Recognizing and locating ripe tomatoes based on binocular stereovision technology

A method for recognizing and locating ripe tomatoes based on binocular stereovision technology was developed for tomato harvesting in greenhouse. The color features were used to recognize ripe tomatoes by segmenting target objects from background. According to the results, the position of the fruit centroid was acquired with centroid-based matching. Then in terms of grey correlation of neighborhood regions, depths of the tomato surface points were calculated with area-based matching. And the method of limited candidate region and twice thresholds was used to reduce computation load and improve precision. The error ranged within ±15 mm when the distance was less than 550 mm. It’s feasible to obtain position information of ripe tomatoes with this measurement, and the measurement precision is high.