解调
卷积神经网络
计算机科学
模式识别(心理学)
人工智能
相(物质)
干涉测量
残余物
特征(语言学)
光学
计算机视觉
算法
频道(广播)
物理
电信
哲学
量子力学
语言学
作者
Rongli Guo,Shuaidong Lu,Miaomiao Zhang,Zhaoxin Li,Dangjuan Li,Fan Wang,Xiaoying Hu,Shenjiang Wu
出处
期刊:Applied Optics
[Optica Publishing Group]
日期:2023-11-28
卷期号:63 (7): B59-B59
被引量:8
摘要
Retrieving a phase map from a single closed fringe pattern is a challenging task in optical interferometry. In this paper, a convolutional neural network (CNN), HRUnet, is proposed to demodulate phase from a closed fringe pattern. The HRUnet, derived from the Unet model, adopts a high resolution network (HRnet) module to extract high resolution feature maps of the data and employs residual blocks to erase the gradient vanishing in the network. With the trained network, the unwrapped phase map can be directly obtained by feeding a scaled fringe pattern. The high accuracy of the phase map obtained from HRUnet is demonstrated by demodulation of both simulated data and actual fringe patterns. Compared results between HRUnet and two other CNNS are also provided, and the results proved that the performance of HRUnet in accuracy is superior to the two other counterparts.
科研通智能强力驱动
Strongly Powered by AbleSci AI