Real-time Detection of Between-row Weeds Using Machine Vision

A system used machine vision to detect between-row weeds was developed and tested inlaboratory with outdoor lighting conditions. A software system named Between-row WeedsDetection System was developed to process the images. The proposed algorithms used colorinformation to discriminate between plants and background, whilst novel analysis techniques wereapplied to distinguish between crop and between-row weeds by use of the information of plantslocation within the field. Firstly, the excessive green algorithm was adopted to gray the sourceimages. Secondly, the gray-level image was transformed to binary image by use of the algorithm ofthe maximum variance optimal threshold selection. Finally, crops and weed were segmented by useof the seed-fill algorithm. It was indicated that the DWB system had the superiority in real-time.