ALNet: Towards Real-Time and Accurate Maize Row Detection via Anchor-Line Network

Ruijun Ma^1*Bofeng Feng¹Qingliang He¹Yun Hu²Hao Cai¹Dongyu Luo¹Zhiye Shen¹Bob Zhang³Long Qi^4,5,6,7*

• ¹College of Engineering, South China Agricultural University, Guangzhou, China
• ²Beijing Jiaotong University School of Traffic and Transportation, Beijing, China
• ³Department of Computer and Information Science, University of Macau, Macau, China
• ⁴College Of Water Conservancy and Civil Engineering, South China Agricultural University, Guangzhou, China
• ⁵Guangdong Engineering Technology Research Center of Rice Transplanting Mechanical Equipment,, Guangzhou, China
• ⁶State Key Laboratory of Agricultural Equipment Technology, Guangzhou, China
• ⁷University of Manitoba Department of Biosystems Engineering, Winnipeg, Canada

Accurate and efficient crop row detection is essential for the visual navigation of agricultural machinery. However, existing deep learning–based methods often suffer from high computational costs, limited deployment capability on edge devices, and difficulty in maintaining both accuracy and speed. This study presents ALNet (Anchor-Line Network), a lightweight convolutional neural network tailored to the elongated geometry of maize rows. ALNet introduces an Anchor-Line mechanism to reformulate row detection as an end-to-end regression task, replacing pixel-wise convolutions with row-aligned kernel operations to reduce computation while preserving geometric continuity. An Attention-guided ROI Align module equipped with a Dual-Axis Extrusion Transformer (DAE-Former) is incorporated to capture global–local feature interactions and enhance robustness under challenging field conditions such as weed infestation, low light, and wind distortion. In addition, a Row IoU (RIoU) loss is designed to improve localization accuracy by aligning predicted and ground-truth row geometries more effectively. Experimental results on field-acquired maize datasets demonstrate that ALNet achieves an mF1 of 59.60 across IoU thresholds (≥9.24 points higher than competing methods) and an inference speed of 161.26 FPS, with a computational cost of only 11.9 GFlops, demonstrating potential for real-time edge deployment. These advances establish ALNet as a practical and scalable solution for intelligent visual navigation in precision agriculture.