EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

End-to-End Extraction of Maize-Row Navigation Lines Using Spatially Constrained Point Annotations

Delin Shang, Yu Yang, Huijun Zhao, Xiaole Wang, Tie Zhang, Zhenchao Wu, Gang Zhang

Agronomy · 18.11.2026 · 16 (22) · 2331

DOI: 10.3390/agronomy16222331 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Agronomy, online erschienen am 18.11.2026. Verfasst von Delin Shang und 6 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Laboratory of Agricultural Equipment Technology, Scientific Research Start-up Foundation of Anhui Agricultural University, Horizontal Scientific Research Program of Anhui Science and Technology University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rapid and stable extraction of maize-row navigation lines is essential for autonomous inter-row operations by agricultural robots. Existing deep-learning methods typically detect individual plants or segment maize rows, then derive navigation feature points from geometric cues including bounding boxes, region centroids, edges, or skeletons. These stages can accumulate errors, while additional post-processing increases computational cost. This study developed point annotations representing navigation-line geometry for end-to-end prediction of navigation keypoints from field images. A navigation-keypoint dataset covering complex maize-row scenarios was constructed from seedling-stage field images collected under diverse natural conditions. Each row was an independent instance. Keypoints generated at fixed vertical positions from manually annotated navigation-line endpoints were directly predicted as structured sequences using YOLOv11n-pose and fitted by least squares. Field-image experiments yielded Pose AP50 and Pose AP50–95 of 99.3% and 95.5%, respectively. Navigation-line normalized root mean square error, normalized lateral error, and angular error were 1.221%, 1.090%, and 1.206°, respectively, with all test navigation lines matched. Processing reached 91.90 frames per second without separate navigation feature-point calculation, balancing detection completeness and real-time performance. In 200-frame video sequences, maximum adjacent-frame heading-angle changes were 8.774° and 2.920° under normal-row and sparse-row conditions, respectively. An observed transient spike under complex interference subsided in the next frame. These results demonstrate that spatially constrained point annotations enable direct learning of navigation-line geometry and reduce dependence on intermediate region processing, providing an effective path-perception approach for real-time field navigation by agricultural robots.

Förderung

  • National Key Laboratory of Agricultural Equipment Technology
  • Scientific Research Start-up Foundation of Anhui Agricultural University
  • Horizontal Scientific Research Program of Anhui Science and Technology University

Zitieren

APA

Shang, D., Yang, Y., Zhao, H., Wang, X., Zhang, T., Wu, Z., & Zhang, G. (2026). End-to-End Extraction of Maize-Row Navigation Lines Using Spatially Constrained Point Annotations. Agronomy, 16(22), 2331. https://doi.org/10.3390/agronomy16222331

Vancouver

Shang D, Yang Y, Zhao H, Wang X, Zhang T, Wu Z, et al. End-to-End Extraction of Maize-Row Navigation Lines Using Spatially Constrained Point Annotations. Agronomy. 2026;16(22):2331. doi:10.3390/agronomy16222331

BibTeX
@article{Shang2026,
  author = {Shang, Delin and Yang, Yu and Zhao, Huijun and Wang, Xiaole and Zhang, Tie and Wu, Zhenchao and Zhang, Gang},
  title = {End-to-End Extraction of Maize-Row Navigation Lines Using Spatially Constrained Point Annotations},
  journal = {Agronomy},
  year = {2026},
  volume = {16},
  number = {22},
  pages = {2331},
  doi = {10.3390/agronomy16222331}
}
Kostenlos starten →