发表机构
University of South Florida; University of Florida; Seoul National University（南佛罗里达大学; 佛罗里达大学; 首尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对水下机器人感知难题，构建了含同步3D多波束声呐点云与RGB图像的uScenes多模态数据集，为水下传感器融合等任务提供了基础。
AI 中文摘要
鲁棒感知对于自主水下机器人的部署至关重要。然而，光学相机在光照差和后向散射环境下会变得不可靠；前视（2D）声学传感器在这些条件下仍能保持有效，但它们测量距离和方位角，却无法解析仰角，这会产生歧义，导致单个声呐回波无法在三维（3D）空间中定位，使传感器难以用于3D场景理解和精确目标检测。本文介绍uScenes，这是一个包含同步3D多波束声呐点云和RGB图像的多模态水下数据集。该数据集包含110个场景和95834次同步观测，对应多次野外采集的277.6分钟数据。uScenes为水下传感器融合、跨模态表征学习和3D场景理解奠定了基础。代码和数据集可在该https URL获取。
英文摘要
Robust perception is essential for the deployment of autonomous underwater robots. However, optical cameras become unreliable under poor illumination and backscatter. Forward looking (2D) acoustic sensors remain effective under these conditions, but they measure range and bearing while leaving elevation unresolved, creating an ambiguity that prevents individual sonar returns from being localized in three dimensional (3D) space. This complicates the sensor use for 3D scene understanding and precise object detection. We introduce \textbf{uScenes}, a multimodal underwater dataset containing synchronized 3D multibeam sonar point clouds and RGB imagery. The dataset contains 110 scenes and 95,834 synchronized observation, representing 277.6 minutes of data collected across multiple field sessions. uScenes establishes a foundation for underwater sensor fusion, cross modal representation learning and 3D scene understanding. Code and datasets are given at https://github.com/era-research-lab/uScenes.
