Innovative computer vision methods for tomato (Solanum Lycopersicon) detection and cultivation: a review

Abstract

Abstract In recent years, machine vision, deep learning, and artificial intelligence have garnered significant research interest in precision agriculture. This article aims to provide a comprehensive review of the latest advancements in machine vision application in tomato cultivation. This study explores integrating cognitive technologies in agriculture, particularly in tomato production. The review covers various studies on tomatoes and machine vision that support tomato harvesting, such as classification, fruit counting, and yield estimation. It addresses plant health monitoring approaches, including detecting weeds, pests, leaf diseases, and fruit disorders. The paper also examines the latest research efforts in vehicle navigation systems and tomato-harvesting robots. The primary objective of this article was to present a thorough analysis of the image processing algorithms utilized in research over the past two years, along with their outcomes.