ALNet: towards real-time and accurate maize row detection via anchor-line network
Bibliographic record
Abstract
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 mF 1 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".