CloudX-net: A robust encoder-decoder architecture for cloud detection from satellite remote sensing images

Sumit Kanu, Rohit Khoja, Shyam Lal, B. S. Raghavendra, Asha CS

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)

Abstract

Cloud Detection is an important pre-processing step for any application involving remote sensing data. This paper presents a deep learning based CloudX-Net architecture, that can detect cloud cover with improved accuracy in comparison to the benchmark from satellite remote sensing images. The proposed CloudX-Net model reduces the number of parameters needed for accurate predictions and thus make deep learning based cloud detection method very efficient. Atrous Spatial Pyramid Pooling (ASPP) and Separable convolution are used to optimize the network. For experimentation, we have used Landsat 8 images and 38-Cloud dataset and trained the architectures using Soft Jaccard loss function. Comparing several quantifying metrics result from various recent deep learning architectures proves the efficiency and effectiveness of the proposed CloudX-Net model for cloud detection from satellite images. The source code and data are available at https://github.com/shyamfec/CloudXNet.

Original languageEnglish
Article number100417
JournalRemote Sensing Applications: Society and Environment
Volume20
DOIs
Publication statusPublished - 11-2020

All Science Journal Classification (ASJC) codes

  • Geography, Planning and Development
  • Computers in Earth Sciences

Fingerprint

Dive into the research topics of 'CloudX-net: A robust encoder-decoder architecture for cloud detection from satellite remote sensing images'. Together they form a unique fingerprint.

Cite this