Scholarlink

<p>Observation of wave overtopping processes in coastal areas is challenging due to their dynamic unpredictability. To overcome the limitations of traditional observation methods, this study develops a novel automated binocular wave overtopping monitoring system based on Binocular Vision-Large Scale Particle Image Velocimetry (BV-LSPIV), integrated with a deep learning-based object detection algorithm. This algorithm enables pixel-level identification of wave run-up and overtopping extent. Furthermore, an improved approach is proposed to calculate overtopping discharge by combining the object detection algorithm, binocular vision technique, and the velocity-area principle. Field validation was conducted at Kanmen Bay, Zhejiang, China, during Typhoon Pulasan on September 19th, 2024. The developed coastal monitoring system successfully identifies 15 wave overtopping events induced by the typhoon, achieving spatial detection accuracies of 98.1% for wave run-up and 97.7% for wave overtopping. It also provides real-time analysis of surface velocity fields and near-real-time analysis of overtopping discharge. The results demonstrate that the developed system provides a robust and accurate solution for real-time wave overtopping monitoring and coastal hazard early warning.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Real-time coastal disaster monitoring system for typhoon-induced wave overtopping

  • 期刊论文

  • 发表日期：

    2026年2月19日

查看全文
  • Ying-Tien Lin,
  • Yiqun Ye,
  • Zheng Kong,
  • Ye Zhu,
  • Xiangbing Kong,
  • Zhiguo He

摘要

Observation of wave overtopping processes in coastal areas is challenging due to their dynamic unpredictability. To overcome the limitations of traditional observation methods, this study develops a novel automated binocular wave overtopping monitoring system based on Binocular Vision-Large Scale Particle Image Velocimetry (BV-LSPIV), integrated with a deep learning-based object detection algorithm. This algorithm enables pixel-level identification of wave run-up and overtopping extent. Furthermore, an improved approach is proposed to calculate overtopping discharge by combining the object detection algorithm, binocular vision technique, and the velocity-area principle. Field validation was conducted at Kanmen Bay, Zhejiang, China, during Typhoon Pulasan on September 19th, 2024. The developed coastal monitoring system successfully identifies 15 wave overtopping events induced by the typhoon, achieving spatial detection accuracies of 98.1% for wave run-up and 97.7% for wave overtopping. It also provides real-time analysis of surface velocity fields and near-real-time analysis of overtopping discharge. The results demonstrate that the developed system provides a robust and accurate solution for real-time wave overtopping monitoring and coastal hazard early warning.