Semantic segmentation for weed detection in corn
Pest Management Science · 2025
DOI: 10.1002/ps.8554 ↗Kurz gefasst
Fachartikel in der Zeitschrift Pest Management Science, 2025. Verfasst von Teng Liu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Peking University Institute of Advanced Agricultural Sciences/Shandong Laboratory of Advanced Agricultural Sciences at Weifang, Weifang, China. Hauptthemen laut MEDLINE: Zea mays, Plant Weeds, Weed Control, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: The Key R&D Program of Shandong Province, The Taishan Scholar of Shandong Program, The National Natural Science Foundation of China.
Abstract (Originalsprache)
BACKGROUND Reliable, fast, and accurate weed detection in farmland is crucial for precision weed management but remains challenging due to the diverse weed species present across different fields. While deep learning models for direct weed detection have been developed in previous studies, creating a training dataset that encompasses all possible weed species, ecotypes, and growth stages is practically unfeasible. This study proposes a novel approach to detect weeds by integrating semantic segmentation with image processing. The primary aim is to simplify the weed detection process by segmenting crop pixels and identifying all vegetation outside the crop mask as weeds. RESULTS The proposed method employs a semantic segmentation model to generate a mask of corn ( Zea mays L.) crops, identifying all green plant pixels outside the mask as weeds. This indirect segmentation approach reduces model complexity by avoiding the need for direct detection of diverse weed species. To enhance real‐time performance, the semantic segmentation model was optimized through knowledge distillation, resulting in a faster, lighter‐weight inference. Experimental results demonstrated that the DeepLabV3+ model, after applying knowledge distillation, achieved an average accuracy (aAcc) exceeding 99.5% and a mean intersection over union (mIoU) across all categories above 95.5%. Furthermore, the model's operating speed surpassed 34 frames per second (FPS). CONCLUSION This study introduces a novel method that accurately segments crop pixels to form a mask, identifying vegetation outside this mask as weeds. By focusing on crop segmentation, the method avoids the complexity associated with diverse weed species, varying densities, and different growth stages. This approach offers a practical and efficient solution to facilitate the training of effective computer vision models for precision weed detection and control. © 2024 Society of Chemical Industry.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Peking University Institute of Advanced Agricultural Sciences/Shandong Laboratory of Advanced Agricultural Sciences at Weifang, Weifang, China.
- Department of Computer Science, Duke University, Durham, NC, USA.
ORCID-Profile: Teng Liu
Förderung
- The Key R&D Program of Shandong Province
- The Taishan Scholar of Shandong Program
- The National Natural Science Foundation of China
Zitieren
APA
Liu, T., Jin, X., Han, K., He, F., Wang, J., Chen, X., Kong, X., & Yu, J. (2025). Semantic segmentation for weed detection in corn. Pest Management Science. https://doi.org/10.1002/ps.8554
Vancouver
Liu T, Jin X, Han K, He F, Wang J, Chen X, et al. Semantic segmentation for weed detection in corn. Pest Management Science. 2025. doi:10.1002/ps.8554
BibTeX
@article{Liu2025,
author = {Liu, Teng and Jin, Xiaojun and Han, Kang and He, Feiyu and Wang, Jinxu and Chen, Xin and Kong, Xiaotong and Yu, Jialin},
title = {Semantic segmentation for weed detection in corn},
journal = {Pest Management Science},
year = {2025},
doi = {10.1002/ps.8554}
}
EUVIMED