A New Paradigm for the Representation and Distribution of High Dimensional Multimedia Content. The proposed project involves cutting edge research in a field of great international significance. The most obvious benefits will be international acclaim and the potential to patent, develop and ultimately export technology and systems for the distribution of high dimensional multimedia content. Outcomes from the project may support the growth of surveillance and networking equipment industries wit ....A New Paradigm for the Representation and Distribution of High Dimensional Multimedia Content. The proposed project involves cutting edge research in a field of great international significance. The most obvious benefits will be international acclaim and the potential to patent, develop and ultimately export technology and systems for the distribution of high dimensional multimedia content. Outcomes from the project may support the growth of surveillance and networking equipment industries within Australia. One application considered explicitly within the project is the demonstration of a new surveillance oriented approach to both distance education and pre-recorded educational content, based upon dense multimedia sampling and our proposed paradigm for efficient distribution to interactive clients.Read moreRead less
Video plasticity: Scalable video coding with inherently consistent motion. This project aims to improve how video coders represent motion, leading to more efficient motion descriptions and fewer distinct motion fields. The project will develop motion inference algorithms that ensure consistent motion descriptions throughout a group of pictures, allowing seamless integration of scalable video coding, motion compensated temporal filtering and motion compensated frame interpolation operations. The ....Video plasticity: Scalable video coding with inherently consistent motion. This project aims to improve how video coders represent motion, leading to more efficient motion descriptions and fewer distinct motion fields. The project will develop motion inference algorithms that ensure consistent motion descriptions throughout a group of pictures, allowing seamless integration of scalable video coding, motion compensated temporal filtering and motion compensated frame interpolation operations. The project is expected to support an efficient and interactive video browsing experience, largely decoupled from original frame rate and resolution; and deliver practical solutions that can be efficiently implemented on consumer devices.Read moreRead less
Smart CMOS Vision Sensors in Deep Sub-0.25um CMOS Technologies. This research project aims to develop a new generation of smart vision sensors featuring on-chip and pixel-level implementation of human vision based algorithms. Built in state-of-the-art deep sub-0.25um CMOS technologies, these imagers will feature extensive in-pixel processing power in contrast to the currently commercially available CMOS vision sensors. This will enable on-chip vision-based decision making but also increased on-c ....Smart CMOS Vision Sensors in Deep Sub-0.25um CMOS Technologies. This research project aims to develop a new generation of smart vision sensors featuring on-chip and pixel-level implementation of human vision based algorithms. Built in state-of-the-art deep sub-0.25um CMOS technologies, these imagers will feature extensive in-pixel processing power in contrast to the currently commercially available CMOS vision sensors. This will enable on-chip vision-based decision making but also increased on-chip image processing. These innovative system-on-chip features will contribute towards the positioning of CMOS imaging technology as the technology of choice for most digital imaging applications, in place of the existing, and so far unchallenged, CCD technology.
Read moreRead less
Interactive and scalable media over software defined networks. A novel API and associated algorithms will be developed to exploit the emerging technology of software defined networks (SDN) for improving the efficiency and responsiveness of interactive media browsing applications. The approach applies to conventional streaming video as well as more interactive services based on scalable media compression and communication technology, notably JPIP (IS15444-9) video. Recent advances in motion codin ....Interactive and scalable media over software defined networks. A novel API and associated algorithms will be developed to exploit the emerging technology of software defined networks (SDN) for improving the efficiency and responsiveness of interactive media browsing applications. The approach applies to conventional streaming video as well as more interactive services based on scalable media compression and communication technology, notably JPIP (IS15444-9) video. Recent advances in motion coding will be combined with new spatio-temporal transforms to develop an efficient inter-frame extension to the JPEG 2000 standard that is fully compatible with JPIP. Each of these innovations is important in its own right, but together they will facilitate a highly compelling interactive media browsing experience.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
Statistical Methods of Model Fitting and Segmentation in Computer Vision. Electronic sensors such as cameras and lasers can provide a rich source of information about the position, shape, and motion of objects around us. However, to extract this information in a reliable, automatic, and accurate way requires a sophisticated statistical theory of the process. Example applications include: video surveillance (better automatic detection of moving people and vehicles and of characterising what those ....Statistical Methods of Model Fitting and Segmentation in Computer Vision. Electronic sensors such as cameras and lasers can provide a rich source of information about the position, shape, and motion of objects around us. However, to extract this information in a reliable, automatic, and accurate way requires a sophisticated statistical theory of the process. Example applications include: video surveillance (better automatic detection of moving people and vehicles and of characterising what those people and vehicles are doing), industrial prototyping and inspection (measuring the size and shape of objects), urban planning (laser scanning streetscapes to create computer models of cities), entertainment industry (movie special effects and games), etc. Read moreRead less
Ultra-fast serialised all optical image processing: addressing the electronic bottleneck in the world's fastest camera. Serial time encoded amplified microscopy can capture over a million frames per second. At this rate, a megapixel image would fill a terabyte hard disk in a second. We will use photonics to condense and manipulated the video stream so that only the important features are 'seen', making it practical to process and store on a computer.
Advancing Medical Image Analysis through High Performance Heterogeneous Computing, Numerical Simulation, and Novel Human Computer Interfaces. This project will link Australian researchers with a major multi-national IT company. The engagement of world-class personnel from Microsoft will provide unprecedented opportunities for graduate students to experience research in both an academic and an industrial setting. The participation of Microsoft product division offers the potential to transform th ....Advancing Medical Image Analysis through High Performance Heterogeneous Computing, Numerical Simulation, and Novel Human Computer Interfaces. This project will link Australian researchers with a major multi-national IT company. The engagement of world-class personnel from Microsoft will provide unprecedented opportunities for graduate students to experience research in both an academic and an industrial setting. The participation of Microsoft product division offers the potential to transform the outcomes of this project into widely-used software solutions. The project will pave the way for more widespread and reliable evidenced-based computer-aided diagnosis and image-guided treatment. It will produce well-trained and sought-after graduates and research associates with extensive inter-disciplinary knowledge of medical image analysis and high-performance computing.Read moreRead less
Compression and communication of single and multi-view video based on overlapping motion hint fields. This project explores a new way of communicating motion for video and multi-view (3D) applications, facilitating efficient interactive access to content. Outcomes will include new compression methods that avoid redundant transmission of motion side information, plus client/server technology that leverages metadata from smart surveillance cameras.
Automated Determination of the Pose of a Human from Visual Information - Markerless 3D Pose Recovery of Humans from Videos. The development of 3D human pose recovery has been sought by computer vision researchers for many years. Our results will, firstly, have benefit for Australia's standing in the international computer vision community. Over time, the research outcomes will be developed into a software product for rehabilitation analysis by recognizing discrepancies between the walking pat ....Automated Determination of the Pose of a Human from Visual Information - Markerless 3D Pose Recovery of Humans from Videos. The development of 3D human pose recovery has been sought by computer vision researchers for many years. Our results will, firstly, have benefit for Australia's standing in the international computer vision community. Over time, the research outcomes will be developed into a software product for rehabilitation analysis by recognizing discrepancies between the walking patterns of healthy individuals and those with abnormalities as a result of accidents or diseases. The Australian economy will benefit by the reduction in the lifetime cost of injuries. This software will also provide benefits to the movie animation, computer games industry, and the training of athletes.Read moreRead less