用无人机影像结合小波纹理特征，提升海浪间歇性裂流的自动识别准确率。
UAV-Based Environmental Monitoring of Rip-Current Indicators Using Wavelet-Derived Texture Features
- 将小波变换提取的纹理特征融入深度学习模型，增强对细微裂流痕迹的感知。
- 双流融合架构分类准确率达95%以上，通道替换法在目标检测中达到94% mAP@50。
- 模型关注区域与真实裂流位置吻合，适合用于海岸安全风险预警系统。
裂流是反复出现的沿海自然威胁，危及游客安全并给救生员和海岸管理者带来操作挑战。利用无人机获取的标准RGB影像进行可靠监测仍具难度，因为危险通道常表现为破碎浪花、泡沫纹理或沉积物模式中的微弱间隙，且受光照、海况和环境噪声影响。本研究提出一种融合小波导出的空间频率纹理特征与深度学习的物理启发式海岸环境监测流程，用于检测视觉表征的裂流指标。评估了多种将离散小波变换特征融入卷积架构的策略，包括计算高效的通道替换和带注意力机制的双流融合。性能通过任务专用卷积神经网络（图像级存在分类）和YOLOv8模型（物体级定位）对比标准RGB基线进行评估。在所用数据集条件下，整合小波纹理特征显著优于仅使用RGB的模型。双流架构取得最高分类性能，准确率超过95%，召回率高；通道替换法在YOLOv8目标检测中表现最优，定位mAP@50达94%。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浪隙区域。结果表明，在当前数据集条件下，物理信息引导的小波融合可支持可解释的无人机辅助决策工具，用于海滩安全风险缓解。
原文摘要 · Abstract (English)
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.
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。