arXiv 2606.230062026-06-23cs.RO

ISOPoT：基于点跟踪的成像声纳里程计

ISOPoT: Imaging Sonar Odometry by Point Tracking

Faculty of Computer and Information Science, University of Ljubljana（卢布尔雅那大学计算机与信息科学学院）；Faculty of Maritime Studies and Transport, University of Ljubljana（卢布尔雅那大学海事研究与运输学院）；OZON Research Group, TIMTEC（TIMTEC公司OZON研究组）；MAT Systemics, University of California, Santa Barbara（加州大学圣塔芭芭拉分校MAT系统学）

Jaša Samec, Vid Rijavec, Marko Peljhan, Aleksander Grm, Andrej Androjna, Danijel Skočaj, Matej Dobrevski

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出ISOPoT方法，利用现代点跟踪技术构建声纳里程计管道，通过多帧点轨迹作为主要对应表示，结合轻量级优化提升鲁棒性，在真实水下数据集上优于现有方法。

摘要：

水下环境中的可靠导航仍然是海洋机器人领域的一个关键挑战。在此类场景中，前视声纳是远距离感知的自然选择，即使在浑浊、低能见度条件下也能提供广泛覆盖。然而，声纳图像本身存在噪声、伪影，且缺乏丰富的语义结构，导致标准计算机视觉方法在关键点检测和匹配方面表现不佳。本文介绍了ISOPoT，一种基于现代点跟踪技术的成像声纳里程计方法。我们提出了一种声纳里程计管道，使用多帧点轨迹作为其主要对应表示，并通过轻量级优化来提高鲁棒性。我们在Aracati 2017数据集以及内部在真实水下环境中收集的声纳数据集上评估了所提方法。结果表明，ISOPoT在仅声纳场景和多传感器设置中均持续优于先前的最先进方法。

英文摘要：

Reliable navigation in underwater environments remains a key challenge in marine robotics. In such scenarios, forward-looking sonars are a natural choice for long-range perception, offering wide coverage even in turbid, low-visibility conditions. However, sonar images are inherently noisy, contain artifacts, and lack rich semantic structure, causing standard computer vision methods for keypoint detection and matching to perform poorly. In this paper, we introduce ISOPoT, an imaging sonar odometry method based on modern point tracking techniques. We propose a sonar odometry pipeline that uses multi-frame point tracks as its primary correspondence representation, augmented with lightweight optimizations to improve robustness. We evaluated the proposed method on the Aracati 2017 dataset, as well as on an internal sonar dataset collected in real-world underwater environments. Our results show that ISOPoT outperforms previous state-of-the-art methods consistently in both sonar-only scenarios and in multi-sensor settings.

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。