EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MS-TFNet: a multi-scale temporal feature fusion network for maize growth stage recognition

Su Wu, Zhihao Liu, Dongli Wu, Yijun Liu, Hanxiao Zhang, Mengxuan Liu, Dongzhe Tian, Guisheng Yin

Frontiers in Plant Science · 21.08.2026 · 17

DOI: 10.3389/fpls.2026.1882260 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 21.08.2026. Verfasst von Su Wu und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Harbin Engineering University, Harbin, China. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate maize growth stage recognition is critical for precision agricultural management, but it remains challenging due to subtle morphological differences between adjacent stages, small seedling targets, and substantial cross-year environmental variability. To address these challenges, this study proposes a Multi-Scale Temporal Feature Fusion Network, termed MS- TFNet, for image-level maize growth stage recognition using red-green-blue (RGB) images and acquisition-date information. The proposed network integrates three complementary components. First, a Multi-Scale Feature Extraction Module (MS) is introduced to capture maize structural variations at different receptive-field scales. Second, a Vegetation-Aware Convolutional Block Attention Module (VCBAM) is designed to adaptively refine RGB feature responses and improve the representation of maize-related visual cues under complex field backgrounds. Third, a Temporal Feature Module (TFM) encodes image acquisition dates using date-based sine–cosine temporal encoding, enabling phenological prior information to be incorporated into single-image growth stage classification. Experiments were conducted on a long-term field observation dataset containing 24,239 maize images collected over eight growing seasons and covering nine maize growth stages. The results show that MS-TFNet achieved a mean Overall Accuracy (OA) of 83.64%, outperforming the ResNet-50 baseline by 4.46 percentage points. Under a ±3-day temporal tolerance criterion, the recognition accuracy further increased to 93.76%, indicating improved robustness for practical crop monitoring scenarios. Overall, MS-TFNet provides an effective framework for maize growth stage recognition under complex field conditions by jointly exploiting multi-scale visual representation, vegetation-aware attention, and acquisition-date-based phenological priors.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismsfield-based RGB imagerymaize growth stage recognitionmulti-scale feature fusiontemporal feature embedding

Autor:innen und Institutionen

  • College of Computer Science and Technology, Harbin Engineering University, Harbin, China.
  • Henan Zhongyuan Photoelectric Measurement and Control Technology Co., Ltd., Zhengzhou, China.
  • Meteorological Observation Centre, China Meteorological Administration, Beijing, China.

Förderung

  • National Key Research and Development Program of China

Zitieren

APA

Wu, S., Liu, Z., Wu, D., Liu, Y., Zhang, H., Liu, M., Tian, D., & Yin, G. (2026). MS-TFNet: a multi-scale temporal feature fusion network for maize growth stage recognition. Frontiers in Plant Science, 17. https://doi.org/10.3389/fpls.2026.1882260

Vancouver

Wu S, Liu Z, Wu D, Liu Y, Zhang H, Liu M, et al. MS-TFNet: a multi-scale temporal feature fusion network for maize growth stage recognition. Frontiers in Plant Science. 2026;17. doi:10.3389/fpls.2026.1882260

BibTeX
@article{Wu2026,
  author = {Wu, Su and Liu, Zhihao and Wu, Dongli and Liu, Yijun and Zhang, Hanxiao and Liu, Mengxuan and Tian, Dongzhe and Yin, Guisheng},
  title = {MS-TFNet: a multi-scale temporal feature fusion network for maize growth stage recognition},
  journal = {Frontiers in Plant Science},
  year = {2026},
  volume = {17},
  doi = {10.3389/fpls.2026.1882260}
}
Kostenlos starten →