AI Case Study
The Northern Territory Department of Primary Industry and Resources achieves 95% accuracy identifying fish with machine learning
Australia's Northern Territory Department of Primary Industry and Resources has implemented machine learning to automate the counting of fish and other sea life by analysing underwater footage. The system has achieved 95-99% success rate in identifying fish.
Public And Social Sector
"The Northern Territory Department of Primary Industry and Resources (DPIR) has turned to artificial intelligence (AI) to speed up its fish-counting exercises. Developed with Microsoft and built on Azure Cognitive Service, the open-source solution is published on GitHub, and had its first iteration running in a month. DPIR said the solution has already shown that the local golden snapper and black jewfish are overfished, and that the solution could be applied elsewhere across the territory."
The system now "can now identify fish with a 95 to 99 percent success rate" after being "widely deployed within six months".
Details not disclosed
Fish counting "used to be completed by DPIR [Department of Primary Industry and Resources] scientists watching hours of underwater footage filmed on reefs around Darwin... The scientists could not enter the water themselves, thanks to saltwater crocodiles and sharks not being completely onside with the idea of humans entering water."
Underwater footage of fish and other aquatic life