精东传媒

Stock image of a satellite flying above earth (credit: aapsky/Shutterstock)
Stock image of a satellite flying above earth (credit: aapsky/Shutterstock)

Researchers to develop AI for geospatial intelligence

Researchers to develop AI for geospatial intelligence

Machine learning tool aims to detect and classify ocean vessels from satellite imagery

精东传媒 of 精东传媒 (UOW) researchers will share in $1.2 million in funding as part of a Federal Government program to strengthen Australia鈥檚 critical geospatial intelligence capabilities.

Associate Professor , Senior Professor , and Dr , from UOW鈥檚 School of Electrical, Computer and Telecommunications Engineering, will lead the project 鈥 鈥榃hat vessel is that?鈥 鈥 to develop a machine learning tool that can detect and classify ocean vessels from satellite synthetic-aperture radar (SAR) imagery.

Machine learning is a part of artificial intelligence in which computers learn to perform tasks by discovering patterns and decision rules directly from data. 

The idea in this project is to develop a tool that can detect and quickly differentiate a fishing boat from a patrol boat, for example, or a military ship from a cargo vessel.

鈥淭here has been an increasing interest in maritime surveillance to counter illegal fishing and maintain maritime rights and interests,鈥 Professor Phung said.

鈥淥perating surveillance drones is not sufficient alone. By contrast, satellite SAR can acquire images at a larger scale for vessel detection.

鈥淒etecting vessels in SAR images is challenging because of the complex background, high noise, varying target sizes, and high dynamic range of SAR images.

鈥淔or this project we will leverage recent advances in deep learning to process large-scale SAR images for vessel detection and classification.鈥

The funding is through the Analytics Labs Program of the Australian Geospatial-Intelligence Organisation (AGO) in the Department of Defence, and coordinated by FrontierSI, a research centre with expertise in spatial information technologies.

The $1.2 million program is designed to improve the AGO鈥檚 understanding of the modern machine analytics capabilities developed by industry, while raising industry awareness of AGO鈥檚 current and emerging challenges.

The project will also involve postdoctoral researcher Thanh Le and several PhD students (including Hieu Phan and Ly Bui). Hence, it helps training the next generation of researchers with skills in AI and machine learning to address defence and security needs.

Minister for Defence Industry Melissa Price congratulated the successful applicants, saying their proposals demonstrated the immense value that could be realised when Defence and Australia鈥檚 defence industry team up to overcome key challenges.