A Single Image 3D Reconstruction Method Based on a Novel Monocular Vision System

被引:12
作者
Wu, Fupei [1 ,2 ]
Zhu, Shukai [2 ]
Ye, Weilin [1 ]
机构
[1] Shantou Univ, Dept Mech Engn, Shantou 515063, Peoples R China
[2] Shantou Univ, Minist Educ, Key Lab Intelligent Mfg Technol, Shantou 515063, Peoples R China
基金
中国国家自然科学基金;
关键词
machine vision; 3D measurement; monocular vision system; automatic optical inspection; SPARSE REPRESENTATION; SHAPE; SUPERRESOLUTION; INSPECTION; SCENES;
D O I
10.3390/s20247045
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Three-dimensional (3D) reconstruction and measurement are popular techniques in precision manufacturing processes. In this manuscript, a single image 3D reconstruction method is proposed based on a novel monocular vision system, which includes a three-level charge coupled device (3-CCD) camera and a ring structured multi-color light emitting diode (LED) illumination. Firstly, a procedure for the calibration of the illumination's parameters, including LEDs' mounted angles, distribution density and incident angles, is proposed. Secondly, the incident light information, the color distribution information and gray level information are extracted from the acquired image, and the 3D reconstruction model is built based on the camera imaging model. Thirdly, the surface height information of the detected object within the field of view is computed based on the built model. The proposed method aims at solving the uncertainty and the slow convergence issues arising in 3D surface topography reconstruction using current shape-from-shading (SFS) methods. Three-dimensional reconstruction experimental tests are carried out on convex, concave, angular surfaces and on a mobile subscriber identification module (SIM) card slot, showing relative errors less than 3.6%, respectively. Advantages of the proposed method include a reduced time for 3D surface reconstruction compared to other methods, demonstrating good suitability of the proposed method in reconstructing surface 3D morphology.
引用
收藏
页码:1 / 16
页数:16
相关论文
共 42 条
[1]   Robotic Arm Based 3D Reconstruction Test Automation [J].
Banerjee, Debdeep ;
Yu, Kevin ;
Aggarwal, Garima .
IEEE ACCESS, 2018, 6 :7206-7213
[2]   Measurement and Torque Calculation of Magnetic Spur Gear Based on Quasi 3-D Analytical Method [J].
Bang, Tae-Kyoung ;
Shin, Kyung-Hun ;
Koo, Min-Mo ;
Han, Cheol ;
Cho, Han-Wook ;
Choi, Jang-Young .
IEEE TRANSACTIONS ON APPLIED SUPERCONDUCTIVITY, 2018, 28 (03)
[3]   Face recognition based on 3D features: Management of the measurement uncertainty for improving the classification [J].
Betta, Giovanni ;
Capriglione, Domenico ;
Gasparetto, Michele ;
Zappa, Emanuele ;
Liguori, Consolatina ;
Paolillo, Alfredo .
MEASUREMENT, 2015, 70 :169-178
[4]   A Compressive Sensing Approach for 3D Breast Cancer Microwave Imaging With Magnetic Nanoparticles as Contrast Agent [J].
Bevacqua, Martina T. ;
Scapaticci, Rosa .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2016, 35 (02) :665-673
[5]   Automatic Inference and Measurement of 3D Carpal Bone Kinematics From Single View Fluoroscopic Sequences [J].
Chen, Xin ;
Graham, Jim ;
Hutchinson, Charles ;
Muir, Lindsay .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2013, 32 (02) :317-328
[6]   Two-View 3D Reconstruction for Food Volume Estimation [J].
Dehais, Joachim ;
Anthimopoulos, Marios ;
Shevchik, Sergey ;
Mougiakakou, Stavroula .
IEEE TRANSACTIONS ON MULTIMEDIA, 2017, 19 (05) :1090-1099
[7]   Numerical methods for shape-from-shadling: A new survey with benchmarks [J].
Durou, Jean-Denis ;
Falcone, Maurizio ;
Sagona, Manuela .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2008, 109 (01) :22-43
[8]   Color Homography: Theory and Applications [J].
Finlayson, Graham ;
Gong, Han ;
Fisher, Robert B. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2019, 41 (01) :20-33
[9]   3D reconstruction of dynamic liquid film shape by optical grid deflection method [J].
Fourgeaud, L. ;
Ercolani, E. ;
Duplat, J. ;
Gully, P. ;
Nikolayev, V. S. .
EUROPEAN PHYSICAL JOURNAL E, 2018, 41 (01)
[10]   A novel dual-camera calibration method for 3D optical measurement [J].
Gai, Shaoyan ;
Da, Feipeng ;
Dai, Xianqiang .
OPTICS AND LASERS IN ENGINEERING, 2018, 104 :126-134