典型文献
Deep-learning-enabled dual-frequency composite fringe projection profilometry for single-shot absolute 3D shape measurement
文献摘要：
Single-shot high-speed 3D imaging is important for reconstructions of dynamic objects. For fringe projection profilometry (FPP), however, it is still challenging to recover accurate 3D shapes of isolated objects by a single fringe image. In this paper, we demonstrate that the deep neural networks can be trained to directly recover the absolute phase from a unique fringe image that involves spatially multiplexed fringe patterns of different frequencies. The extracted phase is free from spectrum-aliasing problem which is hard to avoid for traditional spatial-multiplexing methods. Experiments on both static and dynamic scenes show that the proposed approach is robust to object motion and can obtain high-quality 3D recon-structions of isolated objects within a single fringe image.
文献关键词：
中图分类号：
作者姓名：
Yixuan Li;Jiaming Qian;Shijie Feng;Qian Chen;Chao Zuo
作者机构：
Smart Computational Imaging(SCI)Laboratory,Nanjing University of Science and Technology,Nanjing 210094,China;Jiangsu Key Laboratory of Spectral Imaging&Intelligent Sense,Nanjing University of Science and Technology,Nanjing 210094,China
文献出处：
引用格式：
[1]Yixuan Li;Jiaming Qian;Shijie Feng;Qian Chen;Chao Zuo-.Deep-learning-enabled dual-frequency composite fringe projection profilometry for single-shot absolute 3D shape measurement)[J].光电进展（英文版）,2022(05):33-48
A类：
structions
B类：
Deep,learning,enabled,dual,frequency,composite,fringe,projection,profilometry,single,shot,absolute,measurement,Single,high,speed,imaging,important,reconstructions,dynamic,objects,For,FPP,however,still,challenging,recover,accurate,shapes,isolated,by,image,In,this,paper,demonstrate,that,deep,neural,networks,can,be,trained,directly,phase,from,unique,involves,spatially,multiplexed,patterns,different,frequencies,extracted,free,spectrum,aliasing,problem,which,hard,avoid,traditional,multiplexing,methods,Experiments,both,static,scenes,show,proposed,approach,robust,motion,obtain,quality,within
AB值：
0.608675
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
