DisasterScope: A Comprehensive Dataset and RTMDet-based Methodology for Object Detection in Disaster-Related Remote Sensing Images

Real-time object detection in disasters facilitates efficient rescue operations and mitigates secondary disasters. Artificial intelligence techniques and remote sensing have recently been widely used in disaster management, especially for vision-related tasks. To counter the need for more annotated data in deep learning-based object detection, we introduce a disaster-specific dataset called DisasterScope containing high-resolution disaster-related imagery. The dataset encompasses a range of images depicting diverse disaster scenarios, enhancing the breadth of training data for improved model performance. Besides, we present an enhanced version of the Real-Time Models for Object Detection (RTMDet) and conduct training and validation on the mentioned dataset. Experimental results demonstrate that the proposed approach outperforms state-of-the-art methods.