PanoAir：基于跨时间真实世界无人机数据的全景视觉-惯性SLAM
PanoAir: A Panoramic Visual-Inertial SLAM with Cross-Time Real-World UAV Dataset
AI总结：
本文提出PanoAir全景视觉-惯性SLAM框架，通过全景特征提取与闭环优化提升无人机在复杂环境下的姿态估计精度与鲁棒性，实验验证其优于现有方法。
摘要：
准确的姿态估计对于无人机应用至关重要，视觉-惯性SLAM（VI-SLAM）提供了一种低成本的定位与建图解决方案。然而，现有VI-SLAM方法主要依赖传感器，其视野有限，可能导致漂移甚至在复杂无人机场景中失效。尽管全景相机提供全方位感知以提高鲁棒性，但全景VI-SLAM及对应的无人机真实世界数据集仍不完善。为此，我们首先构建了一个覆盖多样飞行条件的真实世界全景视觉-惯性数据集，包括变化的光照、高度、轨迹长度和运动动态。为实现在如此挑战性无人机场景中的准确稳健姿态估计，我们提出了一个利用所提出的全景特征提取和全景闭环优化的全景VI-SLAM框架，增强特征约束并确保全局一致性。在所提数据集和公开基准上的广泛实验表明，我们的方法在准确性、鲁棒性和一致性方面均优于现有方法。此外，部署在嵌入式平台验证了其实际应用性，实现了与PC实现相当的计算效率。源代码和数据集已公开在https://drive.google.com/file/d/1lG1Upn6yi-N6tYpEHAt6dfR1uhzNtWbT/view
英文摘要：
Accurate pose estimation is fundamental for unmanned aerial vehicle (UAV) applications, where Visual-Inertial SLAM (VI-SLAM) provides a cost-effective solution for localization and mapping. However, existing VI-SLAM methods mainly rely on sensors with limited fields of view (FoV), which can lead to drift and even failure in complex UAV scenarios. Although panoramic cameras provide omnidirectional perception to improve robustness, panoramic VI-SLAM and corresponding real-world datasets for UAVs remain underexplored. To address this limitation, we first construct a real-world panoramic visual-inertial dataset covering diverse flight conditions, including varying illumination, altitudes, trajectory lengths, and motion dynamics. To achieve accurate and robust pose estimation under such challenging UAV scenarios, we propose a panoramic VI-SLAM framework that exploits the omnidirectional FoV via the proposed panoramic feature extraction and panoramic loop closure, enhancing feature constraints and ensuring global consistency. Extensive experiments on both the proposed dataset and public benchmarks demonstrate that our method achieves superior accuracy, robustness, and consistency compared to existing approaches. Moreover, deployment on embedded platform validates its practical applicability, achieving comparable computational efficiency to PC implementations. The source code and dataset are publicly available at https://drive.google.com/file/d/1lG1Upn6yi-N6tYpEHAt6dfR1uhzNtWbT/view
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
