Abstract: Harvesting cherry tomatoes is more laborious than harvesting larger size tomatoes
because of the high fruit density in every cluster. To save labor costs, robotic harvesting
of cherry tomatoes has been studied in Japan. An effective vision algorithm, to detect
positions of many small fruits, was developed for guidance of robotically harvested cherry
tomatoes. A spectral reflectance in the visible region was identified and extracted to provide
high contrast images for the fruit cluster identification. The 3-D position of each fruit
cluster was determined using binocular stereo vision technique. The robot harvested one fruit
at a time and the position. The experimental results showed that this visual feedback control
based harvesting method was effective, with a success rate of 70%.