A probabilistic framework for nonlinear dimensionality reduction algorithms. The Twin Measures Framework is a novel platform for analysing existing dimensionality reduction methods and the invention of new ones. This research will radically improve image analysis, with beneficial applications from pharmaceutical drug design through to border protection.
Pattern-Based Video Coding Techniques for Real-Time Low Bit-Rate and Low Complexity Encoding Applications. This project will benefit the National Research Priority on Frontier Technology with applications in video surveillance, smart home design, and patient monitoring. It will enable Australia to lead the world in setting up coding standards and thus impact directly on the manufacturing initiatives of the multimedia communication and entertainment industries. Telecommunication industries will b ....Pattern-Based Video Coding Techniques for Real-Time Low Bit-Rate and Low Complexity Encoding Applications. This project will benefit the National Research Priority on Frontier Technology with applications in video surveillance, smart home design, and patient monitoring. It will enable Australia to lead the world in setting up coding standards and thus impact directly on the manufacturing initiatives of the multimedia communication and entertainment industries. Telecommunication industries will be the immediate beneficiary by enabling quality live video transmissions at low bit rates in a cost-effective manner. This project will improve the ability of large organisations to operate virtually across huge distances in Australia with the aid of reliable multimedia communications using distributed devices of limited power and processing capacity.Read moreRead less
Non-Parametric Modelling of Motion and Depth fields with Boundary Geometry for Scalable Compression and Dissemination. Applications for large format video surveillance are about to grow rapidly, starting with military applications and then moving into the civilian arena, highlighting the importance of compression for interactive dissemination, so as to make best use of limited communication channels. This project will develop an innovative representation for motion and depth/elevation maps, whi ....Non-Parametric Modelling of Motion and Depth fields with Boundary Geometry for Scalable Compression and Dissemination. Applications for large format video surveillance are about to grow rapidly, starting with military applications and then moving into the civilian arena, highlighting the importance of compression for interactive dissemination, so as to make best use of limited communication channels. This project will develop an innovative representation for motion and depth/elevation maps, which addresses a key obstacle in the deployment of technology for efficient interactive access to large format video and geospatial imagery. These applications are relevant to Australia's defence and infrastructure for smart information use. Moreover, this is a strategic proposal to strengthen Australia's existing lead in aspects of interactive media dissemination.Read moreRead less
Semantic Authentication of Visual Data. Data authentication systems can detect the smallest modification to a message. Authentication systems for media objects such as images, and audio and video clips have a different requirement they must ensure authenticity of the content without needing all the changes to be detectable. The aims of this project are to develop a framework for design and analysis of image and video authentication systems, and construct secure and flexible systems that can be ....Semantic Authentication of Visual Data. Data authentication systems can detect the smallest modification to a message. Authentication systems for media objects such as images, and audio and video clips have a different requirement they must ensure authenticity of the content without needing all the changes to be detectable. The aims of this project are to develop a framework for design and analysis of image and video authentication systems, and construct secure and flexible systems that can be used in practice. This research addresses the urgent need of providing security for multimedia objects in electronic commerce and is of high importance to the acceptance of advanced communication and information services.Read moreRead less
Highly Scalable Video Compression with Finely Embedded Motion Signalling. Highly scalable video compression is critical to the emergence of new applications in video distribution and management. Examples include interactive remote browsing of video and robust video surveillance over shared networks. Previous ARC funding produced fundamental breakthroughs in scalable video compression, resulting in a new paradigm which has been adopted by leading researchers in the field. The present project a ....Highly Scalable Video Compression with Finely Embedded Motion Signalling. Highly scalable video compression is critical to the emergence of new applications in video distribution and management. Examples include interactive remote browsing of video and robust video surveillance over shared networks. Previous ARC funding produced fundamental breakthroughs in scalable video compression, resulting in a new paradigm which has been adopted by leading researchers in the field. The present project addresses the two most important problems which currently limit the potential of this paradigm. Inspired by the applicant's recent discoveries, the outcomes of this project are likely to represent significant scientific breakthroughs and contribute to a new international video coding standard.Read moreRead less
Multi-Modal Dictionary Learning for Smart City Operation and Management. This Project aims to provide new digital asset management tools for city councils to improve city services by utilising new sensing and automated learning technologies for recognising, tracking and auditing of assets. Currently, there are no digital tools available to handle these services. This project proposes new multi-modal sensing and mapping of city asset techniques by building new multi-modal dictionary learning proc ....Multi-Modal Dictionary Learning for Smart City Operation and Management. This Project aims to provide new digital asset management tools for city councils to improve city services by utilising new sensing and automated learning technologies for recognising, tracking and auditing of assets. Currently, there are no digital tools available to handle these services. This project proposes new multi-modal sensing and mapping of city asset techniques by building new multi-modal dictionary learning procedures. The new framework will recognise different conditions of city assets in real-time to make decisions. Expected outcomes of this Project include integration and easy access of assets with unique digital identities to help city councils, governments, and navigation services for real-time asset monitoring.Read moreRead less
Assistive micro-navigation for vision impaired people. This project aims to develop novel algorithms to transform a simple camera into a smart sensor, that can enable a vision-impaired person to navigate freely and without additional aids in a crowded area. Such a smart sensor will be endowed with the capability to detect and locate obstacles, identify the walking path, recognise objects and traffic signs and convey step-by-step instructions to the user. The project outcomes are expected to impr ....Assistive micro-navigation for vision impaired people. This project aims to develop novel algorithms to transform a simple camera into a smart sensor, that can enable a vision-impaired person to navigate freely and without additional aids in a crowded area. Such a smart sensor will be endowed with the capability to detect and locate obstacles, identify the walking path, recognise objects and traffic signs and convey step-by-step instructions to the user. The project outcomes are expected to improve the well-being and accessibility to public areas for vision-impaired people and reduce physical access disparities for this disadvantaged and vulnerable group. Furthermore, technologies developed in this project can potentially be adapted for use in related special navigation applications such as road safety, self-driving vehicles, and autonomous robots.Read moreRead less
Dynamic Visual Scene Gist Recognition using a Probabilistic Inference Framework. How can we see the forest without intentionally looking for the trees? How can we tell traffic is flowing smoothly on a busy highway without identifying vehicles or measuring their speed? These are the questions that inspire this research project. Humans are endowed with the ability to grasp the ‘gist’ or overall meaning of a complex visual scene from a single glance and without attention to details. The aim of this ....Dynamic Visual Scene Gist Recognition using a Probabilistic Inference Framework. How can we see the forest without intentionally looking for the trees? How can we tell traffic is flowing smoothly on a busy highway without identifying vehicles or measuring their speed? These are the questions that inspire this research project. Humans are endowed with the ability to grasp the ‘gist’ or overall meaning of a complex visual scene from a single glance and without attention to details. The aim of this project is to develop new computational vision models that combine biological visual processing with probabilistic inference for gist recognition. The developed models will be able to mimic human vision by analysing a complex dynamic scene rapidly and classifying its semantic categories, without identifying individual objects.Read moreRead less
Extreme events: mining the radio sky for gamma-ray bursts with intelligent algorithms. Gamma-ray bursts and supernova explosions are some of the most extreme events in the Universe, and working out what causes them, and other transient phenomena, will give us new physical insights. The project will search, using next generation telescopes and intelligent algorithms, to find these 'needles in a haystack'.
Hybrid optimisation for automatic large-scale video annotation. Optimization is the basis for solving many problems in Computer Vision, such as three-dimensional geometry recovery, image segmentation, scene labeling and object recognition. This project will develop new optimisation techniques and demonstrate their suitability for large-scale video annotation, which is key to visual data mining and scene understanding.