Gå offline med appen Player FM !
Deep learning can tell the difference between white and blue lupins
Manage episode 370994628 series 1313805
Blue lupins are notorious for being difficult to control and plants produce prolific seed banks.
Blue lupins are closely related to the domesticated narrow-leaf lupin, also known as the white lupin, so whichever herbicide is survived by white lupins is also survived by blue lupins. This is problematic as they look alike.
This is where a team of researchers from AHRI and the Centre for Applied Bioinformatics at the University of Western Australia, led by UWA PhD candidate and Forrest Research Scholar, Monica Danilevicz comes in.
The team has recently taken the approach of using weed labelling and deep learning algorithms to see if they can distinguish between the two lupin species in images captured by unmanned aerial vehicles, known as UAVs, like drones, or ground-based cameras.
The aim is to detect and spray just the blue lupins in crop. Monica explains the results further in this chat.
Links
- Paper: Segmentation of Sandplain Lupin Weeds from Morphologically Similar Narrow-Leafed Lupins in the Field
- Code repository
- Image repository
- Centre for Applied Bioinformatics
- Follow Monica on Twitter here
- Github
- You can also read more about the research in the AHRI insight here
You can follow AHRI on Twitter here. To learn more about AHRI's research and team, check out the website here.
137 episoder
Manage episode 370994628 series 1313805
Blue lupins are notorious for being difficult to control and plants produce prolific seed banks.
Blue lupins are closely related to the domesticated narrow-leaf lupin, also known as the white lupin, so whichever herbicide is survived by white lupins is also survived by blue lupins. This is problematic as they look alike.
This is where a team of researchers from AHRI and the Centre for Applied Bioinformatics at the University of Western Australia, led by UWA PhD candidate and Forrest Research Scholar, Monica Danilevicz comes in.
The team has recently taken the approach of using weed labelling and deep learning algorithms to see if they can distinguish between the two lupin species in images captured by unmanned aerial vehicles, known as UAVs, like drones, or ground-based cameras.
The aim is to detect and spray just the blue lupins in crop. Monica explains the results further in this chat.
Links
- Paper: Segmentation of Sandplain Lupin Weeds from Morphologically Similar Narrow-Leafed Lupins in the Field
- Code repository
- Image repository
- Centre for Applied Bioinformatics
- Follow Monica on Twitter here
- Github
- You can also read more about the research in the AHRI insight here
You can follow AHRI on Twitter here. To learn more about AHRI's research and team, check out the website here.
137 episoder
Alle episoder
×1 Dr Juan Vorster talks about herbicide resistance challenges in South Africa 8:50
1 Hot spot on goosegrass genome is a herbicide resistance generator 7:52
1 Deep learning can tell the difference between white and blue lupins 15:25
1 Testing water quality for effective spray application 14:18
1 How scientists are studying summer weeds to predict and mitigate future resistance 18:09
1 Cinmethylin couldn't be broken, but diversity is key to keeping it that way 9:32
1 Dr Aimone Porri talks on AHRI collaboration and his recent work on PPO mutations 14:23
1 The benefits of 3D mapping soil moisture 14:49
1 Professor Steve Duke talks on upcoming Herbicide Discovery and Development conference 14:54
1 Incoming Director Ken Flower shares his vision for AHRI 13:39
1 Don't stop thinkin' bout tomorrow when it comes to weeds, disease and insect control 6:47
1 Why highly glyphosate resistant plants can’t compete 12:41
1 Velocity® resistant wild radish confirmed 16:21
Velkommen til Player FM!
Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.