Controlling weeds, precisely. The latest in precision weed control research from the @Sydney_Uni Weeds Research Team in Narrabri and Camden.
Narrabri, New South Wales
Joined July 2018
- Tweets380
- Following256
- Followers1K
- Likes481
Pinned Tweet
The #OpenSpotSprayer is a low cost, opensource and simple approach to weed detection. It uses off the shelf items and simple colour-based code to pick out green weeds. Here it is mounted on the Digital Farm Hand robot @pbinarrabri.
Full code and guide released soon.
@SiaSydney
Precision Weed Control Lab retweeted
About 50 years ago, the tech behind reflectance-based 'green-on-brown' sprayers was published.
Since then a lot (!) has changed.
We went through ~175 papers from the last 50 years of weed recognition research for this review.
cambridge.org/core/journals/…
Precision Weed Control Lab retweeted
The OpenWeedLocator demo unit will be at the @MsfMallee Future of Weed Detection Expo in Karoonda next week.
A great opportunity to get hands on experience with how image-based weed detection works and DIY units.
@KMatthewson_22 @AgriFuturesAU
Precision Weed Control Lab retweeted
Just finished assembling the compact OWL or OWLet, after some great feedback during the @MingenewExpo.
Fits inside 125 x 75 x 3mm RHS steel for smash protection, same features as the big OWL.
Designs/assembly guide to follow!
Precision Weed Control Lab retweeted
This machine’s algorithm is capable of distinguishing between #BroadleafWeeds, #GrassWeeds, and #ginger with a great level of accuracy and is helping to detect and spray for #weeds in a ginger crop. To read more about this project, visit bit.ly/3o0cmJK
Precision Weed Control Lab retweeted
To pass the 100th commit🥳for the #OpenWeedLocator, we've released an improved image sampling tool. Now you can save whole images, cropped bounding boxes around the detections or cropped squares.
To collect images - just plug in a USB, set it up and go!
github.com/geezacoleman/Open…
Precision Weed Control Lab retweeted
Really enjoyed writing this article for @nozzle_guy and @Spray_Guy!
Check it out if you're interested in the tech behind camera sprayers, where it all started and how an #opensource approach will help it succeed.
@Sydney_Science @SiaSydney @WeedSmartAU
. @Spray_Guy and I are excited to have @GeezaColeman as a guest author on #Sprayers101 with his take on optical spot sprays and the evolution of the technology. A must read if you want to know how #MachineLearning works and fits into ag.
sprayers101.com/computers-an…
Precision Weed Control Lab retweeted
@GeezaColeman & @WeedAI_news are seeking growers to join a beta testing group for feedback user experience.
📷 All you need are the images to upload.
DM @GeezaColeman if you're interested in participating teapawt.net/GeezaColeman/s…
We're looking for growers to join a beta testing group @WeedAI_news, for feedback on the user experience - you'd just need to have images to annotate/upload.
We'll form an ongoing group around opensource weed recognition too.
Let me know if you're interested!
@HenryLydecker
Precision Weed Control Lab retweeted
We're looking for growers to join a beta testing group @WeedAI_news, for feedback on the user experience - you'd just need to have images to annotate/upload.
We'll form an ongoing group around opensource weed recognition too.
Let me know if you're interested!
@HenryLydecker
Precision Weed Control Lab retweeted
Great to see them go out to a good home👍🏼 one rig working and another 3 coming – at Dubbo, New South Wales
Weed-AI now hosts:
🗄 17 datasets, 20,891 images
🌾 8 crops + fallow
🌱 28 species + poaceae/broadleaf groups
🌏 datasets from: 🇦🇺🇩🇰🇦🇷🇺🇲
If you've got datasets of weeds or need data for a project, check out Weed-AI
weed-ai.sydney.edu.au
The first dataset with fireweed was just uploaded to @WeedAI_news!
A small dataset of fireweed at both vegetative and flowering growth stages collected with the Sony Alpha A7R IV A, providing 61MP per image.
Precision Weed Control Lab retweeted
The first dataset with fireweed was just uploaded to @WeedAI_news!
A small dataset of fireweed at both vegetative and flowering growth stages collected with the Sony Alpha A7R IV A, providing 61MP per image.
21/
Dataset name: Brownlow Hill Fireweed
Classes: 1 (Senecio madagascariensis)
Annotation type: bounding box
Image count: 20
weed-ai.sydney.edu.au/datase…
ALT Fireweed plant in green pasture
Precision Weed Control Lab retweeted
🚨🌱New dataset!
This 552 image dataset of wild radish in wheat is the first on @WeedAI_news that makes use of the new weed growth stage/plant part specification.
Plus Weed-AI now has dataset editing & version control functionality too.
@SiaSydney @Sydney_CRF
21/
Dataset name: RadishWheatDataset
Classes 4 (4 growth stages of R. raphanistrum in wheat)
Annotation type: bounding box
Image count: 552 (1012 boxes)
weed-ai.sydney.edu.au/datase…
Precision Weed Control Lab retweeted
Spot the difference:
One collected at 5km/h, the other at 30km/h, dust and all. Both with the #OpenWeedLocator software.
Precision Weed Control Lab retweeted
Had a great time giving this OWL assembly/demo with @williamtsalter & Gus!
Hopefully demonstrated the whole development process: parts to paddock.
Glad nothing too major went awry!
We’re about to start our OpenWeedLocator live assembly and demonstration with @GeezaColeman at the helm 🎥🎙
Precision Weed Control Lab retweeted
We’re about to start our OpenWeedLocator live assembly and demonstration with @GeezaColeman at the helm 🎥🎙 – at New South Wales, Australia
Precision Weed Control Lab retweeted
A university of OWLs, showing the changes in design since way back in 2019 when I first built an enclosure.
If you want to learn how to build an OWL & see a live demo, it's all happening on Wed May 4th, 12 - 1:30pm AEST.
Register here:
eventbrite.com.au/e/openweed…
@williamtsalter
Precision Weed Control Lab retweeted
weed-ai.sydney.edu.au/ is an open data platform that the Sydney Informatics Hub is building to enable R&D into computer vision methods to identify and control weeds. It's great to see new data coming into the system!
Precision Weed Control Lab retweeted
🚨🌱new dataset!
If you're interested in a project for broadleaf weed recognition in your lawn, this might be a good place to start.
567 instances of weeds (rather unbalanced)
78 images
Perfect to get a YOLOv5 model up and running.
20/
Dataset name: Broadleaf Weeds in Common Couch
Classes: 3 (T. officinale, E. bonariensis, S. oleraceus)
Annotation type: bounding box
Image count: 78
weed-ai.sydney.edu.au/datase…
Precision Weed Control Lab retweeted
Images are everything in #deeplearning!
E.g. #ImageNet has >14 M images in 20k classes. Nothing of the same scale exists for weeds (@WeedAI_news is trying!) but there are open datasets.
For weed recognition, here's a 🧵of all weeds datasets I've found.
📸🌱🧵
🚨 New publication 🚨
Michael Walsh & @SBPowles look at the role of harvest weed seed control in Australian grain production systems.
What does it mean for weed recognition?
Read the full paper here or summary below from @WeedSmartAU
@SiaSydney
publish.csiro.au/CP/pdf/CP21…
HWSC gurus @SBPowles and Michael Walsh summarised 30 years of harvest weed seed control research and innovation in their latest paper 🚜
Find out more about the impact of HWSC and what improves its efficacy in our science review ➡️ buff.ly/35RG2n3
