MCL_drone_dataset

A drone monitoring system integrating deep-learning-based detection and tracking modules is proposed in this work. The challenge in using deep learning for drone detection lies in the limited amount of training drone images. We address this by developing a model-based drone augmentation technique that generates drone images with bounding box labels. For tracking small flying drones, we utilize the residual information between consecutive image frames. Our integrated detection and tracking… See the full description on the dataset page: https://huggingface.co/datasets/uscmcl/MCL_drone_dataset.