EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DaylilyNet: A Multi-Task Learning Method for Daylily Leaf Disease Detection

Zishen Song, Dong Wang, Lizhong Xiao, Yongjian Zhu, Guogang Cao, Yuli Wang

Sensors · 2023

DOI: 10.3390/s23187879 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Zishen Song und 5 weiteren Autor:innen. Beteiligte Einrichtung: Shanghai Institute of Technology, College of Computer Science and Information Engineering, Shanghai 201418, China. Hauptthemen laut MEDLINE: Hemerocallis. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanghai Municipal Natural Science Foundation, Collaborative innovation fund of Shanghai Institute of Technology, University-Industry Collaborative Education Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Timely detection and management of daylily diseases are crucial to prevent yield reduction. However, detection models often struggle with handling the interference of complex backgrounds, leading to low accuracy, especially in detecting small targets. To address this problem, we propose DaylilyNet, an object detection algorithm that uses multi-task learning to optimize the detection process. By incorporating a semantic segmentation loss function, the model focuses its attention on diseased leaf regions, while a spatial global feature extractor enhances interactions between leaf and background areas. Additionally, a feature alignment module improves localization accuracy by mitigating feature misalignment. To investigate the impact of information loss on model detection performance, we created two datasets. One dataset, referred to as the ‘sliding window dataset’, was obtained by splitting the original-resolution images using a sliding window. The other dataset, known as the ‘non-sliding window dataset’, was obtained by downsampling the images. Experimental results in the ‘sliding window dataset’ and the ‘non-sliding window dataset’ demonstrate that DaylilyNet outperforms YOLOv5-L in mAP@0.5 by 5.2% and 4.0%, while reducing parameters and time cost. Compared to other models, our model maintains an advantage even in scenarios where there is missing information in the training dataset.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

HemerocallisAlgorithmsLearningMaintenancePlant Leaves

Stichwörter der Autor:innen

complex background interferencedaylily disease detectionmulti-task learning

Autor:innen und Institutionen

  • Shanghai Institute of Technology, College of Computer Science and Information Engineering, Shanghai 201418, China.
  • Ningbo Minjie Information Technology Co., Ltd., Ningbo 315040, China.

Förderung

  • Shanghai Municipal Natural Science Foundation
  • Collaborative innovation fund of Shanghai Institute of Technology
  • University-Industry Collaborative Education Program
  • Scientific start-up research project of Shanghai Institute of Technology
  • Scientific Start-Up Research Project of the Shanghai Institute of Technology
  • University–Industry Collaborative Education Program

Zitieren

APA

Song, Z., Wang, D., Xiao, L., Zhu, Y., Cao, G., & Wang, Y. (2023). DaylilyNet: A Multi-Task Learning Method for Daylily Leaf Disease Detection. Sensors. https://doi.org/10.3390/s23187879

Vancouver

Song Z, Wang D, Xiao L, Zhu Y, Cao G, Wang Y. DaylilyNet: A Multi-Task Learning Method for Daylily Leaf Disease Detection. Sensors. 2023. doi:10.3390/s23187879

BibTeX
@article{Song2023,
  author = {Song, Zishen and Wang, Dong and Xiao, Lizhong and Zhu, Yongjian and Cao, Guogang and Wang, Yuli},
  title = {DaylilyNet: A Multi-Task Learning Method for Daylily Leaf Disease Detection},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23187879}
}
Kostenlos starten →