Tomato Crop Identification and Recognition for an Autonomous Agricultural Robotic System

Abstract

Using computer vision techniques for robotic systems made for use in agricultural settings is optimal for identifying plants yielding fruit ready to be harvested. In this study, a system for identifying objects by comparing them to an image with a single shape and measuring the total difference between them is proposed as a base for a larger system that can correctly identify the stage of maturity of tomato fruit growing on a plant based on the difference in size and shape from a base image. This was performed by a program that compares a template image with a basic shape, such as a circle or square, and counts the number of pixels yielded in a generated image that highlights the difference between the template image and another test image. Another idea proposed in this study is a program that counts objects in an image by using a technique that involves splitting an image into a celled grid. This information can be implemented into a robotic system, such as a Turtlebot, to assist in object/crop detection in an agricultural setting.