A machine vision based crop rows detection for agricultural robots

Abstract

One approach of navigating agricultural robots to perform different kinds of operations such as weeding, spraying and fertilizing is using a machine vision based row detection system. A new method for robust recognition of crop rows is presented. First, image pre-processing was used to obtain the binarization image; second, the binarization image was divided into several row segments, which created less data points while still reserved information of crop rows; third, vertical projection method was presented to estimate the position of the crop rows for image strips; and last the crop rows were detected by Hough transform. The algorithm requires 70 ms to determine all the crop rows. Experimental results show that this approach can quickly and accurately find the crop rows even under different light conditions.