LiteMS-YOLO: a lightweight framework for small target detection in complex wheat field environments
Frontiers in Plant Science · 05.06.2026 · 17
DOI: 10.3389/fpls.2026.1851297 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 05.06.2026. Verfasst von Hongliang Ma und 11 weiteren Autor:innen. Beteiligte Einrichtung: Tangshan Academy of Agricultural Sciences, Tangshan, China. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Wheat spike detection is essential for yield estimation in precision agriculture, yet it remains challenging due to the small size of targets, dense distribution, and complex field environments. In this study, we propose LiteMS-YOLO, a lightweight object detection framework based on YOLO26n. The model integrates a Feature Complementary Mapping (FCM) module to enhance spatial-semantic feature interaction and a Multi-Kernel Perception (MKP) unit to improve multi-scale feature representation. In addition, targeted redundancy reduction strategies are introduced to significantly lower model complexity. Experiments are conducted on a combined dataset comprising the public Global Wheat Head Detection (GWHD) dataset and 100 field images collected by the Tangshan Academy of Agricultural Sciences, with a total of 6,378 high-resolution images and over 44,000 annotated wheat spikes. LiteMS-YOLO achieves a mAP50 of 92.28% and a mAP50–95 of 52.56%, while using only 0.627 million parameters. Compared with YOLO26n and YOLOv8n, the proposed method reduces parameters by approximately 75% and 79%, respectively, while maintaining competitive accuracy. These results demonstrate that LiteMS-YOLO strikes an excellent balance between detection accuracy and efficiency, making it well-suited for real-time deployment in resource-constrained agricultural scenarios.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Tangshan Academy of Agricultural Sciences, Tangshan, China.
- Guye District Market Supervision Administration of Tangshan, Tangshan, China.
- College of Animal Science and Technology, Hebei Agricultural University, Baoding, China.
Zitieren
APA
Ma, H., Song, M., Yang, M., Li, T., Wang, X., Wang, M., Zhao, X., Peng, C., Huang, H., Wu, P., Lu, Q., & Wu, Z. (2026). LiteMS-YOLO: a lightweight framework for small target detection in complex wheat field environments. Frontiers in Plant Science, 17. https://doi.org/10.3389/fpls.2026.1851297
Vancouver
Ma H, Song M, Yang M, Li T, Wang X, Wang M, et al. LiteMS-YOLO: a lightweight framework for small target detection in complex wheat field environments. Frontiers in Plant Science. 2026;17. doi:10.3389/fpls.2026.1851297
BibTeX
@article{Ma2026,
author = {Ma, Hongliang and Song, Maoxing and Yang, Mengying and Li, Tong and Wang, Xuefei and Wang, Mochu and Zhao, Xiaoxue and Peng, Cheng and Huang, Huina and Wu, Peng and Lu, Qing and Wu, Zhihui},
title = {LiteMS-YOLO: a lightweight framework for small target detection in complex wheat field environments},
journal = {Frontiers in Plant Science},
year = {2026},
volume = {17},
doi = {10.3389/fpls.2026.1851297}
}
EUVIMED