Abstract
A machine vision system for a tomato fruit cluster harvesting robot was studied in this paper. This machine vision system mainly consisted of two identical color TV cameras (VGA class), four lighting devices with PL filters, and two image capture boards. Two images were acquired by the machine vision and RGB color component images were converted into HSI images. Based on the HSI images, main stem, peduncle, and fruits were detected and an end-effector grasping point on the main stem was recognized using physical properties of the tomato plant. Since difficulty to recognize the grasping point depended on exposure of plant parts and on robot access angle, acquired images were classified into three groups (A, B, and C) and were recognized. Experimental results showed that 73% of grasping points on main stems were successfully recognized excluding Group C (images in which some of them were occluded.) which was not able to be recognized even by human eyes.
