EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Varroa Mite Counting Based on Hyperspectral Imaging

Amira Ghezal, Christian Jair Luis Peña, Andreas König

Sensors · 09.07.2024 · 24 (14) · 4437

DOI: 10.3390/s24144437 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 09.07.2024. Verfasst von Amira Ghezal und 2 weiteren Autor:innen. Beteiligte Einrichtung: Fachbereich Elektrotechnik und Informationstechnik, Lehrstuhl Kognitive Integrierte Sensorsysteme, RPTU Kaiserslautern, 67663 Kaiserslautern, Germany. Hauptthemen laut MEDLINE: Varroidae, Hyperspectral Imaging, Support Vector Machine, Principal Component Analysis. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: WIPOTEC, Kaiserslautern.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Varroa mite infestation poses a severe threat to honeybee colonies globally. This study investigates the feasibility of utilizing the HS-Cam and machine learning techniques for Varroa mite counting. The methodology involves image acquisition, dimensionality reduction through Principal Component Analysis (PCA), and machine learning-based segmentation and classification algorithms. Specifically, a k-Nearest Neighbors (kNNs) model distinguishes Varroa mites from other objects in the images, while a Support Vector Machine (SVM) classifier enhances shape detection. The final phase integrates a dedicated counting algorithm, leveraging outputs from the SVM classifier to quantify Varroa mite populations in hyperspectral images. The preliminary results demonstrate segmentation accuracy exceeding 99% and an average precision of 0.9983 and recall of 0.9947 across all the classes. The results obtained from our machine learning-based approach for Varroa mite counting were compared against ground-truth labels obtained through manual counting, demonstrating a high degree of agreement between the automated counting and manual ground truth. Despite working with a limited dataset, the HS-Cam showcases its potential for Varroa counting, delivering superior performance compared to traditional RGB images. Future research directions include validating the proposed hyperspectral imaging methodology with a more extensive and diverse dataset. Additionally, the effectiveness of using a near-infrared (NIR) excitation source for Varroa detection will be explored, along with assessing smartphone integration feasibility.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

VarroidaeHyperspectral ImagingSupport Vector MachinePrincipal Component AnalysisAlgorithmsAnimalsBeesImage Processing, Computer-AssistedMachine Learning

Stichwörter der Autor:innen

automated Varroa countinghyperspectral imagingsegmentationshape detection

Autor:innen und Institutionen

  • Fachbereich Elektrotechnik und Informationstechnik, Lehrstuhl Kognitive Integrierte Sensorsysteme, RPTU Kaiserslautern, 67663 Kaiserslautern, Germany.

Förderung

  • WIPOTEC, Kaiserslautern

Zitieren

APA

Ghezal, A., Peña, C. J. L., & König, A. (2024). Varroa Mite Counting Based on Hyperspectral Imaging. Sensors, 24(14), 4437. https://doi.org/10.3390/s24144437

Vancouver

Ghezal A, Peña CJL, König A. Varroa Mite Counting Based on Hyperspectral Imaging. Sensors. 2024;24(14):4437. doi:10.3390/s24144437

BibTeX
@article{Ghezal2024,
  author = {Ghezal, Amira and Peña, Christian Jair Luis and König, Andreas},
  title = {Varroa Mite Counting Based on Hyperspectral Imaging},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {14},
  pages = {4437},
  doi = {10.3390/s24144437}
}
Kostenlos starten →