Single-frame fringe projection three-dimensional surface type measurement method

Abstract

The invention provides a single-frame fringe projection three-dimensional surface type measurement method, wherein the method comprises the following steps: S1, constructing a deep convolutional neural network which has six paths, and defining the deep convolutional neural network as DL-net. According to the method, firstly, a deep learning method is utilized, high-quality phase information extraction of a single-frame fringe image at three camera visual angles is realized under the driving of a large amount of data, then, a calibration space epipolar relationship among multiple visual angles is utilized, and the similarity wrapping the phase information is used as measurement to realize robust phase unwrapping, and then the high precision absolute depth information of a measured object can be recovered; and the powerful feature extraction advantage of deep learning and the efficient phase unwrapping advantage of geometric constraint are combined, and high-quality phase extraction, robust phase unwrapping and high-precision absolute depth recovery are achieved on the premise of single-frame projection.

Description

technical field [0001] The invention relates to the technical field of optical measurement, in particular to a single-frame fringe projection three-dimensional surface shape measurement method. Background technique [0002] Fringe projection profilometry (FPP) has become one of the most widely used three-dimensional optical measurement techniques due to its high measurement accuracy and simple hardware facilities. In recent years, with the increasing demand for high-quality 3D information acquisition in fast scenes in applications such as rapid reverse engineering, pipeline quality control, and 3D stress analysis, high-speed 3D shape measurement technology based on FPP has become particularly important [J. Qian , S.Feng, T.Tao, Y.Hu, K.Liu, S.Wu, Q.Chen, and C.Zuo, "Highresolution real-time 360°3D model reconstruction of a handheld object with fringe projection profilometry," Opt . Lett. 44, 5751–5754 (2019).]. [0003] In order to realize the measurement of 3D information...

AI Technical Summary

Problems solved by technology

However, using multiple fringe images reduces the measurement efficiency of the stereo phase unwrapping method

Another commonly used phase extraction technique is the Fourier method with single-frame properties [L.Huang, Q.Kemao, B.Pan, and A.K.Asundi, "Comparison of fourier transform, windowed fourier transform, and wavelet transform methods for phase extraction from a single fringe pattern in fringe projection profilometry,"Opt.LasersEng.48, 141–148(2010).], but the imaging quality of this method is poor, so it is not suitable for the application of stereo phase expansion method

[0004] It can be seen from the above analysis that although the stereoscopic phase unwrapping method based on geometric constraints can maximize the efficiency of phase unwrapping, it still cannot achieve single-frame 3D imaging due to its high requirements for phase quality.

Images