EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Farmland pest recognition based on Cascade RCNN Combined with Swin-Transformer

Ruikang Xu iD, Jiajun Yu, Lening Ai, Haojie Yu, Zining Wei

PLOS ONE · 2024

DOI: 10.1371/journal.pone.0304284 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2024. Verfasst von Ruikang Xu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Mechanical and Electrical Engineering Department, Qingdao University of Technology, Linyi, Shandong, China. Hauptthemen laut MEDLINE: Algorithms. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Agricultural pests and diseases pose major losses to agricultural productivity, leading to significant economic losses and food safety risks. However, accurately identifying and controlling these pests is still very challenging due to the scarcity of labeling data for agricultural pests and the wide variety of pest species with different morphologies. To this end, we propose a two-stage target detection method that combines Cascade RCNN and Swin Transformer models. To address the scarcity of labeled data, we employ random cut-and-paste and traditional online enhancement techniques to expand the pest dataset and use Swin Transformer for basic feature extraction. Subsequently, we designed the SCF-FPN module to enhance the basic features to extract richer pest features. Specifically, the SCF component provides a self-attentive mechanism with a flexible sliding window to enable adaptive feature extraction based on different pest features. Meanwhile, the feature pyramid network (FPN) enriches multiple levels of features and enhances the discriminative ability of the whole network. Finally, to further improve our detection results, we incorporated non-maximum suppression (Soft NMS) and Cascade R-CNN’s cascade structure into the optimization process to ensure more accurate and reliable prediction results. In a detection task involving 28 pest species, our algorithm achieves 92.5%, 91.8%, and 93.7% precision in terms of accuracy, recall, and mean average precision (mAP), respectively, which is an improvement of 12.1%, 5.4%, and 7.6% compared to the original baseline model. The results demonstrate that our method can accurately identify and localize farmland pests, which can help improve farmland’s ecological environment.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsAnimalsAgriculturePest ControlNeural Networks, ComputerFarmsCrops, Agricultural

Autor:innen und Institutionen

  • Mechanical and Electrical Engineering Department, Qingdao University of Technology, Linyi, Shandong, China.
  • Management Engineering Department, Qingdao University of Technology, Linyi, Shandong, China.

ORCID-Profile: Ruikang Xu

Zitieren

APA

Xu, R., Yu, J., Ai, L., Yu, H., & Wei, Z. (2024). Farmland pest recognition based on Cascade RCNN Combined with Swin-Transformer. PLOS ONE. https://doi.org/10.1371/journal.pone.0304284

Vancouver

Xu R, Yu J, Ai L, Yu H, Wei Z. Farmland pest recognition based on Cascade RCNN Combined with Swin-Transformer. PLOS ONE. 2024. doi:10.1371/journal.pone.0304284

BibTeX
@article{Xu2024,
  author = {Xu, Ruikang and Yu, Jiajun and Ai, Lening and Yu, Haojie and Wei, Zining},
  title = {Farmland pest recognition based on Cascade RCNN Combined with Swin-Transformer},
  journal = {PLOS ONE},
  year = {2024},
  doi = {10.1371/journal.pone.0304284}
}
Kostenlos starten →