发表机构
University of Maine（缅因大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出ForVis数据集与基准，用于评估森林冠层下无人机VI-SLAM，包含12次飞行和563.8秒数据，基准测试显示传感器选择对轨迹误差影响大于算法差异。
AI 中文摘要
视觉惯性同步定位与建图（VI-SLAM）在真实森林环境中的无人机评估仍然困难，因为运动、光照变化、重复植被和振动都会影响估计。我们提出了ForVis，一个用于评估森林环境中无人机飞行期间VI-SLAM的实地数据集和基准。该数据集包含在每个环境中跨越开阔草地、冠层上方和冠层下方的十二次飞行。总计提供563.8秒的飞行时间，覆盖1096.8米的轨迹，同时使用Intel RealSense D435i和OAK-D Pro Wide记录，并包含惯性和飞行控制器数据。我们对七个开源VI-SLAM系统进行了504次运行的基准测试。结果表明，传感器选择对轨迹误差的影响大于算法之间的差异：所有七种方法在OAK-D Pro上的中位误差均低于在D435i上的。ForVis旨在支持在具有挑战性的森林飞行中评估VI-SLAM的速度、准确性和鲁棒性。
英文摘要
Visual-inertial Simultaneous Localization and Mapping (VI-SLAM) for UAVs remains difficult to evaluate in real forest environments, where motion, illumination changes, repetitive vegetation, and vibration can all affect estimation. We present ForVis, an in-field dataset and benchmark for evaluating VI-SLAM during UAV flight in forest environments. The dataset contains twelve flights across open meadow, above-canopy, and under-canopy conditions in each environment. In total, it provides 563.8s of flight over 1096.8m of trajectory, recorded simultaneously with an Intel RealSense D435i and an OAK-D Pro Wide together with inertial and flight-controller data. We benchmark seven open-source VI-SLAM systems over 504 runs. The results show that sensor choice has a larger effect on trajectory error than the spread between algorithms: all seven methods achieve lower median error on the OAK-D Pro than on the D435i. ForVis is intended to support evaluation of speed, accuracy and robustness for VI-SLAM in challenging forest flight.
