QQ客服 官方微博 反馈留言

	Hilbert Transformation Deep Learning Network for Single-Shot Moiré Profilometry
	Ma, Pu3; Du, Hubing3; Ma, Yueyang3; Zhang, Gaopeng2; Wang, Feng2; Zhao, Zixin1; Feng, Leijie3
英文摘要	Phase demodulation from a single moiré fringe pattern is an ill-posed inverse problem, which limits the applications of moiré profilometry in dynamic 3D measurement. In this paper, a deep learning-based high-precision technique is used to tackle this problem arose from highly under sampled inputs. Our novel approach, to the best of our knowledge, termed 2D Hilbert transformation network, uses two Res U-Net networks paired with a dichotomous network to generate the desiredπ2 phase-shifting fringe pattern referred to the input. This process can be viewed as 2D Hilbert transformation of a fringe pattern. With this network, the wrapped phase can be extracted easily if the sampled fringes pattern is filtered and normalized in advance. Trained using simulated data, experimental results show that the proposed Hilbert transformation network provides a simple but robust solution for phase extraction from a single fringe pattern with phase error less than 0.02rad and, therefore, make it allow for paving a new way to reliable and practical learning-based single-shot Moiré profilometry. © 2022, The Authors. All rights reserved.
	2022-04-21
产权排序	2
语种	英语
内容类型	预印本
源URL	[http://ir.opt.ac.cn/handle/181661/95859]
专题	西安光学精密机械研究所_动态光学成像研究室
作者单位	1.State Key Laboratory for Manufacturing Systems Engineering, Xi'an Jiaotong University, Shaanxi, Xi'An; 710049, China 2.Xi'an Institute of Optics and Precision Mechanics, CAS, Xi'An; 710119, China; 3.School of Mechatronic Engineering, Xi’an Technological University, Shaanxi, Xi'An; 710032, China;
推荐引用方式 GB/T 7714	Ma, Pu,Du, Hubing,Ma, Yueyang,et al. Hilbert Transformation Deep Learning Network for Single-Shot Moiré Profilometry. 2022.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。