Water spray detection for smart irrigation systems with Mask R-CNN and UAV footage

Abstract

While the world’s population rises, demand for food grows accordingly. Smart agriculture emerges as a viable solution to increase the quality and efficiency of crops. Irrigation plays an essential role in the grade and productivity of harvests, while also being a crucial factor in the cost-effectiveness of food production. Smart irrigation uses technology to improve watering, such as the Internet of Things (IoT) applications and Machine Learning algorithms. The correct functioning of irrigation nozzles is critical to ensure that the hydration plan is deployed correctly to the crop field. This paper presents a Machine Learning algorithm that can automatically recognize water from aerial footage of irrigation systems. This automatic recognition can help in the irrigation system inspection, potentially reducing time and cost in system maintenance. Initial results show that it is possible to identify water on image frames captured by an Unmanned Aerial Vehicle (UAV) using the Mask R-CNN Neural Network. The goal is to identify malfunctioning irrigation systems that can lead to under or overwatering, compromising the irrigation plan’s correct implementation.