Polarization orientation method for cloudy sky

Ran ZHANG; Hong CAI; Le GUAN; Zhen-hua WAN; Yong-tai CHEN; Yuan-yi FAN; Jin-kui CHU

doi:10.37188/OPE.20212907.1499

您当前的位置：

首页 >

文章列表页 >

Polarization orientation method for cloudy sky

Modern Applied Optics | 更新时间：2021-08-09

- Polarization orientation method for cloudy sky
- Optics and Precision Engineering Vol. 29, Issue 7, Pages: 1499-1510(2021)
- 作者机构：
  
  1.大连理工大学机械工程学院，辽宁大连116023
  2.大连大学机械工程学院，辽宁大连 116622
- 作者简介：
- 基金信息：
- DOI：10.37188/OPE.20212907.1499
  CLC：
扫描看全文
Ran ZHANG, Hong CAI, Le GUAN, et al. Polarization orientation method for cloudy sky. [J]. Optics and Precision Engineering 29(7):1499-1510(2021)
DOI：

Ran ZHANG, Hong CAI, Le GUAN, et al. Polarization orientation method for cloudy sky. [J]. Optics and Precision Engineering 29(7):1499-1510(2021) DOI： 10.37188/OPE.20212907.1499.

摘要

为了在多云天气下实现天空偏振定向，提出了一种利用改进的U-Net深度神经网络结合偏振度阈值进行云分割的方法，并基于瑞利散射理论获取太阳方向与体轴夹角实现天空偏振定向。采用包含3个残差结构的Respath模块将U-Net神经网络的编码区与解码区更好的融合，并在下采样时添加MultiBlock模块，使输入图像的特征更好地被学习。将神经网络预测的二值分割图与设置偏振度阈值为0.1的二值分割图进行或运算得到能够较好地分割云和蓝天的二值图。最后，将该二值图作为mask模板去除偏振方位角图中异常像素点，使保留的像素点符合瑞利散射理论，进而获取太阳方向与体轴的夹角。多云天气下的实验表明，该方法获取载体坐标系下太阳方位角的均方根误差为0.42°，能够满足实际导航需求。

Abstract

To determine the polarization orientation of the sky in cloudy weather， a method of cloud segmentation using an improved U-Net deep neural network combined with a polarization degree threshold was proposed. This method was based on Rayleigh scattering theory and obtains the angle between the direction of the sun and the body axis to determine the polarization orientation. The Respath module containing three residual structures was used to integrate the coding and decoding areas of the U-Net neural network and to add the MultiBlock module for downsampling， so that the features of the input image could be accurately learned. Next， two binary segmentation maps， one predicted by the neural network and another with a polarization degree threshold set to 0.1， were ORed to obtain a binary image that can more effectively separate clear and cloudy skies. Finally， this binary graph was used as a mask template to remove the abnormal pixels in the polarizing azimuth graph， so that the retained pixels conformed to Rayleigh scattering theory. The angle between the direction of the sun and the body axis could then be obtained. Results of experiments in actual cloudy weather indicate that the RMSE error of the solar azimuth in the carrier coordinate system obtained using this method is 0.42°， which can meet real-world navigational requirements.

关键词

偏振导航深度神经网络偏振度阈值瑞利散射理论多云

Keywords

polarization guidancedeep neural networkpolarization degree thresholdRayleigh scattering theorycloudy weather

references

HEGEDÜS R， ÅKESSON S， HORVÁTH G. Polarization patterns of thick clouds： overcast skies have distribution of the angle of polarization similar to that of clear skies［J］. Journal of the Optical Society of America A， 2007， 24（8）： 2347.

褚金奎，时超，王寅龙，等. 偏振光实时定位系统的设计［J］. 中国激光， 2018， 45（3）： 0310002.

CHU J K， SHI CH， WANG Y L， et al. Design of polarized light real-time positioning system［J］. Chinese Journal of Lasers， 2018， 45（3）： 0310002.（in Chinese）

WANG Y L， CHU J K， ZHANG R， et al. A novel autonomous real-time position method based on polarized light and geomagnetic field［J］. Scientific Reports， 2015， 5： 9725.

褚金奎，张慧霞，王寅龙，等. 多方向偏振光实时定位样机的设计与搭建［J］. 光学精密工程， 2017， 25（2）： 312-318.

CHU J K， ZHANG H X， WANG Y L， et al. Design and construction of autonomous real-time position prototype based on multi-polarized skylight［J］. Optics and Precision Engineering， 2017， 25（2）： 312-318.（in Chinese）

WANG Y L， CHU J K， ZHANG R， et al. Orthogonal vector algorithm to obtain the solar vector using the single-scattering Rayleigh model［J］. Applied Optics， 2018， 57（4）： 594-601.

万振华，赵开春，褚金奎. 基于偏振成像的方位测量误差建模与分析［J］. 光学精密工程， 2019， 27（8）： 1688-1696.

