Solve it or Ignore it? The Challenge of Alignment Distortion and Creating Next Generation Automatic Facial Expression Detection. The last two decades have seen an escalating interest in automating the coding of facial expressions. Despite this keen interest, the promise of computer vision systems to accurately code facial expressions in natural circumstances remains elusive. Our interdisciplinary team will research a new paradigm to account for facial alignment distortion directly rather than ai ....Solve it or Ignore it? The Challenge of Alignment Distortion and Creating Next Generation Automatic Facial Expression Detection. The last two decades have seen an escalating interest in automating the coding of facial expressions. Despite this keen interest, the promise of computer vision systems to accurately code facial expressions in natural circumstances remains elusive. Our interdisciplinary team will research a new paradigm to account for facial alignment distortion directly rather than aiming to achieve invariance to it. The project will also research new data agnostic feature compaction capabilities to enable scalable learning on the world’s largest and challenging expression dataset available to us through international collaboration. Tackling these two major open problems will make accurate coding of facial expressions in natural environments achievable.Read moreRead less
Semantic Vectorisation: From Bitmaps to Intelligent Representations. The objective of this innovative project is to provide a solution to the open question of representing natural images by semantically rich vector graphics. The challenges are to identify key visual and temporal elements for images and videos, and efficiently decompose the visual data into semantic vector representations that are faithful to original data, compact and editable. The project aims to investigate new bitmap-to-vecto ....Semantic Vectorisation: From Bitmaps to Intelligent Representations. The objective of this innovative project is to provide a solution to the open question of representing natural images by semantically rich vector graphics. The challenges are to identify key visual and temporal elements for images and videos, and efficiently decompose the visual data into semantic vector representations that are faithful to original data, compact and editable. The project aims to investigate new bitmap-to-vector conversion methods. It is expected to develop a framework where semantic labels and hyperlinks can be embedded in visual data automatically. It hopes to pioneer the creation of a web of images where the links are on image/video regions. New image simplification, stylisation, and non-photorealistic rendering methods are expected to be provided.Read moreRead less
Development of a three dimensional audio-visual next generation speech recognition system. To overcome the disadvantages of current Audio-Visual Speech Recognition Systems, we propose a set of robust algorithms in three dimensional computer vision and speech processing. The proposed system will have far-reaching implications in various areas, for example, human-machine interaction for speech recognition in automated dialog systems and voice-to-text conversions.
Discovery Early Career Researcher Award - Grant ID: DE120100802
Funder
Australian Research Council
Funding Amount
$375,000.00
Summary
Developing novel concepts for improved safety in aircraft emergency situations. The outcomes of this project will enable the creation of an emergency system that can improve visual situation awareness in emergency landing scenarios by investigating novel detection, control and planning algorithms. The project will contribute significantly to Australia's share in technologies for aircraft automation.
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE100100235
Funder
Australian Research Council
Funding Amount
$280,000.00
Summary
Accelerating Australia's large scale video surveillance research programmes. The research to be conducted using this infrastructure will bring immense benefits to Australia in terms of increased levels of public safety and in the protection of critical facilities from terrorism and other crimes, by developing better surveillance systems. This will provide both increases in measurable research outputs and opportunities for Australian business to commercialise these systems. The infrastructure wil ....Accelerating Australia's large scale video surveillance research programmes. The research to be conducted using this infrastructure will bring immense benefits to Australia in terms of increased levels of public safety and in the protection of critical facilities from terrorism and other crimes, by developing better surveillance systems. This will provide both increases in measurable research outputs and opportunities for Australian business to commercialise these systems. The infrastructure will accelerate the pace of surveillance research and development in Australia, enhancing the competitiveness of both Australia's researchers and the businesses that will commercialise these researchers' discoveries.Read moreRead less
Tracking targets in large scale surveillance camera networks. The research is expected to provide a significant boost in the effectiveness of safety and security measures for public facilities and open spaces that are monitored by surveillance cameras. The general public benefits from this through a decreased need for intrusive security measures, and increased deterrence of crime and anti-social behaviour. This capability is in demand worldwide for both public and private camera networks, whose ....Tracking targets in large scale surveillance camera networks. The research is expected to provide a significant boost in the effectiveness of safety and security measures for public facilities and open spaces that are monitored by surveillance cameras. The general public benefits from this through a decreased need for intrusive security measures, and increased deterrence of crime and anti-social behaviour. This capability is in demand worldwide for both public and private camera networks, whose usefulness is currently limited by the difficulty of monitoring them. We therefore anticipate considerable commercial interest in Australia and internationally.
