Towards agricultural autonomy: crop row detection under varying field conditions using deep learning
This addresses the problem of reliable navigation for agricultural robots in real-world fields, though it is incremental as it focuses on evaluating robustness rather than introducing a major new method.
The paper tackled crop row detection for agricultural robots by evaluating a deep learning semantic segmentation model's robustness across varying field conditions, finding it robust to shadows and growth stages but performance decreased under direct sunlight, high weed density, tramlines, and row discontinuities.
This paper presents a novel metric to evaluate the robustness of deep learning based semantic segmentation approaches for crop row detection under different field conditions encountered by a field robot. A dataset with ten main categories encountered under various field conditions was used for testing. The effect on these conditions on the angular accuracy of crop row detection was compared. A deep convolutional encoder decoder network is implemented to predict crop row masks using RGB input images. The predicted mask is then sent to a post processing algorithm to extract the crop rows. The deep learning model was found to be robust against shadows and growth stages of the crop while the performance was reduced under direct sunlight, increasing weed density, tramlines and discontinuities in crop rows when evaluated with the novel metric.