UAVDT

It is an unconstrained UAV benchmark focusing on complex scenarios with new level challenges.Selected from 10 hours raw videos, about 80, 000 represen-tative frames are fully annotated with bounding boxes as well as up to 14 kinds of attributes (e.g., weather condition, fying altitude, camera view, vehicle category, and occlusion) for three fundamental computer vision tasks: object detection, single object tracking, and multiple object tracking.

该数据集为一款无约束无人机（UAV）基准数据集，聚焦于具备全新层级挑战的复杂场景。其从10小时的原始视频中遴选而来，共计约8万帧代表性帧已完成全面标注：不仅为目标标注了边界框，还涵盖多达14类属性信息（例如天气状况、飞行高度、相机视角、车辆类别与遮挡情况），可支撑三大基础计算机视觉任务：目标检测、单目标跟踪与多目标跟踪。

搜集汇总

背景与挑战

背景概述

UAVDT是一个专注于复杂场景下无人机视角的基准数据集，包含约80,000帧标注丰富的视频帧，适用于目标检测、单目标跟踪和多目标跟踪任务。数据集大小为14.78G，标注了多达14种属性以支持多样化的计算机视觉研究。