An end-to-end fully-convolutional neural network for division of focal plane sensors to reconstruct S0, DoLP, and AoP
An end-to-end fully-convolutional neural network for division of focal plane sensors to reconstruct S0, DoLP, and AoP
复制标题
用于划分焦平面传感器以重建 S0、DoLP 和 AoP 的端到端全卷积神经网络
DOI：
10.1364/oe.27.008566
复制
发表时间：
2019-03-18
期刊：
影响因子：
3.8
通讯作者：
Ye, Wenbin
中科院分区：
文献类型：
--
作者：
Zeng, Xianglong;Luo, Yuan;Ye, Wenbin
焦平面分割偏振计广泛应用于偏振成像传感器中。集成在焦平面上的周期性排列的微偏振片保证了其出色的实时性，但降低了输出图像的空间分辨率，进而影响偏振参数的计算。在本文中，提出了一种称为Fork-Net的四层端到端全卷积神经网络，其目的是直接提高三种偏振特性的成像质量：强度（即，S-0）、线偏振度（DoLP）和偏振角（AoP），而不是专注于减少不同偏振取向的强度图像的插值误差。Fork-Net接受原始马赛克图像作为输入，并直接输出S-0，DoLP和AoP。它还使用定制的损失函数进行训练。实验结果表明，与现有方法相比，该方法获得了最高的峰值信噪比（PSNR）和突出的视觉质量的输出图像。(C)根据OSA开放获取出版协议的条款，2019年美国光学学会
Division of focal plane (DoFP) polarimeter is widely used in polarization imaging sensors. The periodically arranged micro-polarizers integrated on the focal plane ensure its outstanding real-time performance, hut reduce the spatial resolution of output images and further affect the calculation of polarization parameters. In this paper, a four layer, end-to-end fully convolutional neural network called Fork-Net is proposed, which aims to directly improve the imaging quality of three polarization properties: intensity (i.e., S-0), degree of linear polarization (DoLP), and angle of polarization (AoP), rather than focusing on reducing the interpolation error of intensity images of different polarization orientations. The Fork-Net accepts raw mosaic images as input and directly outputs S-0, DoLP, and AoP. It is also trained with a customized loss function. The experimental results show that compared with existing methods, the proposed one achieves the highest peak signal-to-noise ratio (PSNR) and prominent visual quality on output images. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement