Leveraging 3D computer vision for camera-based precise geo-localisation. This project aims to develop advanced 3D computer vision and image processing technology that can turn regular cameras into high-precision location-sensing devices. Spatial Location is a fundamental type of information of our physical world. Determining the precise location of people, vehicle, and mobile devices is essential for many critical applications. Outcomes of the project will enable a wide range of novel applicatio ....Leveraging 3D computer vision for camera-based precise geo-localisation. This project aims to develop advanced 3D computer vision and image processing technology that can turn regular cameras into high-precision location-sensing devices. Spatial Location is a fundamental type of information of our physical world. Determining the precise location of people, vehicle, and mobile devices is essential for many critical applications. Outcomes of the project will enable a wide range of novel applications of significant social, environmental and economic value, such as Location-Aware Service, Environment Monitoring, Augmented Reality, Autonomous Vehicle, and Rapid Emergency Response. The project will enhance Australia's international competitive advantage in forefront of ICT research and technology innovation.Read moreRead less
Combining new synthetic biology tools to boost crop CO2 capture and growth. A solution for improving crop yield is to enhance the carbon dioxide fixation properties of the enzyme Rubisco whose inefficient activity often limits plant growth. This project makes use of new synthetic biology capabilities to artificially evolve Rubisco in the laboratory and select for new versions with improved performance. These beneficial changes will be introduced into crop Rubisco using targeted gene editing appr ....Combining new synthetic biology tools to boost crop CO2 capture and growth. A solution for improving crop yield is to enhance the carbon dioxide fixation properties of the enzyme Rubisco whose inefficient activity often limits plant growth. This project makes use of new synthetic biology capabilities to artificially evolve Rubisco in the laboratory and select for new versions with improved performance. These beneficial changes will be introduced into crop Rubisco using targeted gene editing approaches and the improvements in photosynthesis, growth and yield evaluated. This information will aid complimentary biotechnological efforts seeking to supercharge photosynthesis and help deliver the second Green Revolution needed to meet the improvement required in future agriculture productivity and resource use.Read moreRead less
Nano-reactors: Protein cages as reusable scaffolds for designer enzymes. This project aims to develop robust protein cages derived from the coats of viruses to contain heat-stable P450 enzymes, for use as specialised protein bio-catalysts in chemical industries. A valuable chemical precursor of renewable bio-plastics will be produced from seed oils by enzymes, reducing the use of fossil fuels. This synthetic biology approach combines biotechnology, nanotechnology and protein engineering to estab ....Nano-reactors: Protein cages as reusable scaffolds for designer enzymes. This project aims to develop robust protein cages derived from the coats of viruses to contain heat-stable P450 enzymes, for use as specialised protein bio-catalysts in chemical industries. A valuable chemical precursor of renewable bio-plastics will be produced from seed oils by enzymes, reducing the use of fossil fuels. This synthetic biology approach combines biotechnology, nanotechnology and protein engineering to establish a plant-based platform biotechnology for using enzymes as catalysts to make high-value molecules. The project aims to show how to engineer clean, sustainable chemistry in designer nano-environments. This should make synthetic processes more sustainable and enhance advanced chemical manufacturing in Australia.Read moreRead less
Automatic Training Data Search and Model Evaluation by Measuring Domain Gap. We aim to investigate computer vision training data and test data, using automatically generated data sets for facial expression recognition and object re-identification. This project expects to quantify and understand the domain gap, the distribution difference between training and test data sets. Expected outcomes of this project are insights on measuring the domain gap, the ability to estimate model performance witho ....Automatic Training Data Search and Model Evaluation by Measuring Domain Gap. We aim to investigate computer vision training data and test data, using automatically generated data sets for facial expression recognition and object re-identification. This project expects to quantify and understand the domain gap, the distribution difference between training and test data sets. Expected outcomes of this project are insights on measuring the domain gap, the ability to estimate model performance without accessing expensive test labels and improvements to system generalisation. This should provide significant benefits for computer vision applications that currently require expensive labelling, and commercial and economic benefits across sectors such as transportation, security and manufacturing.Read moreRead less
Partially Observable MDPs, Monte Carlo Methods, and Sustainable Fisheries. Partially Observable Markov Decision Processes (POMDPs) provide a general mathematical framework for sequential decision making under uncertainty. However, solving POMDPs effectively under realistic assumptions remains a challenging problem. This project aims to develop new efficient Monte Carlo algorithms to significantly advance the application of POMDPs to real-world decision problems involving complex action spaces an ....Partially Observable MDPs, Monte Carlo Methods, and Sustainable Fisheries. Partially Observable Markov Decision Processes (POMDPs) provide a general mathematical framework for sequential decision making under uncertainty. However, solving POMDPs effectively under realistic assumptions remains a challenging problem. This project aims to develop new efficient Monte Carlo algorithms to significantly advance the application of POMDPs to real-world decision problems involving complex action spaces and system dynamics. Both theoretical and algorithmic approaches will be applied to sustainable fishery management --- an important problem for Australia and an ideal context for POMDPs. The project will advance research in artificial intelligence, dynamical systems, and fishery operations, and benefit the national economy.Read moreRead less
Two-way Auslan: Automatic Machine Translation of Australian Sign Language. This project aims to develop an automatic two-way machine-translation system between Auslan (Australian Sign Language) and English by researching and leveraging advanced computer vision and machine learning technology. The project expects to advance research in AI technology on topics including visual recognition, language processing and deep learning. This will boost Australia's national research capacity and global com ....Two-way Auslan: Automatic Machine Translation of Australian Sign Language. This project aims to develop an automatic two-way machine-translation system between Auslan (Australian Sign Language) and English by researching and leveraging advanced computer vision and machine learning technology. The project expects to advance research in AI technology on topics including visual recognition, language processing and deep learning. This will boost Australia's national research capacity and global competitiveness. Expected outcomes of this project will help to break the communication barriers between the Deaf and hearing population. This should provide significant benefits to Deaf communities through enhanced communication and improved quality-of-life, leading to a fair, more inclusive and resilient Australian society.Read moreRead less
Personalised Learning for Per-pixel Prediction Tasks in Image Analysis. AI-assisted image segmentation & synthesis are very challenging and usually require pixel-level labelling (per-pixel prediction) that is costly to obtain. The small amount of labels makes it difficult to train an “optimal” unified model for varied data as conventional methods did. This project aims to develop a new paradigm “personalised learning” to tackle this problem, where each image could be dealt with a model tailored ....Personalised Learning for Per-pixel Prediction Tasks in Image Analysis. AI-assisted image segmentation & synthesis are very challenging and usually require pixel-level labelling (per-pixel prediction) that is costly to obtain. The small amount of labels makes it difficult to train an “optimal” unified model for varied data as conventional methods did. This project aims to develop a new paradigm “personalised learning” to tackle this problem, where each image could be dealt with a model tailored to individual characteristics. The success of this project could significantly advance the fundamental research in image analysis. Expected outcomes include new knowledge and algorithms for image analysis, which could benefit fields like biology and archaeology, where labeled images are hard to attain and scarce.Read moreRead less
Human-Unmanned Aerial Vehicle interactions: Making drones talk and listen. This project aims to develop audio technology to enable unmanned aerial vehicles or drones to hear, use speech and sound to communicate with humans, acoustically sense their surroundings and make them less noisy. This project expects to generate new knowledge in acoustic signal processing and its application in drones using innovative approaches, such as use of miniature microphone and loudspeaker arrays, and active noise ....Human-Unmanned Aerial Vehicle interactions: Making drones talk and listen. This project aims to develop audio technology to enable unmanned aerial vehicles or drones to hear, use speech and sound to communicate with humans, acoustically sense their surroundings and make them less noisy. This project expects to generate new knowledge in acoustic signal processing and its application in drones using innovative approaches, such as use of miniature microphone and loudspeaker arrays, and active noise control. Expected outcomes include development of new theories, Intellectual Property, with potential commercial value, and training of next generation researchers. This should provide significant benefits with applications in life saving, search and rescue operations, transportation of goods, and creation of 3D media.Read moreRead less
Ultra-reliable and low-latency mission critical communications. This project aims to develop enabling technologies for ultra-reliable and low-latency communications. While the evolution of wireless communication technologies to date has focused on data rate improvement, very little is known on how to achieve ultra-reliability and almost-zero latency which is urgently required for mission critical applications such as smart manufacturing and intelligent vehicles. The outcomes of the project will ....Ultra-reliable and low-latency mission critical communications. This project aims to develop enabling technologies for ultra-reliable and low-latency communications. While the evolution of wireless communication technologies to date has focused on data rate improvement, very little is known on how to achieve ultra-reliability and almost-zero latency which is urgently required for mission critical applications such as smart manufacturing and intelligent vehicles. The outcomes of the project will be new analytical tools and practical guidelines for designing trusted communication platforms to realise these applications, with benefits ranging from improved safety in intelligent transportation systems to digital transformation of the manufacturing industry.Read moreRead less
Uncertainty, Risk and Related Concepts in Machine Learning. Machine learning is the science of making sense of data. It does not and cannot remove all risk and uncertainty. This project proposes to study the foundations of how machine learning uses, represents and communicates risk and uncertainty. It aims to do so by finding new theoretical connections between diverse notions that have arisen in allied disciplines. These include risk, uncertainty, scoring rules and loss functions, divergences, ....Uncertainty, Risk and Related Concepts in Machine Learning. Machine learning is the science of making sense of data. It does not and cannot remove all risk and uncertainty. This project proposes to study the foundations of how machine learning uses, represents and communicates risk and uncertainty. It aims to do so by finding new theoretical connections between diverse notions that have arisen in allied disciplines. These include risk, uncertainty, scoring rules and loss functions, divergences, statistics and different ways of aggregating information. By building a more complete theoretical map it is expected that new machine learning methods will be developed, but more importantly that machine learning will be able to be better integrated into larger socio-technical systems.Read moreRead less