基于Deeplab V3+的天绘一号卫星多光谱影像的云雪检测方法研究  

Research on a cloud and snow detection method of TH-01 satellite multispectral image based on Deeplab V3+

作　　者：杨戬峰 郝向阳[1] 叶宇 李朋月 郑凯 YANG Jianfeng;HAO Xiangyang;YE Yu;LI Pengyue;ZHENG Kai(School of Geospatial Information,Information Engineering University,Zhengzhou 450000,China;Unit 61618,Beijing 100094,China)

机构地区：[1]信息工程大学,河南郑州450000 [2]61618部队,北京100094

出　　处：《测绘科学与工程》2020年第4期40-45,72,共7页Geomatics Science and Engineering

摘　　要：云雪检测是天绘一号卫星数据处理的重要环节,为了对影像表观质量进行准确评价,需要分别检测影像中的云和雪。本文将基于深度学习的图像语义分割算法,引入到天绘一号卫星影像表观质量评价环节,设计了一种基于可见光波段的影像云雪检测方法,可实现在较少波谱信息下遥感影像云和雪分离,具有一定的实际应用意义。The detection of cloud and snow is an important step in TH01 satellite image processing.In order to evaluate the apparent quality of image accurately,it is necessary to detect the cloud and snow in the image separately.In this paper,the image semantic segmentation algorithm based on deep learning is introduced in the apparent quality evaluation of TH-01 satellite image,and a cloud and snow detection method based on visible spectrum image is designed to separate cloud and snow in remote sensing image with less spectral information.This method has certain practical application significance.

关 键 词：天绘一号 多光谱 深度学习 deeplab 云雪检测 

分 类 号：P237[天文地球—摄影测量与遥感]