EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ADFSNet: An Adaptive Domain Feature Separation Network for the Classification of Wheat Seed Using Hyperspectral Images

Xin Zhao, Shuo Liu, Haotian Que, Min Huang iD, Qibing Zhu

Sensors · 27.09.2023 · 23 (19) · 8116

DOI: 10.3390/s23198116 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 27.09.2023. Verfasst von Xin Zhao und 4 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), School of Internet of Things Engineering, Jiangnan University,…. Hauptthemen laut MEDLINE: Triticum, Climate. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Nature Science Foundation of China, Fundamental Research Funds for the Central Universities, High level project of Jiangsu Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wheat seed classification is a critical task for ensuring crop quality and yield. However, the characteristics of wheat seeds can vary due to variations in climate, soil, and other environmental factors across different years. Consequently, the present classification model is no longer adequate for accurately classifying novel samples. To tackle this issue, this paper proposes an adaptive domain feature separation (ADFS) network that utilizes hyperspectral imaging techniques for cross-year classification of wheat seed varieties. The primary objective is to improve the generalization ability of the model at a minimum cost. ADFS leverages deep learning techniques to acquire domain-irrelevant features from hyperspectral data, thus effectively addressing the issue of domain shifts across datasets. The feature spaces are divided into three parts using different modules. One shared module aligns feature distributions between the source and target datasets from different years, thereby enhancing the model’s generalization and robustness. Additionally, two private modules extract class-specific features and domain-specific features. The transfer mechanism does not learn domain-specific features to reduce negative transfer and improve classification accuracy. Extensive experiments conducted on a two-year dataset comprising four wheat seed varieties demonstrate the effectiveness of ADFS in wheat seed classification. Compared with three typical transfer learning networks, ADFS can achieve the best accuracy of wheat seed classification with small batch samples updated, thereby addressing new seasonal variability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TriticumClimateHyperspectral ImagingSeedsSoil

Stichwörter der Autor:innen

domain adaptivefeature separationhyperspectral imageswheat seed

Substanzen

Soil

Autor:innen und Institutionen

  • Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China.

ORCID-Profile: Min Huang

Förderung

  • National Nature Science Foundation of China
  • Fundamental Research Funds for the Central Universities
  • High level project of Jiangsu Province

Zitieren

APA

Zhao, X., Liu, S., Que, H., Huang, M., & Zhu, Q. (2023). ADFSNet: An Adaptive Domain Feature Separation Network for the Classification of Wheat Seed Using Hyperspectral Images. Sensors, 23(19), 8116. https://doi.org/10.3390/s23198116

Vancouver

Zhao X, Liu S, Que H, Huang M, Zhu Q. ADFSNet: An Adaptive Domain Feature Separation Network for the Classification of Wheat Seed Using Hyperspectral Images. Sensors. 2023;23(19):8116. doi:10.3390/s23198116

BibTeX
@article{Zhao2023,
  author = {Zhao, Xin and Liu, Shuo and Que, Haotian and Huang, Min and Zhu, Qibing},
  title = {ADFSNet: An Adaptive Domain Feature Separation Network for the Classification of Wheat Seed Using Hyperspectral Images},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {19},
  pages = {8116},
  doi = {10.3390/s23198116}
}
Kostenlos starten →