Systems, Man, and Cybernetics

 

Home

• [P1245] Ripe Tomato Extraction For A Harvesting Robotic System
  Author(s): Simon X. Yang
  
  

  Abstract
  A robotic system for harvesting tomatoes in greenhouses is designed. Effective extraction of ripe tomatoes from complex background is the key technology of the harvesting robotic system. In this work, the color feature of ripe tomatoes is utilized. The ripe tomato is segmented by K-means clustering using the L?a?b? color space. To help the robotic system identify the tomato's center coordinate, extracting a single ripe tomato one by one is necessary. In order to identify the single ripe tomato, mathematical morphology is used to denoise and handle the situations of tomato overlapping and sheltering. Experimental results demonstrate the effectiveness of the proposed method.

  
   

Full Text (PDF)