Journal
PEST MANAGEMENT SCIENCE
Volume 78, Issue 2, Pages 521-529Publisher
JOHN WILEY & SONS LTD
DOI: 10.1002/ps.6656
Keywords
artificial intelligence; deep learning; machine learning; digital agriculture; site-specific weed management
Categories
Funding
- National Natural Science Foundation of China [32072498]
Ask authors/readers for more resources
CenterNet, Faster R-CNN, TridentNet, VFNet, and YOLOv3 were found to be insufficient for weed detection in wheat, while AlexNet, DenseNet, ResNet, and VGGNet trained with a large dataset were highly effective in detecting broadleaf weed seedlings in wheat.
BACKGROUND In-field weed detection in wheat (Triticum aestivum L.) is challenging due to the occurrence of weeds in close proximity with the crop. The objective of this research was to evaluate the feasibility of using deep convolutional neural networks for detecting broadleaf weed seedlings growing in wheat. RESULTS The object detection neural networks, including CenterNet, Faster R-CNN, TridenNet, VFNet, and You Only Look Once Version 3 (YOLOv3) were insufficient for weed detection in wheat because the recall never exceeded 0.58 in the testing dataset. The image classification neural networks including AlexNet, DenseNet, ResNet, and VGGNet were trained with small (5500 negative and 5500 positive images) or large training datasets (11 000 negative and 11 000 positive images) and three training image sizes (200 x 200, 300 x 300, and 400 x 400 pixels). For the small training dataset, increasing image sizes decreased the F1 scores of AlexNet and VGGNet but generally increased the F1 scores of DenseNet and ResNet. For the large training dataset, no obvious difference was detected between the training image sizes since all neural networks exhibited remarkable classification accuracies with high F1 scores (>= 0.96). All image classification neural networks exhibited high F1 scores (>= 0.99) when trained with the large training dataset and the training images of 200 x 200 pixels. CONCLUSION CenterNet, Faster R-CNN, TridentNet, VFNet, and YOLOv3 were insufficient, while AlexNet, DenseNet, ResNet, and VGGNet trained with a large training dataset were highly effective for detection of broadleaf weed seedlings in wheat.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available