Authors: Madeleine Darbyshire, Shaun Coutts, Eleanor Hammond, Fazilet Gokbudak, Cengiz Oztireli, Petra Bosilj, Junfeng Gao, Elizabeth Sklar, Simon Parsons
Published on: May 03, 2024
Impact Score: 8.4
Arxiv code: Arxiv:2405.02218
Summary
- What is new: Evaluates the effectiveness of machine vision and multispectral imaging in identifying blackgrass in wheat and barley, using a large new dataset.
- Why this is important: Herbicide resistance and environmental harm from excessive herbicide use require new weed management strategies.
- What the research proposes: Using machine vision and multispectral imaging to identify blackgrass, a major weed, in cereal crops.
- Results: Achieved nearly 90% accuracy in identifying blackgrass in images from unseen fields with a modest amount of training data.
Technical Details
Technological frameworks used: nan
Models used: CNN and transformer-based architectures
Data used: A large dataset of images for blackgrass weed recognition
Potential Impact
Agricultural sector, herbicide manufacturers, cereal crop producers, and agri-tech companies
Want to implement this idea in a business?
We have generated a startup concept here: AgriSpectra.
Leave a Reply