A Cloud Detection Method for Landsat 8 Satellite Remote Sensing Images Based on Improved CDNet Model

作     者：Junping Qiu Peng Cheng Chenxiao Cai 

作者机构：School of AutomationNanjing University of Science and TechnologyNanjing 210094P.R.China 

出 版 物：《Guidance, Navigation and Control》 (制导、导航与控制（英文）)

年 卷 期：2023年第3卷第3期

页      面：129-155页

学科分类：08[工学] 082503[工学-航空宇航制造工程] 0825[工学-航空宇航科学与技术] 

基　　金：supported by the National Natural Science Foundation of China (61973164 62373192) 

主　　题：Cloud detection feature fusing of two dimensions lightweight network cloud detection neural network(CDNet) Landsat 8 satellite imagery 

摘      要：Cloud detection in remote sensing images is a crucial task in various applications,such as meteorological disaster prediction and earth resource exploration,which require accurate cloud identi¯*** work proposes a cloud detection model based on the Cloud Detection neural Network(CDNet),incorporating a fusion mechanism of channel and spatial *** separable convolution is adopted to achieve a lightweight network model and enhance the e±ciency of network training and *** addition,the Convolutional Block Attention Module(CBAM)is integrated into the network to train the cloud detection model with attention features in channel and spatial *** were conducted on Landsat 8 imagery to validate the proposed improved *** over all testing images,the overall accuracy(OA),mean Pixel Accuracy(mPA),Kappa coe±cient and Mean Intersection over Union(MIoU)of improved CDNet were 96.38%,81.18%,96.05%,and 84.69%,*** results were better than the original CDNet and DeeplabV3+.Experiment results show that the improved CDNet is e®ective and robust for cloud detection in remote sensing images.