Research on Navigation Line Extraction Algorithm Based on Onion Ridge Edge Features

Aiming at the phenomenon that existing shallot harvester cannot realize automatic operation in harvesting process of green onion, a navigation path acquisition method onion is proposed, which applied to driving harvester. Firstly, original image grayed by G-R algorithm, and then gray segmented maximum inter-class variance obtain binaryized image; secondly, morphological binary map for noise reduction processing hole filling ridge with good connectivity; then, according geometric characteristics ridge, left right edge feature points are detected, midpoint taken as key point; finally, point fitted least squares method. Gets line ridge. Experimental results show proposed algorithm takes about 71ms an resolution 450 pixels 330 pixels, average error angle 0.649°. The can accurately quickly extract provide accurate information