视觉无人机定位与场景建图数据

面向基于视觉的机器人环境建模与定位导航基础研究，为突破复杂环境下机器人视觉实时高精度定位技术瓶颈，基于精灵 PHANTOM 4 RTK多旋翼无人机进行数据采集，数据集覆盖场景是第31届世界大学生运动会主场馆（该建筑室内外存在严重遮挡，并且建筑立面的部件具有高度的相似性，该建筑的屋面覆盖高反光的、少弱纹理的大量玻璃）。该数据集包含112幅相片，数据量为905 M，主要用于视觉机器人的自主定位与环境建图。

This dataset is developed for fundamental research on vision-based robotic environmental modeling, localization and navigation. To break through the technical bottleneck of real-time high-precision visual localization for robots in complex environments, data was collected using a DJI PHANTOM 4 RTK multi-rotor unmanned aerial vehicle. The dataset covers the main venue of the 31st FISU World University Games, which has severe indoor and outdoor occlusions, highly similar facade components, and its roof is covered with a large amount of highly reflective, low-texture glass. The dataset contains 112 photos with a total data size of 905 MB, and is mainly used for autonomous localization and environmental mapping of vision-based robots.

搜集汇总

背景与挑战

背景概述

该数据集名为'视觉无人机定位与场景建图数据'，包含112幅相片，数据量为905MB，主要用于视觉机器人的自主定位与环境建图。数据集基于精灵PHANTOM 4 RTK多旋翼无人机采集，覆盖第31届世界大学生运动会主场馆的复杂场景，具有高反光、少弱纹理等特点。