Low-power-consumption water level telemetering system based on artificial intelligence cloud identification water gauge

Abstract

The invention relates to a low-power-consumption water level telemetering system based on an artificial intelligence cloud recognition water gauge. The system comprises a telemetering station, a central station server and a cloud server. The central station server is in communication connection with the client computer through a local area network or the Internet. The telemetering station comprises a network camera aligned with the water gauge, a telemetering terminal, a storage battery for supplying power, and a solar panel for charging the storage battery. The network camera collects imagesof the water gauge, saves the images and sends the images to the cloud server, the cloud server identifies the images and transmits water level data back to the telemetering station, and the telemetering station processes the water level data and sends the processed water level data to the central station server. The system is low in power consumption, low in cost and high in environmental adaptability; according to the invention, not only can quasi-water-level data be measured, but also images shot on site can be seen clearly, and manual data calibration on site is not needed any more throughimage comparison, so that the implementation effect is good.

Description

technical field [0001] The invention relates to a low-power consumption water level remote measurement system based on artificial intelligence cloud recognition water gauge, and belongs to the technical field of hydrological automatic measurement and report. Background technique [0002] At present, the water level measurement sensors of the hydrological automatic measurement and reporting system can be divided into two categories: contact type and non-contact type. Contact type water level gauges include float water level gauges, pressure water level gauges, electronic water gauges, etc. Non-contact water level gauges include radar water level gauges , Ultrasonic water level gauge, etc. No matter which type of water level measurement sensor needs to rely on the site conditions for infrastructure construction, for example, the use of float water level gauges requires logging construction, which is costly, and logging needs to be dredged every year; pressure water level gauge...

AI Technical Summary

Problems solved by technology

No matter which type of water level measurement sensor needs to rely on the site conditions for infrastructure construction, for example, the use of float water level gauges requires logging construction, which is costly, and logging needs to be dredged every year; pressure water level gauges need to prevent silting when they are used on site , to prevent naked leakage when the water recedes, and to avoid lightning strikes; radar and ultrasonic water level gauges need to build poles along the river, and poles that are too long or too high will lead to difficulties in maintenance and repair; all of the above measurement methods require regular visits On-site manual observation for data calibration

[0003] The central station can only read the data but cannot check the on-site conditions. When the data is abnormal, there is no traceability

[0004] At present, some products on the market, such as water gauge reading smart domes, use image recognition water gauge to read water level data, which has the disadvantages of needing AC power supply, high power consumption, and high cost, and is not suitable for remote applications without AC power. It is difficult to popularize in a large area; at the same time, although the built-in firmware of the camera claims to comply with the SL651-2014 "Hydrological Monitoring Data Communication Protocol", in actual applications, the communication protocols used in each province, city, and region have their own emphasis, and the communication function codes are different. Therefore, it cannot meet the practical application of various scenarios, and the scalability is poor

[0005] Traditional non-artificial intelligence image detection and recognition is usually based on grayscale, features and relationships. This technology relies on certain algorithms and specific scene optimization methods, resulting in weak generalization capabilities, complex algorithms, and long time-consuming. It is difficult to achieve real-time and universal Adaptability, no breakthrough development, low water gauge detection accuracy and recognition rate, and productization and other factors failed to meet the actual requirements. Practical degree

Images