A deep-learning based water-level measurement method from CCTV camera images

Abstract

As our previous work, we have reported a method to measure the river water level by capturing water gauge images of CCTV cameras for river monitoring into a computer and collating them with one taken at the time of low water level. For this time, we examined a method of measuring the river water level by identifying the water border position based on the deep learning technology, targeting the non-installation sites of the water gauge. We also have estimated the effectiveness of the new method using actual river image data set.