InCrowd-VI：用于评估室内行人密集空间中面向人类导航的 SLAM 的真实视觉-惯性数据集
InCrowd-VI: A Realistic Visual-Inertial Dataset for Evaluating SLAM in Indoor Pedestrian-Rich Spaces for Human Navigation
AI总结：
本文提出 InCrowd-VI 真实视觉-惯性数据集，涵盖室内行人密集场景，并通过评测 VO/SLAM 算法揭示其精度、漂移与实时性不足。
摘要：
同步定位与地图构建（SLAM）技术可用于为视障人士导航，但面向拥挤空间的鲁棒 SLAM 方案的开发受到真实数据集缺乏的限制。为解决这一问题，我们提出 InCrowd-VI，这是一个专为室内行人密集环境中的人类导航而设计的新型视觉-惯性数据集。该数据集使用 Meta Aria Project 眼镜录制，捕捉不受环境控制的真实场景。InCrowd-VI 包含 58 个序列，轨迹总长度为 5 公里，录制时长为 1.5 小时，数据包括 RGB、立体图像和 IMU 测量。数据集捕捉了行人遮挡、变化的人群密度、复杂布局和光照变化等重要挑战。数据集中提供了精度约为 2 厘米的真值轨迹，这些轨迹来自 Meta Aria project 机器感知 SLAM 服务。此外，每个序列还提供场景的半稠密 3D 点云。在 InCrowd-VI 上对最先进的视觉里程计（VO）和 SLAM 算法进行评估后发现，这些方法在真实场景中存在严重的性能局限。在挑战性条件下，各系统超出了 0.5 米的所需定位精度以及 1% 的漂移阈值，其中经典方法的漂移高达 5-10%。尽管基于深度学习的方法保持了较高的位姿估计覆盖率（>90%），但它们未能达到步行速度导航所需的实时处理速度。这些结果表明，需要一个新的数据集来推进复杂室内环境中视障导航的 SLAM 研究，并体现了该数据集的价值。数据集及相关工具公开发布于 https://incrowd-vi.cloudlab.zhaw.ch/。
英文摘要：
Simultaneous localization and mapping (SLAM) techniques can be used to navigate the visually impaired, but the development of robust SLAM solutions for crowded spaces is limited by the lack of realistic datasets. To address this, we introduce InCrowd-VI, a novel visual-inertial dataset specifically designed for human navigation in indoor pedestrian-rich environments. Recorded using Meta Aria Project glasses, it captures realistic scenarios without environmental control. InCrowd-VI features 58 sequences totaling a 5 km trajectory length and 1.5 hours of recording time, including RGB, stereo images, and IMU measurements. The dataset captures important challenges such as pedestrian occlusions, varying crowd densities, complex layouts, and lighting changes. Ground-truth trajectories, accurate to approximately 2 cm, are provided in the dataset, originating from the Meta Aria project machine perception SLAM service. In addition, a semi-dense 3D point cloud of scenes is provided for each sequence. The evaluation of state-of-the-art visual odometry (VO) and SLAM algorithms on InCrowd-VI revealed severe performance limitations in these realistic scenarios. Under challenging conditions, systems exceeded the required localization accuracy of 0.5 meters and the 1\% drift threshold, with classical methods showing drift up to 5-10\%. While deep learning-based approaches maintained high pose estimation coverage (>90\%), they failed to achieve real-time processing speeds necessary for walking pace navigation. These results demonstrate the need and value of a new dataset to advance SLAM research for visually impaired navigation in complex indoor environments. The dataset and associated tools are publicly available at https://incrowd-vi.cloudlab.zhaw.ch/.
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。
