AUTOMATED ROSE CUTTING IN GREENHOUSES WITH 3D VISION AND ROBOTICS: ANALYSIS OF 3D VISION TECHNIQUES FOR STEM DETECTION

Abstract

The reduction of labour cost is the major motivation to develop a system for robot harvesting of roses in greenhouses that at least can compete with manual harvesting. Due to overlapping leaves, one of the most complicated tasks in robotic rose cutting is to locate the stem and trace the stem down to locate the cutting position. Computer vision techniques like stereo imaging, laser triangulation, röntgen imaging and a new technique, called reverse volumetric intersection, are evaluated in this paper to determine which technique is most feasible for the task. Experiments with the techniques applied on different rose plant indicate that reverse volumetric intersection shows that this technique is most promising to locate the stem down to the cutting position in terms of robustness and costs.