Robot-supervised Learning of Crop Row Segmentation
Authors:
- 30 May 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2185-2191
Abstract
We propose an approach for robot-supervised learning that automates label generation for semantic segmentation with Convolutional Neural Networks (CNNs) for crop row detection in a field. Using a training robot equipped with RTK GNSS and RGB camera, we train a neural network that can later be used for pure vision-based navigation. We test our approach on an agri-robot in a strawberry field and successfully train crop row segmentation without any hand-drawn image labels. Our main finding is that the resulting segmentation output of the CNN shows better performance than the noisy labels it was trained on. Finally, we conduct open-loop field trials with our agri-robot and show that row-following based on the segmentation result is accurate enough for closed-loop guidance. We conclude that training with noisy segmentation labels is a promising approach for learning vision-based crop row following.Keywords
This publication has 26 references indexed in Scilit:
- Self-supervised weed detection in vegetable crops using ground based hyperspectral imaging2016
- A Machine Learning Approach to Visual Perception of Forest Trails for Mobile RobotsIEEE Robotics and Automation Letters, 2015
- Towards Autonomous Agriculture: Automatic Ground Detection Using Trinocular StereovisionSensors, 2012
- Support Vector Machines for crop/weeds identification in maize fieldsExpert Systems with Applications, 2012
- Self‐supervised learning to visually detect terrain surfaces for autonomous robots operating in forested terrainJournal of Field Robotics, 2012
- Stereo vision with texture learning for fault-tolerant automatic balingComputers and Electronics in Agriculture, 2011
- A Stereovision-based Crop Row Detection Method for Tractor-automated GuidanceBiosystems Engineering, 2005
- A vision based row-following system for agricultural field machineryMechatronics, 2005
- Real-Time Tracking of Plant Rows Using a Hough TransformReal-Time Imaging, 1995
- Color Indices for Weed Identification Under Various Soil, Residue, and Lighting ConditionsTransactions of the ASAE, 1995