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
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.
Discovery Early Career Researcher Award - Grant ID: DE220101379
Funder
Australian Research Council
Funding Amount
$417,000.00
Summary
Towards Transferable Visual Understanding in the Real World. This project aims to investigate how to improve the transferability of visual understanding algorithm and system in the real-world applications. This project expects to innovate and advance knowledge in the fields of visual transfer learning and generalizable visual representation learning. Expected outcomes of this project include techniques and algorithms to make the visual understanding system robust to diverse real-world scenarios. ....Towards Transferable Visual Understanding in the Real World. This project aims to investigate how to improve the transferability of visual understanding algorithm and system in the real-world applications. This project expects to innovate and advance knowledge in the fields of visual transfer learning and generalizable visual representation learning. Expected outcomes of this project include techniques and algorithms to make the visual understanding system robust to diverse real-world scenarios. This project should provide significant benefits, such as improving the robustness and safety of autonomous vehicles in transportation area, and reducing the cost of destructive data collection for intelligent fault detection in advanced manufacturing area.Read moreRead less
Robust and scalable change detection in geo-spatial data. A flood of data in the form of text, images and video emanate from a proliferation of sensors. These data are collected but rarely analysed, rendering it meaningless. This project aims to develop new software and techniques to detect changes over time in large scale geographically referenced data (for example photomaps) for use across numerous domains.
Discovery Early Career Researcher Award - Grant ID: DE130101775
Funder
Australian Research Council
Funding Amount
$375,000.00
Summary
Distributed large-scale optimisation methods in computer vision. With the number of images and video available over the internet reaching billions and growing, the need for new tools for handling and interpreting such huge amounts of data is quickly becoming apparent. This project will focus on developing new optimisation methods for efficiently computing solutions for a broad class of large-scale problems.
Design of adaptive learning visual sensor networks for crowd modelling in high-density and occluded scenarios. Partnering University of Melbourne researchers, with video surveillance experts SenSen, engineering consultants ARUP and the Melbourne Cricket Club, the project addresses research enabling a system-integrating, existing surveillance, infrastructure to model crowd behaviour and exit strategies, providing real-time analysis, prediction and response capabilities for venue managers and emer ....Design of adaptive learning visual sensor networks for crowd modelling in high-density and occluded scenarios. Partnering University of Melbourne researchers, with video surveillance experts SenSen, engineering consultants ARUP and the Melbourne Cricket Club, the project addresses research enabling a system-integrating, existing surveillance, infrastructure to model crowd behaviour and exit strategies, providing real-time analysis, prediction and response capabilities for venue managers and emergency services. This new capability enhances utilisation of security resources to prevent injury and fatalities in evacuation scenarios, applicable to existing venues and influencing the development of new facilities around the country. The project delivers researcher training, global clientele for local technology and a platform for local industry growth.Read moreRead less