The early and accurate detection of oods from satellite imagery can aid rescue planning and assessment of geophysical damage. Automatic identication of water from satellite images has historically relied on hand-crafted functions, but these often do not provide the accuracy and robustness needed for accurate and early ood detection. To try to overcome these limitations we investigate a tiered methodology combining water index like features with a deep convolutional neural network based solution to ood identication against the MediaEval 2019 ood dataset. Our method builds on existing deep neural network methods, and in particular the VGG16 network. Specically, we explored dierent water indexing techniques and proposed a water index function with the use of Green/SWIR and Blue/NIR bands with VGG16. Our experiment shows that our approach outperformed all other water index technique when combined with VGG16 network in order to detect ood in images.

No abstract

No abstract

No abstract

Self-Supervised learning (SSL) has become the new state-of-art in several domain classification and segmentation tasks. Of these, one popular category in SSL is distillation networks such as BYOL. This work proposes RSDnet, which applies the distillation network (BYOL) in the remote sensing (RS) domain where data is non-trivially different from natural RGB images. Since Multi-spectral (MS) and synthetic aperture radar (SAR) sensors provide varied spectral and spatial resolution information, we utilised them as an implicit augmentation to learn invariant feature embeddings. In order to learn RS based invariant features with SSL, we trained RSDnet in two ways, i.e., single channel feature learning and three channel feature learning. This work explores the usefulness of single channel feature learning from random MS and SAR bands compared to the common notion of using three or more bands. In our linear evaluation, these single channel features reached a 0.92 F1 score on the EuroSAT classification task and 59.6 mIoU on the DFC segmentation task for certain single bands. We also compared our results with ImageNet weights and showed that the RS based SSL model outperforms the supervised ImageNet based model. We further explored the usefulness of multi-modal data compared to single modality data, and it is shown that utilising MS and SAR data learn better invariant representations than utilising only MS data.