基于点追踪的声呐里程计，提升水下导航精度
ISOPoT: Imaging Sonar Odometry by Point Tracking
- 用多帧点轨迹作为主要匹配依据，增强鲁棒性
- 在真实水下环境与Aracati 2017数据集上均优于现有方法
- 适合水下机器人导航、声呐感知研究者使用
水下环境中的可靠导航仍是海洋机器人领域的关键挑战。在此类场景中，前视声呐是长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覆盖。然而，声呐图像固有噪声大、含伪影且缺乏丰富语义结构，导致传统计算机视觉的关键点检测与匹配方法表现不佳。本文提出ISOPoT，一种基于现代点追踪技术的成像声呐里程计方法。我们设计了一种以多帧点轨迹为主要对应关系表示的声呐里程计流程，并引入轻量级优化提升鲁棒性。我们在Aracati 2017数据集及实际水下环境采集的内部声呐数据集上进行了评估。结果表明，ISOPoT在仅使用声呐的场景和多传感器设置下，均持续优于以往最先进方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。