EUVIMEDSkopri EUVIMED
Crossref

Detection and coverage estimation of purple nutsedge in turf with image classification neural networks

Xiaojun Jin iD, Kang Han, Hua Zhao, Yan Wang, Yong Chen, Jialin Yu

Pest Management Science · 2024

DOI: 10.1002/ps.8055 ↗

At a glance

Journal article in Pest Management Science, 2024. Written by Xiaojun Jin and 5 co-authors. Institution: College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing, China. Major MEDLINE topics: Plant Weeds, Neural Networks, Computer. Cited 18 times so far (Crossref); 56 references. Funded by: Postgraduate Research & Practice Innovation Program of Jiangsu Province, National Natural Science Foundation of China, Taishan Scholars Program.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

BACKGROUND Accurate detection of weeds and estimation of their coverage is crucial for implementing precision herbicide applications. Deep learning (DL) techniques are typically used for weed detection and coverage estimation by analyzing information at the pixel or individual plant level, which requires a substantial amount of annotated data for training. This study aims to evaluate the effectiveness of using image‐classification neural networks (NNs) for detecting and estimating weed coverage in bermudagrass turf. RESULTS Weed‐detection NNs, including DenseNet, GoogLeNet and ResNet, exhibited high overall accuracy and F 1 scores (≥0.971) throughout the k ‐fold cross‐validation. DenseNet outperformed GoogLeNet and ResNet with the highest overall accuracy and F 1 scores (0.977). Among the evaluated NNs, DenseNet showed the highest overall accuracy and F 1 scores (0.996) in the validation and testing data sets for estimating weed coverage. The inference speed of ResNet was similar to that of GoogLeNet but noticeably faster than DenseNet. ResNet was the most efficient and accurate deep convolution neural network for weed detection and coverage estimation. CONCLUSION These results demonstrated that the developed NNs could effectively detect weeds and estimate their coverage in bermudagrass turf, allowing calculation of the herbicide requirements for variable‐rate herbicide applications. The proposed method can be employed in a machine vision‐based autonomous site‐specific spraying system of smart sprayers. © 2024 Society of Chemical Industry.

Subjects

MeSH terms (MEDLINE)

Plant WeedsNeural Networks, ComputerImage Processing, Computer-AssistedWeed ControlCynodonHerbicidesDeep Learning

Author keywords

deep learningprecision herbicide applicationweed detectionweed‐coverage estimation

Substances

Herbicides

Authors and institutions

  • College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing, China.
  • Peking University Institute of Advanced Agricultural Sciences/Shandong Laboratory of Advanced Agricultural Sciences at Weifang, Weifang, China.
  • School of Mechanical Engineering, Jiangsu Ocean University, Lianyungang, China.

ORCID profiles: Xiaojun Jin

Funding

  • Postgraduate Research & Practice Innovation Program of Jiangsu Province
  • National Natural Science Foundation of China
  • Taishan Scholars Program

Cite

APA

Jin, X., Han, K., Zhao, H., Wang, Y., Chen, Y., & Yu, J. (2024). Detection and coverage estimation of purple nutsedge in turf with image classification neural networks. Pest Management Science. https://doi.org/10.1002/ps.8055

Vancouver

Jin X, Han K, Zhao H, Wang Y, Chen Y, Yu J. Detection and coverage estimation of purple nutsedge in turf with image classification neural networks. Pest Management Science. 2024. doi:10.1002/ps.8055

BibTeX
@article{Jin2024,
  author = {Jin, Xiaojun and Han, Kang and Zhao, Hua and Wang, Yan and Chen, Yong and Yu, Jialin},
  title = {Detection and coverage estimation of purple nutsedge in turf with image classification neural networks},
  journal = {Pest Management Science},
  year = {2024},
  doi = {10.1002/ps.8055}
}
Start for free →