(4) : 1265-1275.

DOI: 10.1016/j.cie.2008.07.023

[3] Yinling Ke, Shuqian Fan, Weidong Zhu, et al. Feature-based reverse modeling strategies[J]. Computer-Aided Design, 2006, 38(5): 485–506.

DOI: 10.1016/j.cad.2005.12.002

[4] Yu-Kun Lai, Qian-Yi Zhou, Shi-Min Hu, et al. Robust Feature Classification and Editing[C]. IEEE Transaction on Visualization and Computer Graphics, 2007, 13(1): 34-45.

DOI: 10.1109/tvcg.2007.19

[5] Pal Benko, Tamas Varady. Segmentation methods for smooth point regions of conventional engineering objects[J]. Computer-Aided Design, 2004, 36(6): 511–523.

DOI: 10.1016/s0010-4485(03)00159-3

[6] Miguel Vieira, Kenji Shimada. Surface mesh segmentation and smooth surface extraction through region growing[J]. Computer Aided Geometric Design, 2005, 22(8): 771–792.

DOI: 10.1016/j.cagd.2005.03.006

[7] HAO Yongtao, XIAO Wensheng, HU Yajun. Method of data processing for discrete cloud based on Wavelet Transform. Journal of Tongji University(Natural Science), 2009, 37(5): 674-679.

[8] YANG Hong-juan， ZHOU Yi-qi， CHEN Cheng-jun. Feature segmentation of sectonal curve based On multi-scale analysis in reverse engineering[J]. 2007, 13(2): 375-380.

[9] E. J. Candes, L. Demanet, D.L. Donoho. Fast Discrete Curvelet Transforms, Applied and Computational Mathematics. California Institute of Technology, 2005, 1-43.

[10] Jiao Licheng, Hou Biao, Wang Shuang, et al. Image Multiscale Geometric Analysis：Theory and Applications—Beyond wavelets[M]. Xi'an: Xidian University Press, (2008).

[11] Feng Xiangchu, Gan Xiaobing, Song Guoxiang. Numerical functional and wavelet theory[M]. Xi'an: Xidian University Press, 20083.

[12] Star&J L，Candes EJ，Donoho DL．The Curvelet transform for image denoising[J]. IEEETram Image Proc, 2002, 11(6): 670-684.

DOI: 10.1109/tip.2002.1014998

[13] Chang S G，Bin Yu，Vetterli M．Adaptive wavelet thresholding for image denoising and compression[J]．IEEE Trans Image ProeA＆ssing，2000, 9: 1532-1546.

DOI: 10.1109/83.862633