EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning-Driven Automatic Segmentation of Weeds and Crops in UAV Imagery

Jianghan Tao, Qian Qiao, Jian Song, Shan Sun, Yijia Chen, Qingyang Wu iD, Yongying Liu iD, Feng Xue, Hao Wu, Fan Zhao iD

Sensors · 25.10.2025 · 25 (21) · 6576

DOI: 10.3390/s25216576 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.10.2025. Verfasst von Jianghan Tao und 9 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Global Environmental Studies, Sophia University, Tokyo 102-8554, Japan. Die Arbeit wurde bisher 42-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Science and Technology Agency SPRING Program (JST SPRING), JST SPRING Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate segmentation of crops and weeds is essential for enhancing crop yield, optimizing herbicide usage, and mitigating environmental impacts. Traditional weed management practices, such as manual weeding or broad-spectrum herbicide application, are labor-intensive, environmentally harmful, and economically inefficient. In response, this study introduces a novel precision agriculture framework integrating Unmanned Aerial Vehicle (UAV)-based remote sensing with advanced deep learning techniques, combining Super-Resolution Reconstruction (SRR) and semantic segmentation. This study is the first to integrate UAV-based SRR and semantic segmentation for tobacco fields, systematically evaluate recent Transformer and Mamba-based models alongside traditional CNNs, and release an annotated dataset that not only ensures reproducibility but also provides a resource for the research community to develop and benchmark future models. Initially, SRR enhanced the resolution of low-quality UAV imagery, significantly improving detailed feature extraction. Subsequently, to identify the optimal segmentation model for the proposed framework, semantic segmentation models incorporating CNN, Transformer, and Mamba architectures were used to differentiate crops from weeds. Among evaluated SRR methods, RCAN achieved the optimal reconstruction performance, reaching a Peak Signal-to-Noise Ratio (PSNR) of 24.98 dB and a Structural Similarity Index (SSIM) of 69.48%. In semantic segmentation, the ensemble model integrating Transformer (DPT with DINOv2) and Mamba-based architectures achieved the highest mean Intersection over Union (mIoU) of 90.75%, demonstrating superior robustness across diverse field conditions. Additionally, comprehensive experiments quantified the impact of magnification factors, Gaussian blur, and Gaussian noise, identifying an optimal magnification factor of 4×, proving that the method was robust to common environmental disturbances at optimal parameters. Overall, this research established an efficient, precise framework for crop cultivation management, offering valuable insights for precision agriculture and sustainable farming practices.

Schlagwörter

Stichwörter der Autor:innen

UAV remote sensingautomatic segmentationcrops-weed detectiondeep learningprecision agriculturesuper-resolution reconstruction

Autor:innen und Institutionen

  • Graduate School of Global Environmental Studies, Sophia University, Tokyo 102-8554, Japan.
  • Faculty of Robot Science and Engineering, Northeastern University, Shenyang 110819, China.
  • Graduate School of Frontier Sciences, The University of Tokyo, Tokyo 277-8563, Japan.
  • College of Information Science and Engineering, Xinjiang College of Science & Technology, Urumqi 830046, China.
  • Department of Environmental Health Sciences, University of California, Los Angeles, CA 90095, USA.
  • Graduate School of Information, Production and Systems, Waseda University, Tokyo 169-8050, Japan.

ORCID-Profile: Qingyang Wu, Yongying Liu, Fan Zhao

Förderung

  • Japan Science and Technology Agency SPRING Program (JST SPRING)
  • JST SPRING Program

Zitieren

APA

Tao, J., Qiao, Q., Song, J., Sun, S., Chen, Y., Wu, Q., Liu, Y., Xue, F., Wu, H., & Zhao, F. (2025). Deep Learning-Driven Automatic Segmentation of Weeds and Crops in UAV Imagery. Sensors, 25(21), 6576. https://doi.org/10.3390/s25216576

Vancouver

Tao J, Qiao Q, Song J, Sun S, Chen Y, Wu Q, et al. Deep Learning-Driven Automatic Segmentation of Weeds and Crops in UAV Imagery. Sensors. 2025;25(21):6576. doi:10.3390/s25216576

BibTeX
@article{Tao2025,
  author = {Tao, Jianghan and Qiao, Qian and Song, Jian and Sun, Shan and Chen, Yijia and Wu, Qingyang and Liu, Yongying and Xue, Feng and Wu, Hao and Zhao, Fan},
  title = {Deep Learning-Driven Automatic Segmentation of Weeds and Crops in UAV Imagery},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {21},
  pages = {6576},
  doi = {10.3390/s25216576}
}
Kostenlos starten →