E2CropDet: An efficient end-to-end solution to crop row detection

Crop row detection is the basis for the visual navigation of agricultural machinery. Previous research has typi-cally developed crop detection schemes based on specific application objects, with cumbersome image processing steps. A compact and efficient deep learning-based crop row detection network, named E2CropDet, is proposed in this study. E2CropDet models each crop row as a complete and independent object to enable an end-to-end detection manner with no involvement of image post-processing. Generic backbones are used as feature ex-tractors in E2CropDet. Line-shaped proposals are developed as pre-defined detection anchors based on the shape characteristics and distribution pattern of crop rows. The feature vector obtained by pooling along the slender crop rows is fed into fully connected layers after aggregating contextual information. Then the final centreline extraction results are obtained by classification and regression. With ResNet-34 as the backbone, the proposed model results in a lateral deviation of 5.945 pixels for centerline extraction, which exceeds the semantic segmentation-based (7.153) and the Hough transform-based (17.834) approaches. Additionally, benefiting from an end-to-end pipeline that requires no post-process, it achieves a remarkable detection speed of 166 frames per second.

Automated summary

Crop row detection is crucial for visual navigation of agricultural machinery. In this study, a compact and efficient deep learning-based network named E2CropDet is proposed, which models each crop row as an independent object, enabling an end-to-end detection process with no post-processing. The network utilizes generic feature extractors and line-shaped proposals for detection, achieving remarkable results and a detection speed of 166 frames per second.