Scholarlink

Coastal erosion is a significant issue driven by various factors, including rising sea levels, human activities, and natural processes. This paper proposes a method to estimate the surface level using FastSAM, a convolutional neural network (CNN) designed for segmentation tasks. By using a point prompt, the model identifies the mask of the gauge and converts it to water surface level by counting the amount of the pixel height of the mask. The effectiveness of this method was evaluated using root mean square error (RMSE) and correlation coefficient. The proposed method was evaluated using data collected from a natural environment, Moonlight beach, Thailand. Compared to pressure sensor data, the proposed method achieve an RMSE of 0.7 cm and a correlation coefficient of 0.92. Additionally, when tested against manual observation of 3,000 images, the RMSE is 1.0 cm, with a correlation coefficient of 0.97. These indicate the promising potential of the proposed method in applying for coastal erosion monitoring systems.

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

Water Surface Level Estimation Based on the Fast Segment Anything Model for Coastal Monitoring Systems

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Julathit Chetsawang,
  • Kaweewat Sricharoenchit,
  • Krittapak Jairak,
  • Warit Yuvaniyama,
  • Peeravich Teerapatanapan,
  • Kittin Traisiwakul,
  • Tawin Supmahaudom,
  • Akkharawoot Takhom,
  • Phutphalla Kong,
  • Didin Agustian Permadi,
  • Sharifah Hafizah Syed Ariffin,
  • Kasorn Galajit,
  • Surasak Boonkla,
  • Jessada Karnjana

摘要

Coastal erosion is a significant issue driven by various factors, including rising sea levels, human activities, and natural processes. This paper proposes a method to estimate the surface level using FastSAM, a convolutional neural network (CNN) designed for segmentation tasks. By using a point prompt, the model identifies the mask of the gauge and converts it to water surface level by counting the amount of the pixel height of the mask. The effectiveness of this method was evaluated using root mean square error (RMSE) and correlation coefficient. The proposed method was evaluated using data collected from a natural environment, Moonlight beach, Thailand. Compared to pressure sensor data, the proposed method achieve an RMSE of 0.7 cm and a correlation coefficient of 0.92. Additionally, when tested against manual observation of 3,000 images, the RMSE is 1.0 cm, with a correlation coefficient of 0.97. These indicate the promising potential of the proposed method in applying for coastal erosion monitoring systems.