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

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.

Towards Infield Navigation: leveraging simulated data for crop row detection

“…The task T1 should be initiated when the robot is nearing the end of the currently traversing crop row. The End Of Row (EOR) detector from our previous work [11] is used to trigger the T1 task. The EOR detector tracks the row end of a crop field and triggers a signal when the row end reaches the middle of the camera frame.…”

“…End of row (EOR) detection is an important step for any crop row switching algorithm since it serves as the starting point for any crop row switching manoeuvre [6]. The EOR detection scheme proposed in [18] employs image binarisation using classic computer vision methods to calculate the pixel count in binary masks to determine the EOR.…”

“…However, such colour-based EOR detection methods are highly susceptible to distortions caused by external field variations. The advantages of deep learning-based methods in EOR detection outperform such colour-based methods [5], [6]. A 3D point cloud-based rowend detection was introduced in [14] where the EOR is identified by detection of height drop between the plant and the ground within the point cloud.…”

“…To this end, a vision-based navigation system that uses a single front-mounted camera to perform in-row navigation and row switching would be in line with this objective. In our previous work, we have developed a vision-based crop row detection algorithm [5] and an in-row navigation framework [6] that then uses the crop row detection to guide the robot through a single crop row only based on RGB images. The crop row switching algorithm presented in this paper relates to our previous work on vision-based crop row detection [5] and navigation [6] in arable fields.…”

“…In our previous work, we have developed a vision-based crop row detection algorithm [5] and an in-row navigation framework [6] that then uses the crop row detection to guide the robot through a single crop row only based on RGB images. The crop row switching algorithm presented in this paper relates to our previous work on vision-based crop row detection [5] and navigation [6] in arable fields. The newly proposed algorithm serves as a vital bridge, seamlessly connecting with the established in-row navigation algorithm to dexterously integrate into a comprehensive, fully autonomous field-scale navigation behaviour.…”