Evaluation of two deep learning‐based approaches for detecting weeds growing in cabbage
Pest Management Science · 2024-06 · 80 (6) · 2817-2826
DOI: 10.1002/ps.7990 ↗Kurz gefasst
Evaluationsstudie in der Zeitschrift Pest Management Science, online erschienen am 07.02.2024. Verfasst von Hu Sun und 4 weiteren Autor:innen. Beteiligte Einrichtung: Shandong Provincial University Laboratory for Protected Horticulture, Weifang University of Science and Technology, Weifang, China. Hauptthemen laut MEDLINE: Deep Learning, Brassica, Plant Weeds, Weed Control. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 74 Literaturangaben. Gefördert von: Taishan Scholars Program, National Natural Science Foundation of China.
Abstract (Originalsprache)
BACKGROUND Machine vision‐based precision weed management is a promising solution to substantially reduce herbicide input and weed control cost. The objective of this research was to compare two different deep learning‐based approaches for detecting weeds in cabbage: (1) detecting weeds directly, and (2) detecting crops by generating the bounding boxes covering the crops and any green pixels outside the bounding boxes were deemed as weeds. RESULTS The precision, recall, F1‐score, mAP 0.5 , mAP0 .5:0.95 of You Only Look Once (YOLO) v5 for detecting cabbage were 0.986, 0.979, 0.982, 0.995, and 0.851, respectively, while these metrics were 0.973, 0.985, 0.979, 0.993, and 0.906 for YOLOv8, respectively. However, none of these metrics exceeded 0.891 when detecting weeds. The reduced performances for directly detecting weeds could be attributed to the diverse weed species at varying densities and growth stages with different plant morphologies. A segmentation procedure demonstrated its effectiveness for extracting weeds outside the bounding boxes covering the crops, and thereby realizing effective indirect weed detection. CONCLUSION The indirect weed detection approach demands less manpower as the need for constructing a large training dataset containing a variety of weed species is unnecessary. However, in a certain case, weeds are likely to remain undetected due to their growth in close proximity with crops and being situated within the predicted bounding boxes that encompass the crops. The models generated in this research can be used in conjunction with the machine vision subsystem of a smart sprayer or mechanical weeder. © 2024 Society of Chemical Industry.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Shandong Provincial University Laboratory for Protected Horticulture, Weifang University of Science and Technology, Weifang, China.
- Peking University Institute of Advanced Agricultural Sciences/Shandong Laboratory of Advanced Agricultural Sciences at Weifang, Weifang, China.
ORCID-Profile: Teng Liu
Förderung
- Taishan Scholars Program
- National Natural Science Foundation of China
Zitieren
APA
Sun, H., Liu, T., Wang, J., Zhai, D., & Yu, J. (2024). Evaluation of two deep learning‐based approaches for detecting weeds growing in cabbage. Pest Management Science, 80(6), 2817-2826. https://doi.org/10.1002/ps.7990
Vancouver
Sun H, Liu T, Wang J, Zhai D, Yu J. Evaluation of two deep learning‐based approaches for detecting weeds growing in cabbage. Pest Management Science. 2024;80(6):2817-2826. doi:10.1002/ps.7990
BibTeX
@article{Sun2024,
author = {Sun, Hu and Liu, Teng and Wang, Jinxu and Zhai, Danlan and Yu, Jialin},
title = {Evaluation of two deep learning‐based approaches for detecting weeds growing in cabbage},
journal = {Pest Management Science},
year = {2024},
volume = {80},
number = {6},
pages = {2817--2826},
doi = {10.1002/ps.7990}
}
EUVIMED