EVD4UAV: An Altitude-Sensitive Benchmark to Evade Vehicle Detection in UAV

arXiv:2403.05422v1 Announce Type: new
Abstract: Vehicle detection in Unmanned Aerial Vehicle (UAV) captured images has wide applications in aerial photography and remote sensing. There are many public benchmark datasets proposed for the vehicle detection and tracking in UAV images. Recent studies show that adding an adversarial patch on objects can fool the well-trained deep neural networks based object detectors, posing security concerns to the downstream tasks. However, the current public UAV datasets might ignore the diverse altitudes, vehicle attributes, fine-grained …

abstract adversarial aerial applications arxiv benchmark cs.cv datasets detection images objects photography public sensing show studies tracking type unmanned aerial vehicle