Crop‐edge detection based on machine vision

Abstract Attached to an agricultural machine, a crop‐edge detection system and algorithm based on machine vision was developed in this study. A camera was mounted in front of a tractor and captured crop images during normal field operation. Using the colour and luminance differences of the crop and the cropped area, the position of the crop edge and specific points could be detected. The line of the crop edge was calculated using the Passing a Known Point Hough Transform. The test results show that the method is suitable for a range of different crops and had the key characteristics of fast response times, high accuracy and low sensitivity to stray environmental interferences.