| Summary: | 碩士 === 國立雲林科技大學 === 資訊工程系 === 105 === April to September is Taiwan's rainy season and typhoon season. Typhoons or heavy rains often cause flooding. Therefore, the purpose of this study is to develop a system for measuring the water level. Traditionally, water level was measured by supersonic water level sensor, pressure gauge and buoy. However, they are limited by the depth of water level and external impact. Therefore, this study presents an image based water level detection technology. Five image processing based water-level measurement methods and an assessment mechanism are used to determine the water level. The implemented system had been installed in 10 river monitor stations. The experimental results demonstrate good detection accuracy of four videos taken during four typhoons (Nepartak, Meranti, Megi and Neset) in 2016 and 2017. The detection accuracy of the proposed method achieves 93.94%.
|
|---|
