外观
论文arXiv 2609.354821 个月前
ForVis：面向森林冠层下 UAV 飞行 VIO 的实地数据集与基准
原文链接：ForVis: An In-Field Dataset and Benchmark for VIO Using Under-Canopy UAV Flights in Forests（arXiv 2609.35482 · 发布日期：2026-09-28）
ForVis: An In-Field Dataset and Benchmark for VIO Using Under-Canopy UAV Flights in Forests
ForVis面向森林UAV飞行中VI-SLAM评估，提供实地数据集与基准，并在七个开源系统上验证。
核心要点
- 森林实景中运动、光照变化、重复植被与振动会影响UAV的VI-SLAM估计。
- 数据集包含12次飞行，覆盖开阔草地、冠层上方和冠层下方条件。
- 数据同步记录RealSense D435i、OAK-D Pro Wide、惯性与飞控数据。
- 基准测试七个开源VI-SLAM系统，结果显示传感器选择对轨迹误差影响更大。
验证范围与局限：验证范围为森林环境中的实地UAV飞行，包含开阔草地、冠层上方和冠层下方条件。
英文摘要 (Abstract)
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.
作者：Arman Kiani, Masoud Ataei, Elvis Gyaase, Jeffrey Eiyike, Aaron R. Weiskittel, Prabuddha Chakraborty, Vikas Dhiman
来源
本页事实对应的公开页面，以原文为准。