Object reconstruction in multilayer neural network based profilometry using grating structure comprising two regions with different spatial periods

被引：17

作者：

Ganotra, D ^{[1
]}

Joseph, J ^{[1
]}

Singh, K ^{[1
]}

机构：

[1] Indian Stat Inst, Photon Grp, Dept Phys, New Delhi 110016, India

来源：

OPTICS AND LASERS IN ENGINEERING | 2004年 / 42卷 / 02期

关键词：

neural networks; profilometry; 3D object shape reconstruction;

D O I：

10.1016/j.optlaseng.2003.08.002

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

Feed-forward backpropagation neural network has been used in fringe projection profilometry for reconstruction of a three-dimensional (3D) object. A grating structure comprising two regions of different spatial periods is projected on the reference surface over which the object is placed. The shorter spatial period part of the grating is projected over the object. whereas the longer spatial period part is projected on the reference surface only. 3D object shape is reconstructed with the help of neural networks using images of the projected Grating. During training phase of the network, the shorter spatial period grating along with the longer spatial period grating is used. Experimental results are presented for a diffuse object, showing that the 3D shape of the object is recovered using the above-mentioned method. However, the phases wrapping takes place in Fourier transform profilometry by using only one grating of shorter spatial period. (C) 2003 Elsevier Ltd. All rights reserved.

引用

页码：179 / 192

页数：14

共 24 条

[1] MULTICHANNEL FOURIER FRINGE ANALYSIS AS AN AID TO AUTOMATIC PHASE UNWRAPPING [J].

BURTON, DR ;

LALOR, MJ .

APPLIED OPTICS, 1994, 33 (14) :2939-2948

[2] Overview of three-dimensional shape measurement using optical methods [J].

Chen, F ;

Brown, GM ;

Song, MM .

OPTICAL ENGINEERING, 2000, 39 (01) :10-22

[3] Depth object recovery using radial basis functions [J].

Cuevas, FJ ;

Servin, M ;

Rodriguez-Vera, R .

OPTICS COMMUNICATIONS, 1999, 163 (4-6) :270-277

[4] Multi-layer neural network applied to phase and depth recovery from fringe patterns [J].

Cuevas, FJ ;

Servin, M ;

Stavroudis, ON ;

Rodriguez-Vera, R .

OPTICS COMMUNICATIONS, 2000, 181 (4-6) :239-259

[5] Profilometry for the measurement of three-dimensional object shape using radial basis function, and multi-layer perceptron neural networks [J].

Ganotra, D ;

Joseph, J ;

Singh, K .

OPTICS COMMUNICATIONS, 2002, 209 (4-6) :291-301

[6] Enhanced three-dimensional reconstruction of surfaces using multicolor gratings [J].

Gilbert, BS ;

Blatt, JH .

OPTICAL ENGINEERING, 2000, 39 (01) :52-60

[7] Multifrequency grating projection profilometry based on the nonlinear excess fraction method [J].

Hao, YD ;

Zhao, Y ;

Li, DC .

APPLIED OPTICS, 1999, 38 (19) :4106-4110

[8]

Haykin S., 1994, Neural networks: a comprehensive foundation

[9] Error-reduction methods for shape measurement by temporal phase unwrapping [J].

Huntley, JM ;

Saldner, HO .

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1997, 14 (12) :3188-3196

[10] A PERSPECTIVE ON RANGE FINDING TECHNIQUES FOR COMPUTER VISION [J].

JARVIS, RA .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1983, 5 (02) :122-139

← 1 2 3 →