2022
DOI: 10.3390/s22176469
|View full text |Cite
|
Sign up to set email alerts
|

Deep Learning-Based 3D Measurements with Near-Infrared Fringe Projection

Abstract: Fringe projection profilometry (FPP) is widely applied to 3D measurements, owing to its advantages of high accuracy, non-contact, and full-field scanning. Compared with most FPP systems that project visible patterns, invisible fringe patterns in the spectra of near-infrared demonstrate fewer impacts on human eyes or on scenes where bright illumination may be avoided. However, the invisible patterns, which are generated by a near-infrared laser, are usually captured with severe speckle noise, resulting in 3D re… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 8 publications
(5 citation statements)
references
References 33 publications
0
5
0
Order By: Relevance
“…In the last decade, with the application of deep learning in optical metrology [31], such as image denoising [32,33], fringe pattern enhancement [34], wrapped phase retrieval [35], phase unwrapping [36], and stereo matching [37], many researchers have applied deep learning to FPP in order to obtain accurate wrapped phases with fewer patterns and further achieve phase unwrapping. Qian et al [38] proposed a single-shot absolute 3D shape measurement with deeplearning-based color FPP.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…In the last decade, with the application of deep learning in optical metrology [31], such as image denoising [32,33], fringe pattern enhancement [34], wrapped phase retrieval [35], phase unwrapping [36], and stereo matching [37], many researchers have applied deep learning to FPP in order to obtain accurate wrapped phases with fewer patterns and further achieve phase unwrapping. Qian et al [38] proposed a single-shot absolute 3D shape measurement with deeplearning-based color FPP.…”
Section: Introductionmentioning
confidence: 99%
“…In this case, the SPPWM pattern is significantly affected by higher harmonics and speckle patterns. In the case where traditional algorithms cannot simultaneously eliminate the interference of high-order harmonics and speckle patterns, based on the potential of deep learning in eliminating high-order harmonics [45] and noise [32,46], we proposed a sinusoidal pattern reconstruction network (SPRNet) that can simultaneously eliminate high-order harmonics and speckle patterns in SPPWM patterns to obtain high-quality sinusoidal patterns. In addition, considering the distribution characteristics of speckle patterns in SPPWM pattern, we proposed a multi-temporal spatial correlation matching algorithm (MTSCMA), which achieves a more reliable coarse disparity map calculation.…”
Section: Introductionmentioning
confidence: 99%
“…The latter fringe-to-phase group aims to transform fringe pattern(s) into several potential intermediate outputs before determining the unwrapped phase and 3D shape by the conventional technique [47][48][49][50]. Here, unwrapped refers to the demodulation of the wrapped phase because conventional algorithms generally yield phase data wrapped in a small value range.…”
Section: Introductionmentioning
confidence: 99%
“…In other studies, the researchers [ 57 , 64 ] employed two subnetworks with cosine fringe pattern and multi-code/reference pattern to obtain the wrapped phase and fringe orders. The work reported in [ 65 , 66 ] followed a framework comprising two deep neural networks, aiming to enhance the quality of the fringe pattern and accurately determine the numerator and denominator through denoising patterns. Machineni et al [ 67 ] presented an end-to-end deep learning-based framework for 3D object profiling, and the method encompassed a two-stage process involving a synthesis network and a phase estimation network.…”
Section: Introductionmentioning
confidence: 99%