Development of a Tomato Volume Estimating Robot that Autonomously Searches an Appropriate Measurement Position – Basic Feasibility Study Using a Tomato Bed Mock-Up –

Abstract

Recently, the promotion of the utilization of data mining in Japanese agriculture has become noteworthy. The purpose of such data mining is to transform the knowledge and know-how of experienced farmers into an explicit form. In particular, it is required for creating a tomato cultivation database to acquire the growth data of not only red mature tomatoes, but also green immature tomatoes. We are developing a robot to estimate the volume of a tomato that actively searches an appropriate measurement position. While patrolling a tomato bed, the robot first detects a tomato by using saliency-based image processing technology. When a tomato has been detected, a motion stereo camera installed on the robot generates a point cloud and a clustering process extracts the fruit region. A three-point-algorithm-based ellipse detector then estimates the width of the extracted fruit region. Finally, the estimation result is immediately evaluated using multiple indicators. This immediate evaluation process rejects unreliable data and suggests the correct position for re-measurement.