DUT-Dve

DUT-Dve is a drone detection benchmark designed for evaluating detector robustness under adverse weather conditions. Extended from DUT Anti-UAV, the dataset incorporates synthetic weather degradations including rainy conditions, dense fog, and motion blur that simulate real-world visibility challenges. DUT-Dve comprises 8,000 images in total, with 5,200 for training, 1,600 for validation, and 1,200 for testing. The dataset addresses a critical gap in existing benchmarks by providing systematic evaluation scenarios for degraded visibility, enabling comprehensive assessment of detection algorithms under environmental disturbances commonly encountered in practical surveillance applications.