Cloud-based architecture for automated weed control

Abstract

Automated weed control has received an increased interest from the scientific community in recent years. Even tough there is fairly large number of available approaches and even commercially available systems for weed control, several challenges exist that need to be assessed. Most of the approaches use automated detection of weed and apply herbicides with sprayers on the most infested regions of the land. Automated weed control has proven to reduce the quantity of applied herbicides, thus reducing the pollution of products, land and water. Being a part of the precision agriculture paradigm, automated weed control can be performed only by accessing large amount of on the field sensory data including images and videos from unmanned areal and ground vehicles. With the increased granularity of the regions which is a consequence of the increased resolutions of the used vision sensors, there is even larger need of fast and reliable data processing architectures that allow large volumes of data to be instantly processed. Furthermore, the weed detection includes computer vision algorithms that have high time and space complexity and that often depend on parameters that need to be tuned. By gathering and processing data from multiple fields, the parameter estimation can be performed with higher accuracy and greater reliability. In this paper we propose a cloud based architecture that elevates the automated weed control by using the possibilities introduced from the cloud to gather additional aggregated knowledge from the process of automated weed control and further improve the process of weed control data processing and parameter estimation. We discuss the main benefits of the proposed architecture and the challenges that need to be overcome for it to be introduced to the agricultural communities.