Research On The Technology Of Kiwifruit Recognition And Location Based On Machine Vision

With Kiwi fruit as the subject, the key technology of fruit recognition and location indeveloping the kiwifruit picking robot is studied; the machine vision technique is used tocollect necessary information for effective recognition and location of kiwifruit. The mainresearch results are as follows:(1)In order to identify the best color spatial and color mode, based on robot visiontechnique in Kiwifruit recognition,This paper puts forward using the Haartraining to identifykiwi, Can the preliminary marquee kiwi fruit, and save. this method effectively extracted thekiwi area from images the color components distilled in RGB color space of40pieces ofKiwifruit images are chosen for statistical analysis. With the analyses of color character inkiwifruit, leaves, branches and other important areas, the R–B color mode is the best tosegment Kiwifruit;(2)The fixed and automatic thresholds are adopted respectively to segment the R-BComponent images and the segmentation efficiencies are higher than86%and81%.After comparison, the fixed threshold method has the better segmentation efficiency andreal-time performance, automatic threshold has a better segment effect and adaptability, but itconsumes more time. To solve the residual problem usually existing in segmented two valueimages, flood fill and morphology operation method are applied to eradicate the residualpreferably;(3)Fruit adhesion watershed segmentation method can effectively split, and to achievethe separation of the effects of adhesion fruits.(4)To meet the vision requirements of the fruit robot, outline, area, center of gravity andenclosing rectangle are confirmed as parameters for extracting the object's characters forimage recognition;(5)Develop the matching method of the Kiwifruit centroid; use the centroid characters ofthe fruit in2D image to match the binocular images of Kiwifruit;(6)Using the stereo vision principle after stereo matching, calculate the3D informationof spatial points and locate the position of the fruit. With precise dimensional measurements on the position data, the experiments show that calculation error of the special position is11.2mm when the orientation depth.