发表机构
Center for Solar Energy and Hydrogen Research (ZSW); University of Stuttgart（太阳能与氢能研究中心（ZSW）; 斯图加特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对蝙蝠夜间飞行产生的超稀疏LiDAR数据，提出轻量级3D U-Net进行体素占用检测，结合加权损失处理类别不平衡，成功恢复前景轨迹，为生物多样性保护应用奠定基础。
AI 中文摘要
监测飞行动物对于理解和保护生物多样性至关重要，但蝙蝠等夜行性物种在野外难以观察。使用LiDAR，蝙蝠在夜间的活动会产生超稀疏的三维时空数据，标准重建损失在此类数据上往往只预测背景而遗漏真实飞行路径。我们将此问题作为传感器中心LiDAR射线堆中的体素级占用检测来研究。提出了一种轻量级3D U-Net，它保持时间分辨率，使用跳跃连接保留空间细节，并结合加权二元交叉熵与Dice损失来处理强烈的类别不平衡。在开阔田野上对蝙蝠的真实LiDAR记录中（与声学监测交叉验证），基于重建的3D卷积自编码器基线无法恢复前景轨迹。相比之下，所提出的U-Net在诊断实验中恢复了稀疏的前景占用，并沿蝙蝠飞行轨迹生成连贯的占用模式，为验证规模实验、后续飞行轨迹聚类以及未来将蝙蝠活动信息整合到生物多样性感知的风力涡轮机削减策略中提供了实用基础。
英文摘要
Monitoring flying animals is important for understanding and protecting biodiversity, but nocturnal species such as bats are difficult to observe in the field. Using LiDAR, bat movements at night result in ultra-sparse 3D spatio-temporal data in which standard reconstruction losses tend to predict only background and miss real flight paths. We study this problem as voxel-wise occupancy detection in sensor-centric LiDAR raystacks. A lightweight 3D U-Net is proposed that preserves temporal resolution, uses skip connections for spatial detail, and combines weighted binary cross-entropy with Dice loss to handle the strong class imbalance. In real LiDAR recordings of bats over open fields, cross-checked with acoustic monitoring, a reconstruction-based 3D convolutional autoencoder baseline fails to recover foreground trajectories. In contrast, the proposed U-Net recovers sparse foreground occupancy in diagnostic experiments and produces coherent occupancy patterns along bat flight trajectories, providing a practical basis for validation-scale experiments, later clustering of flight tracks, and future integration of bat activity information into biodiversity-aware turbine curtailment strategies.
Comments6 pages, 4 figures. Accepted and presented at the AI4Nature@AVSS 2026 Workshop of the 22nd International Conference on Advanced Visual and Signal-Based Systems (AVSS 2026), Lecce, Italy
