In order to provide fairly perfect environment information for automatic navigation and harvesting obstacle avoidance of apple harvesting robot, the trunk and branch of apple harvesting robot was studied. The most effective multiple segmentation method of trunk and branch was selected after the discussing and comparison, then the morphological closed operation and holes filling operation were executed, the central axis that is the main characteristics of trunk and branch that was extracted through skeletonizing method and removing subbranch method based on different templates. Finally, the tests about recognition effect and recognition time for trunk and branch were done, the detecting rate was 95%, and the recognition average time was less than 1s.
展开▼
