Contactless Water Level Detection System for Pickling Barrels Using Image Recognition Technology

Abstract

Water level monitoring has long been an important task for farmers. Because weather conditions can change quickly, farmers have often checked that the water levels of their crops were ideal for good growing conditions. Farmers would benefit from the development of a simple device to determine the water level of crops at any time. This research designs a noncontact water level detection system, including a data acquisition system, a data management monitoring system, and an instant messenger. In the data acquisition system, a digital water gauge is designed, mainly using image recognition technology to identify the water level in a barrel. Our research shows that using a black dot with a diameter of 1 cm as the water gauge scale can achieve 100% recognition results at a distance of 110 cm. Considering that the application of a contactless water level detection system (CWLDS) in agriculture is a fixed measurement method and an external light source is supported, 100% identification can be obtained, and the operation cost of a CWLDS can be reduced without an additional machine learning technique. To effectively reduce the transmission cost, the reading part of the digital water gauge is divided into single-barrel and multi-barrel parts. The water level information is sent to a management center through a narrowband Internet of Things (NB-IoT) transmission module. This system provides a well-structured and systematic approach to the problem of measuring water levels in pickling barrels. Through the data management monitoring system, the collected water level of each object is matched with a database in the host to determine whether the water level is abnormal. The system can provide immediate alerts to relevant personnel by using popular instant messaging software that transmits abnormal water level information to farmers.