AMRITAFLOODDATA

For the semantic segmentation to be effectively done, a labelled flood scene image dataset was created. This initiative was undertaken with official permission obtained from the BBC News Website and YouTube channel, providing a valuable dataset for our research. We were granted permission to use flood-related videos for research purposes, ensuring ethical and legal considerations. Specifically, videos were sourced from the BBC News YouTube channel. The obtained videos were then processed to extract image frames, resulting in a dataset comprising 10,854 images. This substantial dataset served as the foundation for training and evaluating our flood scene classification models. To augment the dataset and enhance model generalisation, various image data augmentation techniques were employed. Transformations such as rotation, flipping, and scaling were applied to diversify the dataset.