Despite having more coral species than the Great Barrier Reef, the waters from Darwin are under threat of growing species, overestimation and climate change.
In an attempt to better control and monitor fish populations in Darwin Harbor's infested infested waters, the Territorial government of North Wales automated the process by feeding pieces of bum cameras into an artificial intelligence platform.
Scientists from the Department of Primary and Resources Industry (DPIR) turned to GitHub and Microsoft Cognitive Services to develop the open source AI solution, spending tens of hours identifying fish species that swam into opinion the cameras to train the machine's learning program behind the stage.
The first re-address of the system ran within one month, and in the next six months of development and use, its abilities were identified to be gradually improved to the point in which the AI can now recognize fish with accuracy between 95 to 99 percent.
The speed of fish identification has also been given to the point in which the AI can analyze the hours of video in minutes, releasing DPIR scientists for more valuable ecosystem management.
DPIR fishery scientist, Dr Shane Penny, said that the system allows them to look at species that are at risk of over-trading, such as the gold war and black jewelery, and better tailor conservation efforts.
"These are two important commercial and recreational species in North Territory, but research has proven that they have been overwhelmed around the Darwin area," says Penny.
DPIR's chief information officer Rowan Dollar is already keen to expand the program based on her early success, including the monitoring of wild fish in freshwater systems and the provision of commercial boats with cameras.
"We could look into the installation of a camera on an off-shore subterranean and to identify the holding on the vehicle, so we can start measuring subtraction. We can start to identify that in real time, to help control better fisheries, "said Dollar.
Other fisheries around the world could also adopt the system, which has been uploaded to GitHub, to manage fisheries stock in different environments.
In North Territory alone, the value generated by primary industries, including fisheries, reaches more than half billion dollars a year.
The demand for NT marine resources is expected to grow with global trends, where fish consumption has increased by 3.2 per cent per year according to the United Nations report in 2018.
Other state environmental agencies also look at machinery vision solutions to manage sensitive ecosystems, including Queensland Agriculture and Fisheries Department that traces invasive plant species in connection with QUT.