[Home ] [Archive]   [ فارسی ]  
:: Main :: About :: Current Issue :: Archive :: Search :: Submit :: Contact ::
Main Menu
Journal Information::
Articles archive::
For Authors::
For Reviewers::
Contact us::
Site Facilities::
Search in website

Advanced Search
Receive site information
Enter your Email in the following box to receive the site news and information.
:: Volume 8, Issue 4 (3-2021) ::
jgit 2021, 8(4): 45-68 Back to browse issues page
A multi-scale convolutional neural network for automatic cloud and cloud shadow detection from Gaofen-1 images
Mehdi Khoshboresh-Masouleh , Reza Shah-Hosseini *
School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran
Abstract:   (2272 Views)
The reconstruction of the information contaminated by cloud and cloud shadow is an important step in pre-processing of high-resolution satellite images. The cloud and cloud shadow automatic segmentation could be the first step in the process of reconstructing the information contaminated by cloud and cloud shadow. This stage is a remarkable challenge due to the relatively inefficient performance of the current methods in complex scenes in multispectral high-resolution satellite images. In recent years, using deep convolutional neural networks has largely improved the performance of cloud and cloud shadow segmentation. Increasing the generalization capability of cloud and cloud shadow segmentation is one of the problems of deep convolutional neural networks. In this paper, we focus on tackling the poor generalization performance of automatic cloud and cloud shadow segmentation in Gaofen-1 (GF-1) images. In this regard, we propose a deep learning multi-scale method, founded on multi-dimension filters, for accurate segmentation of cloud/cloud shadow in single date GF-1 images which is based on a new multi-scale deep residual-convolutional neural network called MultiCloud-Net. The cloud/cloud shadow masks are extracted based on a new loss function to generate the final cloud/cloud shadow masks. The MultiCloud-Net was implemented in the Google Colab and was validated using 12 globally distributed GF-1 images. The quantitative assessments of test images show that the average F1 score, the average Jaccard Similarity Index (JSI), and the Kappa coefficient for cloud (cloud shadow) segmentation are about 97 (95.5), 96 (94.5), and 0.98, respectively. The experimental results using the GF-1 images demonstrate a more reasonable accuracy and efficient computational cost achievement of the proposed method compared to the automatic cloud/cloud shadow segmentation performance of two advanced deep learning and statistical methods.
Keywords: Gaofen-1, cloud, cloud shadow, deep learning, multi-scale convolution.
Full-Text [PDF 2561 kb]   (751 Downloads)    
Type of Study: Research | Subject: RS
Received: 2020/01/1 | Accepted: 2021/01/26 | Published: 2021/04/20
Send email to the article author

XML   Persian Abstract   Print

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Khoshboresh-Masouleh M, Shah-Hosseini R. A multi-scale convolutional neural network for automatic cloud and cloud shadow detection from Gaofen-1 images. jgit 2021; 8 (4) :45-68
URL: http://jgit.kntu.ac.ir/article-1-736-en.html

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Volume 8, Issue 4 (3-2021) Back to browse issues page
نشریه علمی-پژوهشی مهندسی فناوری اطلاعات مکانی Engineering Journal of Geospatial Information Technology
Persian site map - English site map - Created in 0.04 seconds with 36 queries by YEKTAWEB 4657