Back to Search
Start Over
DeepWeeds: A Multiclass Weed Species Image Dataset for Deep Learning
- Source :
- Scientific Reports, Vol 9, Iss 1, Pp 1-12 (2019), Scientific Reports
- Publication Year :
- 2019
- Publisher :
- Nature Publishing Group, 2019.
-
Abstract
- Robotic weed control has seen increased research of late with its potential for boosting productivity in agriculture. Majority of works focus on developing robotics for croplands, ignoring the weed management problems facing rangeland stock farmers. Perhaps the greatest obstacle to widespread uptake of robotic weed control is the robust classification of weed species in their natural environment. The unparalleled successes of deep learning make it an ideal candidate for recognising various weed species in the complex rangeland environment. This work contributes the first large, public, multiclass image dataset of weed species from the Australian rangelands; allowing for the development of robust classification methods to make robotic weed control viable. The DeepWeeds dataset consists of 17,509 labelled images of eight nationally significant weed species native to eight locations across northern Australia. This paper presents a baseline for classification performance on the dataset using the benchmark deep learning models, Inception-v3 and ResNet-50. These models achieved an average classification accuracy of 95.1% and 95.7%, respectively. We also demonstrate real time performance of the ResNet-50 architecture, with an average inference time of 53.4 ms per image. These strong results bode well for future field implementation of robotic weed control methods in the Australian rangelands.<br />Comment: 14 pages, 8 figures, 4 tables
- Subjects :
- 0301 basic medicine
Crops, Agricultural
FOS: Computer and information sciences
Computer Science - Machine Learning
Boosting (machine learning)
Computer science
Weed Control
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
lcsh:Medicine
Machine Learning (stat.ML)
Environment
Machine learning
computer.software_genre
Article
Machine Learning (cs.LG)
Machine Learning
03 medical and health sciences
0302 clinical medicine
Deep Learning
Statistics - Machine Learning
lcsh:Science
Multidisciplinary
business.industry
Deep learning
lcsh:R
Australia
Agriculture
Robotics
Weed control
030104 developmental biology
lcsh:Q
Artificial intelligence
Neural Networks, Computer
Rangeland
business
Weed
computer
030217 neurology & neurosurgery
Subjects
Details
- Language :
- English
- ISSN :
- 20452322
- Volume :
- 9
- Issue :
- 1
- Database :
- OpenAIRE
- Journal :
- Scientific Reports
- Accession number :
- edsair.doi.dedup.....9856fc61192ba1e0e6af22dc9f4692fd