VisDrone aerial object detection toolkit with 33 models (Torchvision + YOLO), training, evaluation, video inference, benchmarking, and annotation conversion.

Many yolov8 model are trained on the VisDrone dataset.

基于渐进式学习的轻量级无人机目标检测

object detection using YOLO11x on VisDrone dataset

Object detection format converter from VisDrone2019-DET to Yolo.

Lamaah: A YOLO-Based Model for Multi-Scale Object Detection in UAV Systems

Attention-guided object detection on VisDrone using Grad-CAM++ and YOLO, with metrics and visual outputs.