AI 中文总结
本研究提出结合小波衍生纹理特征与深度学习的无人机裂流监测工作流程，通过不同策略融入离散小波变换特征，在分类和定位任务中提升性能，为海滩安全风险缓解提供可解释的无人机决策支持工具。
AI 中文摘要
裂流是反复出现的沿海自然灾害，威胁海滩游客，并给救生员和海岸管理人员带来运营挑战。利用无人机（UAV）获取的标准RGB（红-绿-蓝）图像进行可靠的监测仍然存在困难，因为危险的裂流通道常表现为破波中的细微间隙、泡沫纹理或沉积物图案，且这些特征会受到光照、海况和环境噪声的影响。本研究提出一种基于物理知识的沿海环境监测工作流程，用于检测视觉呈现的裂流指标，该流程将小波衍生的空间-频率纹理特征与深度学习相结合。我们评估了将离散小波变换（Discrete Wavelet Transform）特征融入卷积架构的多种策略，从计算高效的通道替换到带注意力机制的双流融合。我们使用任务特定的卷积神经网络进行图像级存在分类，使用YOLOv8模型进行目标级定位，以标准RGB基线评估性能。在评估的数据集条件下，整合小波衍生的纹理特征比仅使用RGB的模型性能更优。双流架构实现了最强的分类性能，准确率超过95%且召回率高；而通道替换对YOLOv8目标检测最有效，定位达到94%的mAP@50。可解释人工智能分析提供了定性证据，表明模型关注与裂流相关的视觉上合理的波隙区域。这些结果表明，在评估的数据集条件下，基于物理知识的小波整合可支持基于无人机的决策支持工具，用于可解释的海滩安全风险缓解。
英文摘要
Rip currents are recurrent coastal natural hazards that threaten beachgoers and create operational challenges for lifeguards and coastal managers. Reliable monitoring from standard RGB (red-green-blue) imagery acquired by unmanned aerial vehicles (UAVs) remains difficult because hazardous channels often appear as subtle gaps in breaking waves, foam texture, or sediment patterns, and these signatures are affected by illumination, sea state, and environmental noise. This study presents a physically informed coastal environmental monitoring workflow for detecting visually expressed rip-current indicators that integrates wavelet-derived spatial-frequency texture features with deep learning. We evaluate multiple strategies for incorporating Discrete Wavelet Transform features into convolutional architectures, from computationally efficient channel replacement to dual-stream fusion with attention mechanisms. Performance is assessed against a standard RGB baseline using a task specific convolutional neural network for image-level presence classification and a YOLOv8 model for object-level localization. Under the evaluated dataset conditions, integrating wavelet derived texture features improves performance over RGB-only models. The dual-stream architecture achieves the strongest classification performance, exceeding 95% accuracy with high recall, while channel replacement is most effective for YOLOv8 object detection, reaching 94% mAP@50 for localization. Explainable artificial intelligence analyses provide qualitative evidence that the models attend to visually plausible wave-gap regions associated with rip currents. These results suggest that under the conditions of the evaluated dataset, physically informed wavelet integration may support UAV-based decision-support tools for interpretable beach-safety risk mitigation.
Comments24 pages, 10 figures