Read moreRead less
Detecting, Locating and Tracking Human Faces using Skin Colour. With growing concerns for national security and public safety, government agencies in Australia and around the world are taking strong measures to introduce biometric-enhanced official identification documents such as passports, visas, and ID cards. The proposed face detection and tracking system will play a key role in personal identification and human activity monitoring. The developed system will have a huge potential in surveill ....Detecting, Locating and Tracking Human Faces using Skin Colour. With growing concerns for national security and public safety, government agencies in Australia and around the world are taking strong measures to introduce biometric-enhanced official identification documents such as passports, visas, and ID cards. The proposed face detection and tracking system will play a key role in personal identification and human activity monitoring. The developed system will have a huge potential in surveillance, security, law enforcement, and ICT. This project will contribute to building a knowledge economy in Australia and help safeguard and protect Australia from terrorism and crime. Furthermore, its outcomes will enhance the reputation of Australia as a leader in frontier technologies and smart information use.Read moreRead less
Image search for simulator content creation. The World Wide Web contains tens of billions of images, with personal and industrial collections stretching to may times that number. The potential economic value of these image-based resources is enormous, but largely untapped as we have no practical way of recovering the images we need. This project will develop image search technologies which will allow Australian industry to exploit these important resources. Some of the wide variety of possible ....Image search for simulator content creation. The World Wide Web contains tens of billions of images, with personal and industrial collections stretching to may times that number. The potential economic value of these image-based resources is enormous, but largely untapped as we have no practical way of recovering the images we need. This project will develop image search technologies which will allow Australian industry to exploit these important resources. Some of the wide variety of possible applications might include the searching of surveillance video for objects of interest, vision-based guidance of unmanned vehicles, smart-phone and smart-home systems which understand their environments, and stock tracking systems which can detect spoilage.Read moreRead less
Robust face detection and recognition for computer-based security surveillance. The research aims at improving the existing and creating new automated face detection and recognition methods by making them invariant, firstly to head pose, orientation, scale and rotation, and then to occlusion, lighting conditions and facial expressions.
A robust face detector will be developed first and then a new face recognition algorithm that continues to learn identity-specific discriminants on-line by co ....Robust face detection and recognition for computer-based security surveillance. The research aims at improving the existing and creating new automated face detection and recognition methods by making them invariant, firstly to head pose, orientation, scale and rotation, and then to occlusion, lighting conditions and facial expressions.
A robust face detector will be developed first and then a new face recognition algorithm that continues to learn identity-specific discriminants on-line by collecting incremental face exemplars. The result of the research will be an algorithm that can improve its performance on-line adapting in a stable learning process each identity model to the correct facial examples.
The research has significant practical implication in visual surveillance increasing the robustness of identification of person identity, state and intent.
Read moreRead less
Visual Solutions for Automated Translation Between Spoken and Signed Languages. We propose to build a robust visual speech recognition system that analyzes images of spoken language and achieves a recognition of the utterances with at least human expert recognition rates. This visual speech recognition system will then be integrated with our existing gesture recognition system to improve performance, just as humans combine visual and audio data for language understanding. The result will be a sy ....Visual Solutions for Automated Translation Between Spoken and Signed Languages. We propose to build a robust visual speech recognition system that analyzes images of spoken language and achieves a recognition of the utterances with at least human expert recognition rates. This visual speech recognition system will then be integrated with our existing gesture recognition system to improve performance, just as humans combine visual and audio data for language understanding. The result will be a system providing translation between English and the Australian sign language Auslan in a practical application domain. Significantly, our work will provide insights into the cognitive models of neural activity linking language and gesture.Read moreRead less