DroneDetect: A Benchmark UAV Dataset for Deep Learning-Based Drone Detection

This dataset, DroneDetect, has been developed to support research in the field of drone detection using deep learning and computer vision. It contains aerial and ground-based images of drones captured under diverse conditions, including varying backgrounds, altitudes, distances, and lighting environments. The dataset has been carefully annotated with bounding boxes in YOLO-compatible format to enable seamless use with state-of-the-art object detection algorithms.The dataset is designed for training, validation, and testing of drone detection models and can be applied across multiple deep learning frameworks, including YOLO, Faster R-CNN, SSD, and other neural network architectures. Potential applications include airspace monitoring, critical infrastructure protection, airport safety, defense, and real-time UAV tracking systems.By releasing this dataset on IEEE DataPort, we aim to provide the research community with a standardized benchmark that facilitates reproducibility, performance comparison, and the development of robust drone detection solutions.