Ground-Based Cloud Detection Using Multiscale Attention Convolutional Neural Network
- 27 August 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 19 (1545598X) , 1-5
Abstract
Cloud detection plays a significant role in ground-based remote sensing observation, and it is quite challenging due to the variations in illumination and cloud form, and the vague boundaries between cloud and sky. In this letter, we propose a novel deep model named multiscale attention convolutional neural network (MACNN) for ground-based cloud detection, which possesses a symmetric encoder–decoder structure. For accurate cloud detection, we design the multiscale module in MACNN to obtain different receptive fields by using different hole rates for the filters, and meanwhile, we propose the attention module in MACNN to learn the attention coefficients in order to reflect different importance of pixels. Furthermore, we release the Tianjin Normal University (TJNU) cloud detection database (TCDD) to provide a comparative study for different methods, and to the best of our knowledge, it is the largest cloud detection database. We conduct a series of experiments on the TCDD, and the experimental results demonstrate that the proposed MACNN outperforms state-of-the-art methods in five quantitative evaluation criteria.Keywords
Funding Information
- National Natural Science Foundation of China (62171321)
- Natural Science Foundation of Tianjin (20JCZDJC00180)
- Natural Science Foundation of Tianjin (19JCZDJC31500)
- Open Projects Program of National Laboratory of Pattern Recognition (202000002)
- Tianjin Higher Education Creative Team Funds Program
This publication has 18 references indexed in Scilit:
- Ground-Based Cloud Detection Using Graph Model Built Upon SuperpixelsIEEE Geoscience and Remote Sensing Letters, 2017
- Color-Based Segmentation of Sky/Cloud Images From Ground-Based CamerasIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016
- Learning Deconvolution Network for Semantic Segmentation2015
- Fully convolutional networks for semantic segmentation2015
- Ground-based Cloud Detection Using Automatic Graph Cut2015
- Visualizing and Understanding Convolutional Networks2014
- All-sky imaging: a simple, versatile system for atmospheric researchApplied Optics, 2009
- Climate change impacts on the hydrological cycleEcohydrology & Hydrobiology, 2008
- Retrieving Cloud Characteristics from Ground-Based Daytime Color All-Sky ImagesJournal of Atmospheric and Oceanic Technology, 2006
- A Simple Method for the Assessment of the Cloud Cover State in High-Latitude Regions by a Ground-Based Digital CameraJournal of Atmospheric and Oceanic Technology, 2006