High-Speed 3D Imaging and Sensing: From Classical Fringe Projection to Deep Learning Approaches

With the rapid development of optoelectronic information technology, three-dimensional (3D) imaging and sensing have become a research forefront in optical metrology. Fringe projection profilometry (FPP) is one of the most representative 3D imaging technologies due to its non-contact, high-resolution, high-speed, and full-field measurement capability. In recent years, with the rapid advances of optoelectronic devices and digital signal processing units, people subsequently set higher expectations on FPP: it should be both “high precision” and “high speed”. While these two aspects seem contradictory in nature, “speed” has gradually become a fundamental factor that must be taken into account when using FPP, and high-precision 3D reconstruction using only one pattern has been the ultimate goal of structured light 3D imaging in perpetual pursuit. Nowadays, deep learning technology has fully permeated” almost all tasks of optical metrology.

In this talk, we introduce our recent efforts to apply deep-learning approaches to FPP. We show that the deep-learning-enabled fringe analysis approach can significantly boost the accuracy and improve the quality of the phase reconstruction compared to conventional single-fringe phase retrieval approaches. Deep learning can also be used to achieve single-frame, high-precision, unambiguous 3D shape reconstruction, which is expected to fill the speed “gap” between 3D imaging and 2D sensing and enables FPP techniques to go a step further in high-speed and high-accuracy 3D surface imaging of transient events.

Subject Matter Level: Intermediate - Assumes basic knowledge of the topic

What You Will Learn:
• Deep learning enhances Fringe Projection Profilometry (FPP) by significantly improving the accuracy and quality of phase reconstruction over traditional methods.
• The integration of deep learning enables high-precision 3D reconstruction from a single frame, addressing the longstanding trade-off between speed and accuracy.
• This advancement paves the way for real-time, high-speed 3D imaging of dynamic events, narrowing the gap between 3D and 2D sensing technologies.

Who Should Attend:
• Researchers and engineers in optical metrology, 3D imaging, and fringe projection technologies.
• Graduate students and academics interested in the intersection of deep learning and optical sensing.
• Industry professionals working in fields like environmental monitoring, remote sensing, or geospatial analysis who seek cutting-edge solutions for high-speed, high-precision 3D measurement.
 

About the Presenter: Chao Zuo from Nanjing University of Science and Technology

Dr. Chao Zuo is a Zijin Chair Professor at Nanjing University of Science and Technology (NJUST), Distinguished Professor of "Changjiang Scholars Program", Ministry of Education of China. He leads the Smart Computational Imaging Laboratory (SCILab: www.scilaboratory.com) at the School of Electronic and Optical Engineering, NJUST, and is also the founder and director of the Smart Computational Imaging Research Institute of NJUST. He has long been engaged in the development of novel Computational Optical Imaging and Measurement technologies, with a focus on Phase Measuring Imaging Metrology. He has published > 300 peer-reviewed articles with over 20,000 citations. He currently serves as an Associate / Topical Editor of eLight, PhotoniX, Optics Letters, Optics and Lasers in Engineering, IEEE Transaction on Computational Imaging, Microwave and Optical Technology Letters, and Advanced Devices & Instrumentation. He is a Fellow of SPIE | Optica | IOP, and listed as a Clarivate Highly Cited Researcher.