“…For example, the method of measuring the water level by ultrasonic bubble sensors may be affected by the environment because of the shape and size of the bubbles, so when the environment changes a lot, the sensor's readings will produce a certain amount of error. (4) The robustness of traditional image processing (i.e., nondeep learning) technology used for water level detection is relatively poor, and these methods cannot be adapted to complex harsh environments with rain, snow, haze, shadows and shade, etc. [2,3].…”
Section: Introductionmentioning
confidence: 99%
“…With deep learning technology exhibiting excellent performance [4][5][6], the automatic identification of water levels based on artificial intelligence has become a research hotspot. In the literature [7], the use of the Unet image segmentation technique to identify water level lines has been proposed.…”
Accurately perceiving changes in water level information is key to achieving the fine control of water and flooding; however, the existing technology cannot achieve water level recognition in complex and harsh environments, such as at night; in haze, rain, or snow; or during obscuration by floating objects or shadows. Therefore, on the basis of a deep analysis of the characteristics of water level images in complex and harsh environments, in this study, we took full advantage of a deep learning network’s ability to characterise semantic features and carried out exploratory research on water level detection in no-water-ruler scenarios based on the two technical means of target detection and semantic segmentation. The related experiments illustrate that all the methods proposed in this study can effectively adapt to complex and harsh environments. The results of this study are valuable for applications in solving the difficulties of accurate water level detection and flood disaster early warnings in poor-visibility scenarios.
“…For example, the method of measuring the water level by ultrasonic bubble sensors may be affected by the environment because of the shape and size of the bubbles, so when the environment changes a lot, the sensor's readings will produce a certain amount of error. (4) The robustness of traditional image processing (i.e., nondeep learning) technology used for water level detection is relatively poor, and these methods cannot be adapted to complex harsh environments with rain, snow, haze, shadows and shade, etc. [2,3].…”
Section: Introductionmentioning
confidence: 99%
“…With deep learning technology exhibiting excellent performance [4][5][6], the automatic identification of water levels based on artificial intelligence has become a research hotspot. In the literature [7], the use of the Unet image segmentation technique to identify water level lines has been proposed.…”
Accurately perceiving changes in water level information is key to achieving the fine control of water and flooding; however, the existing technology cannot achieve water level recognition in complex and harsh environments, such as at night; in haze, rain, or snow; or during obscuration by floating objects or shadows. Therefore, on the basis of a deep analysis of the characteristics of water level images in complex and harsh environments, in this study, we took full advantage of a deep learning network’s ability to characterise semantic features and carried out exploratory research on water level detection in no-water-ruler scenarios based on the two technical means of target detection and semantic segmentation. The related experiments illustrate that all the methods proposed in this study can effectively adapt to complex and harsh environments. The results of this study are valuable for applications in solving the difficulties of accurate water level detection and flood disaster early warnings in poor-visibility scenarios.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.