Vision based Crop Row Navigation under Varying Field Conditions in Arable Fields

TL;DR

This paper introduces a new dataset and a robust vision-based algorithm for crop row detection that performs well under diverse and challenging field conditions, aiding autonomous navigation in agriculture.

Contribution

It provides a comprehensive dataset with 11 field variations and a novel RGB image-based crop row detection algorithm for robust autonomous navigation.

Findings

The algorithm outperforms traditional colour-based methods.

It effectively detects crop rows under various challenging conditions.

It can identify crop row ends and navigate towards headlands.

Abstract

Accurate crop row detection is often challenged by the varying field conditions present in real-world arable fields. Traditional colour based segmentation is unable to cater for all such variations. The lack of comprehensive datasets in agricultural environments limits the researchers from developing robust segmentation models to detect crop rows. We present a dataset for crop row detection with 11 field variations from Sugar Beet and Maize crops. We also present a novel crop row detection algorithm for visual servoing in crop row fields. Our algorithm can detect crop rows against varying field conditions such as curved crop rows, weed presence, discontinuities, growth stages, tramlines, shadows and light levels. Our method only uses RGB images from a front-mounted camera on a Husky robot to predict crop rows. Our method outperformed the classic colour based crop row detection baseline. Dense weed presence within inter-row space and discontinuities in crop rows were the most challenging field conditions for our crop row detection algorithm. Our method can detect the end of the crop row and navigate the robot towards the headland area when it reaches the end of the crop row.