Morphology-based guidance line extraction for an autonomous weeding robot in paddy fields

Abstract

The guidance line extracted from an image of a rice row precisely guides a robot for weed control in paddy fields. The guidance line enables the robot to follow the crop row without damaging for a successful weed control-equipped vision camera. The accuracy of the guidance line is affected by the morphological characteristics in the image, such as crop leaves, stems, orientation and density. In the case in paddy rice fields, it is difficult to extract the guidance line precisely because leaves are oriented in multiple directions. This paper proposes a new guidance line extraction algorithm to improve the navigation accuracy of weeding robots in paddy fields. The proposed algorithm seeks to identify the central region of the rice plant using the morphological characteristic of which leaves converge normally toward the direction of the central stem region. The guidance line is extracted from the intersection points of virtual straight lines using the modified robust regression. The virtual straight line is represented as the extended line from each segmented straight line created on the edges of the rice plants in the image using the Hough transform. The proposed algorithm was observed to have good performance experimentally with a high accuracy of less than 1 with varying rice plant sizes.