Nguyen Andrew-Hieu, Wang Zhaoyang
Neuroimaging Research Branch, National Institute on Drug Abuse, National Institutes of Health, Baltimore, MD 21224, USA.
Department of Mechanical Engineering, The Catholic University of America, Washington, DC 20064, USA.
Sensors (Basel). 2023 Aug 20;23(16):7284. doi: 10.3390/s23167284.
In recent years, integrating structured light with deep learning has gained considerable attention in three-dimensional (3D) shape reconstruction due to its high precision and suitability for dynamic applications. While previous techniques primarily focus on processing in the spatial domain, this paper proposes a novel time-distributed approach for temporal structured-light 3D shape reconstruction using deep learning. The proposed approach utilizes an autoencoder network and time-distributed wrapper to convert multiple temporal fringe patterns into their corresponding numerators and denominators of the arctangent functions. Fringe projection profilometry (FPP), a well-known temporal structured-light technique, is employed to prepare high-quality ground truth and depict the 3D reconstruction process. Our experimental findings show that the time-distributed 3D reconstruction technique achieves comparable outcomes with the dual-frequency dataset (p = 0.014) and higher accuracy than the triple-frequency dataset (p = 1.029 × 10-9), according to non-parametric statistical tests. Moreover, the proposed approach's straightforward implementation of a single training network for multiple converters makes it more practical for scientific research and industrial applications.
近年来，由于其高精度以及适用于动态应用，将结构化光与深度学习相结合在三维（3D）形状重建中受到了广泛关注。虽然先前的技术主要集中在空间域处理，但本文提出了一种新颖的时间分布方法，用于使用深度学习进行时间结构化光3D形状重建。所提出的方法利用自动编码器网络和时间分布包装器将多个时间条纹图案转换为反正切函数的相应分子和分母。条纹投影轮廓术（FPP）是一种著名的时间结构化光技术，用于准备高质量的地面真值并描述3D重建过程。我们的实验结果表明，根据非参数统计测试，时间分布3D重建技术与双频数据集取得了可比的结果（p = 0.014），并且比三频数据集具有更高的准确性（p = 1.029 × 10-9）。此外，所提出方法对多个转换器采用单个训练网络的简单实现方式使其在科研和工业应用中更具实用性。
