Convolutional Neural Networks for Multispectral Image Cloud Masking

Abstract

Convolutional neural networks (CNN) have proven to be state of the art methods for many image classification tasks and their use is rapidly increasing in remote sensing problems. One of their major strengths is that, when enough data is available, CNN perform an end-to-end learning without the need of custom feature extraction methods. In this work, we study the use of different CNN architectures for cloud masking of Proba-V multispectral images. We compare such methods with the more classical machine learning approach based on feature extraction plus supervised classification. Experimental results suggest that CNN are a promising alternative for solving cloud masking problems.

Preprint corresponding to the paper published in 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Fort Worth, TX, USA, pp. 2255-2258

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• XGBoost: A Scalable Tree Boosting System
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Unsupervised Deep Feature Extraction for Remote Sensing Image Classification
• Land Use Classification in Remote Sensing Images by Convolutional Neural Networks

Cited by in corpus (3)

• Deep learning based cloud detection for medium and high resolution remote sensing images of different sensors
• A lightweight deep learning based cloud detection method for Sentinel-2A imagery fusing multi-scale spectral and spatial features
• Multi-scale Cloud Detection in Remote Sensing Images using a Dual Convolutional Neural Network