Crop Row Line Detection with Auxiliary Segmentation Task

Abstract

Autonomous robots for agricultural tasks have been researched to great extent in the past years as they could result in a great improvement of field efficiency. Navigating an open crop field still is a great challenge; RTK-GNSS is a excellent tool to track the robot’s position, but it needs precise mapping and planning while also being expensive and signal dependent. As such, onboard systems that can sense the field directly to guide the robot are a good alternative. Those systems detect the rows with adequate image techniques and estimate the position by applying algorithms to the obtained mask, such as the Hough transform or linear regression. In this paper, a direct approach is presented by training a neural network model to obtain the position of crop lines directly from an RGB image. While, usually, the camera in such systems are looking down to the field, a camera near the ground is proposed to take advantage of tunnels formed between rows. A simulation environment for evaluating both the model’s performance and camera placement was developed and made available in Github, and two datasets to train the models are proposed. The results are shown across different resolutions and stages of plant growth, indicating the system’s capabilities and limitations.

This study was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brasil (CAPES) - Finance Code 001; The National Council for Scientific and Technological Development - CNPq under project number 314121/2021-8; and Fundação de Apoio a Pesquisa do Rio de Janeiro (FAPERJ) - APQ1 Program - E-26/010.001551/2019.