arXiv 2401.036042024-01-07cs.CV

Amirkabir校园数据集：面向视障人群的视觉惯性里程计（VIO）现实世界挑战与场景

Amirkabir campus dataset: Real-world challenges and scenarios of Visual Inertial Odometry (VIO) for visually impaired people

Amirkabir University of Technology（阿米尔卡比尔理工大学）；Sharif University of Technology（谢里夫理工大学）

Ali Samadzadeh, Mohammad Hassan Mojab, Heydar Soudani, Seyed Hesamoddin Mireshghollah, Ahmad Nickabadi

备注：: 7 pages, 4 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出了Amirkabir校园数据集（AUT-VI），包含126个序列和17个地点的极端导航场景，以解决现有VIO数据集在动态环境中对视障人群导航的不足，并评估了多种VIO和VO方法。

摘要：

视觉惯性里程计（VIO）算法通过结合相机和惯性测量单元（IMU）传感器来估计精确的相机轨迹。VIO的应用范围广泛，包括增强现实和室内导航。VIO算法具有在室内和室外环境中辅助视障人群进行导航的潜力。然而，最先进的VIO算法在动态环境中面临重大挑战，特别是在拥挤的走廊中。现有的VIO数据集（例如ADVIO）通常未能有效利用这些挑战。在本文中，我们引入了Amirkabir校园数据集（AUT-VI）来解决上述问题并改进导航系统。AUT-VI是一个新颖且极具挑战性的数据集，包含在17个不同地点采集的126个多样化序列。该数据集包含动态物体、具有挑战性的回环检测/地图重用、不同的光照条件、反射和突然的相机运动，以覆盖所有极端导航场景。此外，为了支持持续的开发工作，我们向公众发布了用于数据采集的Android应用程序。这使得其他研究人员能够轻松捕获其定制化的VIO数据集变体。另外，我们在我们的数据集上评估了最先进的视觉惯性里程计（VIO）和视觉里程计（VO）方法，强调了这一具有挑战性的数据集的必要性。

英文摘要：

Visual Inertial Odometry (VIO) algorithms estimate the accurate camera trajectory by using camera and Inertial Measurement Unit (IMU) sensors. The applications of VIO span a diverse range, including augmented reality and indoor navigation. VIO algorithms hold the potential to facilitate navigation for visually impaired individuals in both indoor and outdoor settings. Nevertheless, state-of-the-art VIO algorithms encounter substantial challenges in dynamic environments, particularly in densely populated corridors. Existing VIO datasets, e.g., ADVIO, typically fail to effectively exploit these challenges. In this paper, we introduce the Amirkabir campus dataset (AUT-VI) to address the mentioned problem and improve the navigation systems. AUT-VI is a novel and super-challenging dataset with 126 diverse sequences in 17 different locations. This dataset contains dynamic objects, challenging loop-closure/map-reuse, different lighting conditions, reflections, and sudden camera movements to cover all extreme navigation scenarios. Moreover, in support of ongoing development efforts, we have released the Android application for data capture to the public. This allows fellow researchers to easily capture their customized VIO dataset variations. In addition, we evaluate state-of-the-art Visual Inertial Odometry (VIO) and Visual Odometry (VO) methods on our dataset, emphasizing the essential need for this challenging dataset.

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。