A Robust Recognition Method for Occlusion of Mini Tomatoes based on Hue Information and Shape of Edge

摘要

In this paper, we propose a robust recognition method for occlusion of mini tomatoes based on hue information and shape of edge. This method is used for a managing system using robots for hydroponic that we have proposed. In this system, robots need to detect mini tomatoes to manage farmlands. In a lot of cases, mini tomatoes are covered partially behind its leaf stems or its other fruits. Thence, the system needs a mini tomato recognition method in the situations including occlusion. Firstly, this method detects red areas using hue information from a source image. Secondly, the method detects contours from the areas using contour tracking. Finally, the method judges whether contours are mini tomatoes or not using the curvature. Experimental results showed that recognition rate of this method was 78.8%. Therefore, we consider that the proposed method is appropriate for mini tomato recognition in the situations including occlusion.