End-to-end Cloud Segmentation in High-Resolution Multispectral Satellite Imagery Using Deep Learning
This work addresses the problem of automating cloud segmentation for governmental institutions that process large volumes of satellite images, but it is incremental as it applies an existing architecture to a new dataset.
The paper tackles cloud segmentation in high-resolution multispectral satellite imagery by introducing the CloudPeru2 dataset and an end-to-end CNN method based on Deeplab v3+, achieving results such as 96.62% accuracy and 96.46% precision on the test set.
Segmenting clouds in high-resolution satellite images is an arduous and challenging task due to the many types of geographies and clouds a satellite can capture. Therefore, it needs to be automated and optimized, specially for those who regularly process great amounts of satellite images, such as governmental institutions. In that sense, the contribution of this work is twofold: We present the CloudPeru2 dataset, consisting of 22,400 images of 512x512 pixels and their respective hand-drawn cloud masks, as well as the proposal of an end-to-end segmentation method for clouds using a Convolutional Neural Network (CNN) based on the Deeplab v3+ architecture. The results over the test set achieved an accuracy of 96.62%, precision of 96.46%, specificity of 98.53%, and sensitivity of 96.72% which is superior to the compared methods.