Robotic crop row tracking around weeds using cereal-specific features

Crop row following is especially challenging in narrow row cereal crops, such as wheat. Separation between plants within a row disappears at an early growth stage, and canopy closure between rows, when leaves from different rows start to occlude each other, occurs three to four months after the crop emerges. Canopy closure makes it challenging to identify separate rows through computer vision as clear lanes become obscured. Cereal crops are grass species and so their leaves have a predictable shape and orientation. We introduce an image processing pipeline which exploits grass shape to identify and track rows. The key observation exploited is that leaf orientations tend to be vertical along rows and horizontal between rows due to the location of the stems within the rows. Adaptive mean-shift clustering on Hough line segments is then used to obtain lane centroids, and followed by a nearest neighbor data association creating lane line candidates in 2D space. Lane parameters are fit with linear regression and a Kalman filter is used for tracking lanes between frames. The method is achieves sub-50 mm accuracy which is sufficient for placing a typical agri-robot's wheels between real-world, early-growth wheat crop rows to drive between them, as long as the crop is seeded in a wider spacing such as 180 mm row spacing for an 80 mm wheel width robot.

Automated summary

Crop row following in narrow row cereal crops is challenging, as the separation between plants within a row disappears early on and canopy closure between rows occurs months later. This study proposes an image processing pipeline that uses the shape and orientation of grass leaves to identify and track rows. The method achieves sub-50 mm accuracy and is suitable for agri-robots to drive between real-world wheat crop rows.