An Integrated Method for River Water Level Recognition from Surveillance Images Using Convolution Neural Networks

Abstract

Water conservancy personnel usually need to know the water level by water gauge images in real-time and with an expected accuracy. However, accurately recognizing the water level from water gauge images is still a complex problem. This article proposes a composite method applied in the Wuyuan City, Jiangxi Province, in China. This method can detect water gauge areas and number areas from complex and changeable scenes, accurately detect the water level line from various water gauges, and finally, obtain the accurate water level value. Firstly, FCOS is improved by fusing a contextual adjustment module to meet the requirements of edge computing and ensure considerable detection accuracy. Secondly, to deal with scenes with indistinct water level features, we also apply the contextual adjustment module for Deeplabv3+ to segment the water gauge area above the water surface. Then, the area can be used to obtain the position of the water level line. Finally, the results of the previous two steps are combined to calculate the water level value. Detailed experiments prove that this method solves the problem of water level recognition in complex hydrological scenes. Furthermore, the recognition error of the water level by this method is less than 1 cm, proving it is capable of being applied in real river scenes.

An Approach Based on Video Image Intelligent Recognition for Water Turbidity Monitoring in River

“…In recent years, computer vision technology has made significant strides, impacting fields like autonomous driving and target monitoring. , It has also been increasingly applied to hydrological monitoring, including tasks such as identifying water bodies and assessing water quality using remote sensing images, measuring river flow velocity using spatiotemporal images, and detecting water levels through video images . Computer vision technology has demonstrated potential in automatic water turbidity monitoring as well.…”

“…10,11 It has also been increasingly applied to hydrological monitoring, including tasks such as identifying water bodies and assessing water quality using remote sensing images, 12 measuring river flow velocity using spatiotemporal images, 13 and detecting water levels through video images. 14 Computer vision technology has demonstrated potential in automatic water turbidity monitoring as well. Feizi et al, 15 for instance, conducted an image-based study on turbidity identification under laboratory conditions, achieving 97.5% accuracy in detecting water turbidity classes.…”

Evaluation of deep learning computer vision for water level measurements in rivers

“…In recent years, there has been a growing trend of utilizing deep learning networks for water level analysis. The concept of using deep learning neural networks for water level analysis is similar to the traditional method of measuring water levels by capturing images of water gauges [ [17] , [18] , [19] ] or water level lines [ [20] , [21] , [22] , [23] , [24] , [25] , [26] ]. However, there is a significant difference between the two approaches.…”

“…This reduces the threshold for establishing a program. Object recognition is used by the deep learning network to identify the position of the water gauge in the image and calculate the water level based on the length of the gauge exposed above the water body [ 17 , 18 ] or the displayed water gauge number [ 19 ]. This implies the need to install water gauges on-site.…”

Generated Image Editing Method Based on Global-Local Jacobi Disentanglement for Machine Learning

“…STGAN-WO [ 22 ] controls image generation at two scales separately in the latent space and achieves disentanglement of image structure from texture semantic attribute using weight orthogonal regularization, but its regularization method limits the weight space in the network; consequently, reduces the quality of the generated images. Chen et al [ 23 , 24 ]. achieves good results using spatial features of deep convolutional neural networks for image feature detection.…”