EUVIMEDEUVIMED entdecken
Crossref

Field evaluation of an agricultural weed detector using YOLO image recognition: background conditions affect detection performance

Saeko Matsuhashi iD, Ryo Sugiura, Motoaki Asai, Hidenori Asami, Yusuke Kowata, Yuki Akamatsu, Kozue Sasaki, Namiko Yoshino, Nozomi Ihara, Akira Koarai

Pest Management Science · 2025-10 · 81 (10) · 6560-6566

DOI: 10.1002/ps.70009 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pest Management Science, online erschienen am 18.06.2025. Verfasst von Saeko Matsuhashi und 9 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Plant Protection, NARO, Tsukuba, Japan. Hauptthemen laut MEDLINE: Plant Weeds, Weed Control, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 28 Literaturangaben. Gefördert von: a research project for technologies to strengthen the international competitiveness of Japan's agriculture and food industry.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND Image recognition tools for weed identification, such as smartphone applications, have the potential to enhance user knowledge, provide early invasive weed alerts, and enable site‐specific weed management. Although numerous studies have reported product development and model accuracy, few have evaluated these tools in practical environments beyond developmental settings. In this study, we developed a weed detector using the You Only Look Once (YOLO) v3 object detection algorithm to identify six noxious weed species. Specifically, we examined the effects of: (i) image collection locations, (ii) target backgrounds, and (iii) camera devices on detection accuracy, assessing applicability through field verification at 68 sites across Japan and controlled garden experiments. RESULTS Detection success was influenced by the background of the target species in images, with significant interaction effects observed between background and target species on detection outcomes. In the most affected combination (background: tray; species: Ipomoea lacunosa ), the average precision (AP) value decreased by ~0.2 compared with the other conditions. AP values in field tests were lower than those from test data resembling training data, with no correlation between AP values from test data sets and field verification. No clear effects of land use or camera devices on detection success were detected. CONCLUSION This study highlights the importance of background in image‐based weed detection and identifies limitations in detector applicability. Our findings are expected to support more‐efficient development and underscore the importance of sharing applicability data for improved weed detection tools. © 2025 Society of Chemical Industry.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Plant WeedsWeed ControlImage Processing, Computer-AssistedJapanAlgorithms

Stichwörter der Autor:innen

alien speciesartificial intelligencedeep learningobject detectionsite‐specific weed management

Autor:innen und Institutionen

  • Institute for Plant Protection, NARO, Tsukuba, Japan.
  • Research Center for Agricultural Information Technology, NARO, Memuro, Japan.
  • Institute for Plant Protection NARO, Fukushima, Japan.
  • Western Region Agricultural Research Center, NARO, Hiroshima, Japan.
  • Institute of Livestock and Grassland Science, NARO, Tochigi, Japan.

ORCID-Profile: Saeko Matsuhashi

Förderung

  • a research project for technologies to strengthen the international competitiveness of Japan's agriculture and food industry

Zitieren

APA

Matsuhashi, S., Sugiura, R., Asai, M., Asami, H., Kowata, Y., Akamatsu, Y., Sasaki, K., Yoshino, N., Ihara, N., & Koarai, A. (2025). Field evaluation of an agricultural weed detector using YOLO image recognition: background conditions affect detection performance. Pest Management Science, 81(10), 6560-6566. https://doi.org/10.1002/ps.70009

Vancouver

Matsuhashi S, Sugiura R, Asai M, Asami H, Kowata Y, Akamatsu Y, et al. Field evaluation of an agricultural weed detector using YOLO image recognition: background conditions affect detection performance. Pest Management Science. 2025;81(10):6560-6566. doi:10.1002/ps.70009

BibTeX
@article{Matsuhashi2025,
  author = {Matsuhashi, Saeko and Sugiura, Ryo and Asai, Motoaki and Asami, Hidenori and Kowata, Yusuke and Akamatsu, Yuki and Sasaki, Kozue and Yoshino, Namiko and Ihara, Nozomi and Koarai, Akira},
  title = {Field evaluation of an agricultural weed detector using YOLO image recognition: background conditions affect detection performance},
  journal = {Pest Management Science},
  year = {2025},
  volume = {81},
  number = {10},
  pages = {6560--6566},
  doi = {10.1002/ps.70009}
}
Kostenlos starten →