Development of a line following autonomous spraying vehicle with Machine vision-based leaf density estimation for cherry tomato greenhouses

Abstract

Traditional manual spraying systems and even modern automated ones often neglect the critical factors of plant growth stage and coverage density during spraying for plants, which can result in suboptimal yields. To address this issue, this study aims to describe the development of an efficient and affordable autonomous spraying vehicle (ASV) for application in cherry tomato greenhouses. The ASV integrates a visual autonomous spraying system (VASS) and a vehicle control system (VCS). The VASS uses leaf density signalling with machine vision and a vertical spray boom to target leaves for precision spraying application. Leaf density signalling is an algorithm developed to recognise and estimate leaf density by machine, simplifying the real-time determination of leaf density levels in plants. The performance of the algorithm demonstrates an accuracy of 84 % with an average video processing speed of 33.3 ms. The VASS is integrated into VCS to facilitate remote or autonomous navigation. The visual line-following system (VLFS) supports ASV in autonomously navigating between narrow-spaced rows in cherry tomato greenhouses, thereby automating the entire spraying process. The analysis of the comprehensive performance of the ASV and the comparative analysis with knapsack sprayers in field experiments are discussed and presented. Comparative analysis with manually operated sprayers demonstrates the better performance of the ASV. These experiments highlight the potential of the ASV to replace traditional manual spraying methods while enhancing spraying precision.