AI 中文总结
针对现有3D声纳检测器无法处理潜水员自由姿态的问题，本文提出SonarVoxNet，采用6D旋转参数化预测9自由度边界框，并发布Diver3D数据集，证明从3D声纳可恢复全身姿态。
AI 中文摘要
协助人类潜水员的自主水下航行器（AUVs）必须持续跟踪潜水员的3D位置以及其全身姿态。然而，基于视觉的感知在水下不可靠，而前视声纳——尽管被广泛使用——却丢弃了姿态估计所需的仰角信息，这构成了一个根本性的限制。最近商业化的3D声纳保留了仰角信息，但产生稀疏、嘈杂的返回信号，且现有检测器是为密集LiDAR数据以及保持直立且仅绕偏航轴旋转的目标（如车辆、行人）设计的，因此无法表示自由俯仰和滚转的潜水员。为解决这一差距，我们提出两项贡献。首先，SonarVoxNet将基于体素的编码器和无锚点中心检测头适配到3D声纳数据，用连续的6D旋转参数化取代传统的仅偏航旋转表示，以预测完整的9自由度定向边界框——据我们所知，这是首个实现此功能的3D声纳潜水员检测器。其次，Diver3D是首个具有潜水员多样化非直立姿态完整3D方向标签的公开3D声纳数据集，在天然洞穴潜水地点收集。通过对骨干网络和检测头的受控消融实验，我们表明准确基于3D声纳的潜水员检测的主导因素是从仅偏航旋转到完整SO(3)旋转的转变。这一转变显著提高了检测精度并降低了方向误差。这些结果表明，仅凭3D声纳即可恢复潜水员全身姿态，为未来潜水员姿态估计和潜水员-机器人交互的研究奠定了基础。
英文摘要
Autonomous underwater vehicles (AUVs) assisting human divers must continuously track not only the diver's 3D position but also their full-body orientation. However, vision-based perception is unreliable underwater, and forward-looking sonar -- despite being widely used -- discards the elevation information needed for orientation estimation, posing a fundamental limitation. Recently commercialized 3D sonar preserves elevation but produces sparse, noisy returns, and existing detectors are built for dense LiDAR data and for targets that remain upright and rotate only about the yaw axis (e.g., vehicles, pedestrians), making them unable to represent a freely pitching and rolling diver. To address this gap, we present two contributions. First, SonarVoxNet adapts a voxel-based encoder and an anchor-free center-based detection head to 3D sonar data, replacing the conventional yaw-only rotation representation with a continuous 6D rotation parameterization to predict full 9-DoF oriented bounding boxes -- to our knowledge, the first 3D sonar diver detector to do so. Second, Diver3D is the first public 3D sonar dataset with full 3D orientation labels for divers in diverse, non-upright poses, collected at a natural cave-diving site. Through controlled ablations over the backbone and detection head, we show that the dominant factor behind accurate 3D sonar-based diver detection is the transition from yaw-only rotation to full-SO(3) rotation. This transition substantially improves detection accuracy and reduces orientation error. These results demonstrate that full-body diver orientation is recoverable from 3D sonar alone, laying the groundwork for future work on diver pose estimation and diver-robot interaction.
