PGG Wrightson
SkyCount drone livestock counting
PGG Wrightson counts livestock by drone with about 97% accuracy first time
Problem
Traditional farm audits could take five or six staff off the road for a week. Mustering for a count can take up to a week on large properties.
Approach
With AI firm Inde, PGG Wrightson built SkyCount. Drones photograph animals on preset flight paths, an AI model trained on tens of thousands of images counts them, and Power Apps builds the audit report.
Results
Takeaway
One drone operator can run a count, and farmers review results in a few minutes. Microsoft reported accuracy at around 97% first time.
Categories
- Industry
- Agriculture and food production
- Business function
- Production and quality
- Innovation type
- Product and service innovation
- AI technology
- Computer vision
- Adoption
- Co-developed with a partner
- Evidence
- Vendor's case study
Sources
Source summaries
Microsoft's New Zealand newsroom describes the drone counting system built with Inde. It gives the accuracy figure and contrasts it with week-long manual audits.
Full details are in the original sources.