基于二维经验模态分解的三维面形测量  

Three-dimensional shape measurement based on two-dimensional empirical mode decomposition

作　　者：郑素珍[1,2] 曹益平[1] 

机构地区：[1]四川大学光电科学技术系,四川成都610064 [2]西南石油大学理学院,四川成都610500

出　　处：《光电子．激光》2013年第10期1967-1971,共5页Journal of Optoelectronics·Laser

基　　金：国家'863'高技术研究发展计划(2007AA01Z333);国家重大专项(2009ZX02204-008);四川省学术和技术带头人培养基金(07GRC-01)资助项目

摘　　要：采用结构光投影的三维面形测量，为了得到包含待测物体高度信息的基频成分，变形条纹图中通常含有随机噪声和背景信息需要去除。提出一种基于二维经验模态分解（2D—EMD）的三维面形测量方法。2D—EMD用于去除低频背景分量并抑制噪声影响，再结合二维希尔伯特变换提取三维面形的相位信息，最后根据相位与高度的映射关系得到被测物体的三维形貌。2D—EMD采用完全的二维分析方法，考虑了条纹图行与行之间的相关性，能有效提取任意方向条纹图中的调制相位。由于不需要像聚合EMD（EEMD）反复添加噪声再分解的去噪过程，缩短了数据的处理时间。计算机仿真结果表明，与傅里叶变换轮廓术（FTP）相比，较大陡跳误差从-40mm降到了-1～1mm。实验结果也证明了本文方法的有效性。Deformed fringes often contain low frequency information degraded with random noise and background intensity information in structured light projection of three-dimensional surface shape meas- urement. In order to get fundamental frequency component of the tested object height information,the random noise and background interisity information need to be removed. A 3D shape measurement meth- od is proposed based on 2D empirical mode decomposition （2D-EMD）. Because 2D-EMD method has noise reduction in a way,at the same time, we remove the background components. The rest of funda- mental signals are performed by 2D Hilbert transform to effectively obtain the necessary phase informa- tion in 3D shape measurement. Then according to the mapping relationship of phase and height,we can get the three-dimensional shape of the tested object. Because 2D-EIVID method is a complete two dimen- sional analysis method, considering the fringe pattern of the relationship between the line and the line, the modulation phase of any direction fringe pattern can be effectively extracted. Without adding noise re- peatedly like ensemble empirical mode decomposition （EEMD, the data operating time is shortened. Computer simulations show that the larger steep jump error is dropped from -40 mm to -1-1 mm compared with the Fourier transform technique. Experiment proves the feasibility of this method.

关 键 词：测量 三维面形测量 二维经验模态分解(EMD) 抑噪 希尔伯特-黄变换(HHT) 

分 类 号：O438.2[机械工程—光学工程]