UAV-VisLoc
收藏资源简介:
UAV-VisLoc数据集是由北京邮电大学网络与交换技术国家重点实验室创建,旨在支持无人机视觉定位任务。该数据集包含来自中国11个不同地点的6742张无人机图像和11张卫星地图,涵盖了多种地形特征,如城市、乡村、河流和山丘。数据收集过程中,使用了固定翼和多地形无人机,捕捉了不同高度和方向的图像。此数据集特别适用于训练和测试模型,以解决无人机在全球导航卫星系统不可靠时的精确位置定位问题。
The UAV-VisLoc Dataset was created by the State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, to support unmanned aerial vehicle (UAV) visual localization tasks. This dataset includes 6,742 UAV images and 11 satellite maps collected from 11 distinct locations across China, covering various terrain features such as urban areas, rural regions, rivers and hills. During the data collection process, fixed-wing and multi-terrain UAVs were used to capture images at different altitudes and viewing directions. This dataset is particularly suitable for training and testing models to solve the problem of precise position localization for UAVs when the Global Navigation Satellite System (GNSS) is unreliable.




