Row anchor selection classification method for early-stage crop row-following

• Published in: Computers and electronics in agriculture Vol. 192; p. 106577
• Main Authors: Wei, Chunyu, Li, Hailong, Shi, Junyi, Zhao, Guoyang, Feng, Huaiqu, Quan, Longzhe
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.01.2022; Elsevier BV
• Subjects: Accuracy; Agriculture Robotics; Artificial neural networks; Classification; Datasets; Lightweight DCNN; Navigation; Project management; Row Anchor Classification; Row Anchor Selection; Segmentation; Visual-based Navigation; Visual-based Navigation; Lightweight DCNN; Row Anchor Selection; Row Anchor Classification; Agriculture Robotics
• ISSN: 0168-1699; 1872-7107
• DOI: 10.1016/j.compag.2021.106577

•A crop row following method (RASCM) is proposed with cost-effectiveness and execution speed considered.•RasM is proposed to obtain crop row datasets, which effectively reducing manpower and costs.•GhostNet is used as backbone network to perform better and reduce memory usage.•C-loss is proposed to improve the accuracy of GhostNet.•RASCM is a novel attempt in the research field of crop line tracking and resulting in excellent reference significance. The field navigation tasks of agricultural robots are the basis for implementing field management projects in the early stages of seedlings guided by precision agriculture policies. High accuracy and execution speed of navigation tasks are needed for the escalating field machine implementations in a significantly unstructured and irregular field environment, contributing to the difficulty and urgency of achieving a field navigation solution with high navigation accuracy while maintaining proper execution speed. In our study, the row anchor selection classification method (RASCM) is presented to track early-stage crop rows, and the early corn seedling dataset (E-dataset) and LRC-dataset are developed for the measurement of the experimental results. RASCM is divided into three parts, including a row anchor selection method (RasM), a lightweight deep convolutional neural network (DCNN) network GhostNet, and a combined loss function (C-loss). It is suggested that RASCM has achieved good results in terms of calculation speed and accuracy by comparing the end-to-end regression operation based on the steering wheel angle (E2Er) and crop row pixel segmentation (SeG) approaches with RASCM on the LRC-dataset, which can be effectively applied in actual projects. Finally, a class activation map (CAM) is used to visualize the internal working mechanism of GhostNet, and the demonstrated effectiveness of GhostNet is not limited to the RasM labeling area. In contrast, broad global features are learned, and the previous noise is highly mitigated. Strong generalization performance for different environments is displayed by using RACSM, contributing to the effectiveness of early-stage crop row-following. The main contribution of our paper is the proposal of RASCM, which is a novel method in the field of early-stage crop row-following and can be used as a basic reference for subsequent work in this research field.