Dynamic 3-D measurement based on fringe-to-fringe transformation using deep learning

TL;DR

This paper introduces a deep learning-based phase retrieval method for fringe projection profilometry that reduces the number of fringes needed, enabling more accurate dynamic 3-D shape measurement with fewer images.

Contribution

It presents a novel deep convolutional neural network approach for phase retrieval from fewer fringes, improving dynamic 3-D measurement accuracy and efficiency.

Findings

The method successfully retrieves phase with a single fringe in restricted depth scenarios.

Numerical and experimental results validate the approach's effectiveness for dynamic 3-D measurement.

The technique reduces motion-induced errors compared to traditional methods.

Abstract

Fringe projection profilometry (FPP) has become increasingly important in dynamic 3-D shape measurement. In FPP, it is necessary to retrieve the phase of the measured object before shape profiling. However, traditional phase retrieval techniques often require a large number of fringes, which may generate motion-induced error for dynamic objects. In this paper, a novel phase retrieval technique based on deep learning is proposed, which uses an end-to-end deep convolution neural network to transform a single or two fringes into the phase retrieval required fringes. When the object's surface is located in a restricted depth, the presented network only requires a single fringe as the input, which otherwise requires two fringes in an unrestricted depth. The proposed phase retrieval technique is first theoretically analyzed, and then numerically and experimentally verified on its applicability for dynamic 3-D measurement.