EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SS-OPDet: A Semi-Supervised Open-Set Detection Framework for Dead Pine Wood Detection

Xiaojian Lu iD, Shiguo Huang, Songqing Wu iD, Feiping Zhang, Mingqing Weng, Jianlong Luo, Xiaolin Li

Sensors · 2025

DOI: 10.3390/s25113407 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Xiaojian Lu und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou 350002, China. Hauptthemen laut MEDLINE: Pinus, Plant Diseases, Wood. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Key R&D Program of China, the Natural Science Foundation of Fujian Province, China, the Scientific and Technological Innovation of Fujian Agriculture and Forestry University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Pine wilt disease poses a significant threat to pine forests worldwide, necessitating efficient and accurate detection of dead pine wood for effective disease control and forest management. Traditional deep learning methods based on supervised closed-set paradigms often struggle to address unknown interfering objects, causing false positives, missed detection, and increased annotation burdens. To overcome these challenges, we propose SS-OPDet, a semi-supervised open-set detection framework that leverages a small amount of labeled data along with abundant unlabeled data. SS-OPDet integrates a Weighted Multi-scale Feature Fusion module to dynamically integrate global- and local-scale features, thereby significantly improving representational accuracy for dead pine wood. Additionally, a Dynamic Confidence Pseudo-Label Generation strategy categorizes predictions by confidence level, effectively reducing training noise and maximizing the use of reliable unlabeled data. Experimental results from 7733 UAV images demonstrate that SS-OPDet achieves an average precision (APK) of 84.73%, a recall (RK) of 94.48%, an Absolute Open-Set Error (AOSE) of 271 and a Wilderness Impact (WI) of 0.0917%. Cross-region validation further confirms the robustness and generalization capability of the proposed framework. The proposed method offers a cost-effective and accurate solution for timely detection of pine wilt disease, providing substantial benefits to forest monitoring and management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PinusPlant DiseasesWoodForestsDeep LearningRemote Sensing TechnologyAlgorithms

Stichwörter der Autor:innen

dead pine wooddynamic confidence pseudo-label generationopen-set detectionsemi-supervised learningweighted multi-scale feature fusion

Autor:innen und Institutionen

  • College of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou 350002, China.
  • College of Forestry, Fujian Agriculture and Forestry University, Fuzhou 350002, China.

ORCID-Profile: Xiaojian Lu, Songqing Wu

Förderung

  • the National Key R&D Program of China
  • the Natural Science Foundation of Fujian Province, China
  • the Scientific and Technological Innovation of Fujian Agriculture and Forestry University
  • National Key R&D Program of China
  • Natural Science Foundation of Fujian Province, China
  • Scientific and Technological Innovation of Fujian Agriculture and Forestry University

Zitieren

APA

Lu, X., Huang, S., Wu, S., Zhang, F., Weng, M., Luo, J., & Li, X. (2025). SS-OPDet: A Semi-Supervised Open-Set Detection Framework for Dead Pine Wood Detection. Sensors. https://doi.org/10.3390/s25113407

Vancouver

Lu X, Huang S, Wu S, Zhang F, Weng M, Luo J, et al. SS-OPDet: A Semi-Supervised Open-Set Detection Framework for Dead Pine Wood Detection. Sensors. 2025. doi:10.3390/s25113407

BibTeX
@article{Lu2025,
  author = {Lu, Xiaojian and Huang, Shiguo and Wu, Songqing and Zhang, Feiping and Weng, Mingqing and Luo, Jianlong and Li, Xiaolin},
  title = {SS-OPDet: A Semi-Supervised Open-Set Detection Framework for Dead Pine Wood Detection},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25113407}
}
Kostenlos starten →