WAN ZH H ， ZHAO K CH ， CHU J KUI. Modeling and analysis of orientation measurement error based on polarization imaging［J］. Optics and Precision Engineering， 2019， 27（8）： 1688-1696.（in Chinese）

陈永台，张然，林威，等. 天空实时全偏振成像探测器设计与搭建［J］. 光学精密工程， 2018， 26（4）： 816-824.

CHEN Y T， ZHANG R， LIN W， et al. Design and construction of real-time all-polarization imaging detector for skylight［J］. Optics and Precision Engineering， 2018， 26（4）： 816-824.（in Chinese）

王玉杰，胡小平，练军想，等. 仿生偏振视觉定位定向机理与实验［J］. 光学精密工程， 2016， 24（9）： 2109-2116.

WANG Y J， HU X P， LIAN J X， et al. Mechanisms of bionic positioning and orientation based on polarization vision and corresponding experiments［J］. Optics and Precision Engineering， 2016， 24（9）： 2109-2116.（in Chinese）

LIANG H， BAI H， LIU N， et al. Polarized skylight compass based on a soft-margin support vector machine working in cloudy conditions［J］. Applied Optics， 2020， 59（5）： 1271-1279.

WANG Y J， HU X P， ZHANG L L， et al. Polarized light compass-aided visual-inertial navigation under foliage environment［J］. IEEE Sensors Journal， 2017， 17（17）： 5646-5653.

FAN C， HU X P， HE X F， et al. Multicamera polarized vision for the orientation with the skylight polarization patterns［J］. Optical Engineering， 2018， 57（4）：1-10.

LU H， ZHAO K C， WANG X C， et al. Real-time imaging orientation determination system to verify imaging polarization navigation algorithm［J］. Sensors （Basel， Switzerland）， 2016， 16（2）： 144-157.

ZHANG W J， CAO Y， ZHANG X Z， et al. Angle of sky light polarization derived from digital images of the sky under various conditions［J］. Applied Optics， 2017， 56（3）： 587-595.

TANG J， ZHANG N， LI D L， et al. Novel robust skylight compass method based on full-sky polarization imaging under harsh conditions［J］. Optics Express， 2016， 24（14）： 15834-15844.

WANG X， GAO J， ROBERTS N W. Bio-inspired orientation using the polarization pattern in the sky based on artificial neural networks［J］. Optics Express， 2019， 27（10）： 13681-13693.

LIU B B， FAN Z G， WANG X Q. Solar position acquisition method for polarized light navigation based on ∞ characteristic model of polarized skylight pattern［J］. IEEE Access， 2020， 8： 56720-56729.

ZHAO H J， XU W J， ZHANG Y， et al. Polarization patterns under different sky conditions and a navigation method based on the symmetry of the AOP map of skylight［J］. Optics Express， 2018， 26（22）： 28589-28603.

GUAN L， LIU S， CHU J K， et al. A novel algorithm for estimating the relative rotation angle of solar azimuth through single-pixel rings from polar coordinate transformation for imaging polarization navigation sensors［J］. Optik， 2019， 178： 868-878.

WAN Z H， ZHAO K C， CHU J K. Robust azimuth measurement method based on polarimetric imaging for bionic polarization navigation［J］. IEEE Transactions on Instrumentation and Measurement， 2020， 69（8）： 5684-5692.

WISCOMBE W J. Improved Mie scattering algorithms［J］. Applied Optics， 1980， 19（9）： 1505-1509.

AYCOCK T M， LOMPADO A， WHEELER B M. Using atmospheric polarization patterns for azimuth sensing［C］. SPIE Defense + Security. Proc SPIE 9085， Sensors and Systems for Space Applications VII， Baltimore， Maryland， USA. 2014， 9085： 90850B.

叶亮. 地基云图像的云状识别技术研究［D］. 武汉：华中科技大学， 2019.

YE L. Research on Cloud Type Recognition in Ground-based Cloud Images［D］. Wuhan： Huazhong University of Science and Technology， 2019. （in Chinese）

DEV S， NAUTIYAL A， LEE Y H， et al. CloudSegNet： a deep network for nychthemeron cloud image segmentation［J］. IEEE Geoscience and Remote Sensing Letters， 2019， 16（12）： 1814-1818.

IBTEHAZ N， RAHMAN M S. MultiResUNet： Rethinking the U-Net architecture for multimodal biomedical image segmentation［J］. Neural Networks， 2020， 121： 74-87.

RONNEBERGER O， FISCHER P， BROX T. U-net： convolutional networks for biomedical image segmentation［C］. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015， 2015： 1-8.

HUANG G， LIU Z， WEINBERGER K Q， et al. Densely connected convolutional networks［EB/OL］. 2016： arXiv： 1608.

06993［cs.CV］. https：//arxiv.org/abs/1608.06993https://arxiv.org/abs/1608.06993.

DEV S， LEE Y H， WINKLER S. Color-based segmentation of sky/cloud images from ground-based cameras［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2017， 10（1）： 231-242.

Views

100

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Image reconstruction based on deep compressive sensing combined with global and local features

Related Author

No data

Related Institution

School of Microelectronics and Communication Engineering， Chongqing University

Institute of Physical Science and Information Technology， Anhui University

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