An intelligent water gauge recognition method

Abstract

The invention discloses an intelligent water gauge identification method, belonging to the technical field of water level monitoring, comprising the following steps: 1) collecting water gauge images,and dividing all water gauge images into a training set and a verification set; the water gauge image in the training set being screened and extracted to obtain the target area of the water gauge. 2)setting the width of the water gauge as a, adopting a rectangle with a length of 2a and a width of 2a to intercept the target area in a certain step length, and ensuring that the intercepted part doesnot exceed the left and right edges of the water gauge in the interception process; 3) taking the intercepted image above the water surface as a positive sample and the image below the water surfaceas a negative sample, and storing the intercepted image above the water surface into the data set of the corresponding water gauge scale value; 4) training the neural network model by using the data set correspond to all water gauge calibration values; 5) intercepting the target area of the water gauge image to be identify, judging the water level by using the trained neural network model after being processed in the step 2), and storing the image into the data set corresponding to the water gauge calibration values, so as to effectively identify pictures with unclear water level lines.

Description

technical field [0001] The invention relates to the technical field of water level monitoring, in particular to an intelligent water gauge identification method. Background technique [0002] Water level monitoring is an important monitoring index for water bodies such as rivers, rivers, and reservoirs, and is of great significance. In the prior art, conventional water level monitoring methods include sensor monitoring and water gauge manual monitoring. Among them, in the aspect of water gauge identification, in order to achieve the purpose of water saving, the method of video image monitoring is used to monitor the water level in the river and irrigation canal in real time. Although the method of manually reading the video can record data such as the water level of the water gauge, due to the huge number of monitoring points, the recorder cannot concentrate for a long time. Faced with so many monitoring images, often due to a negligence of the recorder, the input Occasion...

AI Technical Summary

Problems solved by technology

[0005] Although the above methods do not need to use a specific scale to realize the automation of water level monitoring, they only consider the turbidity and opacity of the water quality in the process of water level monitoring. When the water quality is clear, the color of the water and the water level line are not easy to identify. large error, so the scope of use is limited

Images