Producing 3D video sequences from 2D input video. The project will develop new methods for extracting 3D information from existing films so that they may be used with 3D television monitors marketed by the industrial partner, Dynamic Digital Depth. The 3D representation will allow existing video material such as existing films, TV programs and news video to be viewed in 3D on a suitable 3D TV monitor. This will give a boost to the acceptance of 3D television and film as a preferred medium. Ex ....Producing 3D video sequences from 2D input video. The project will develop new methods for extracting 3D information from existing films so that they may be used with 3D television monitors marketed by the industrial partner, Dynamic Digital Depth. The 3D representation will allow existing video material such as existing films, TV programs and news video to be viewed in 3D on a suitable 3D TV monitor. This will give a boost to the acceptance of 3D television and film as a preferred medium. Expected outcome is a software system that will speed the conversion of 2D video to a 3D representation through automatic and interactive analysis techniques.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
Autonomous Functions for Smart Cars. The aim of this project is to develop autonomous functions for smart cars, such as lane departure warning, driver fatigue warning, and automatic lane following. Every year 70,000 people are killed in road accidents, 95% of which can be attributed to driver error. The potential outcomes of this project therefore significant. Many of the theoretical methods required for this project have been developed by our group. However, further theoretical refinements fo ....Autonomous Functions for Smart Cars. The aim of this project is to develop autonomous functions for smart cars, such as lane departure warning, driver fatigue warning, and automatic lane following. Every year 70,000 people are killed in road accidents, 95% of which can be attributed to driver error. The potential outcomes of this project therefore significant. Many of the theoretical methods required for this project have been developed by our group. However, further theoretical refinements followed by experimental verification is necessary. For smart cars to be accepted, the systems must be demonstrated to be reliable and to operate in a wide range of conditions.Read moreRead less
Space-based space surveillance with robust computer vision algorithms. Space-based space surveillance with robust computer vision algorithms. This project aims to develop computer vision algorithms to detect man-made objects in space. These algorithms function on nanosatellite platforms, enabling space-based space surveillance. This technology is expected to provide always-on monitoring of the Earth's orbit to enhance existing defence infrastructure and protect vital space assets, including comm ....Space-based space surveillance with robust computer vision algorithms. Space-based space surveillance with robust computer vision algorithms. This project aims to develop computer vision algorithms to detect man-made objects in space. These algorithms function on nanosatellite platforms, enabling space-based space surveillance. This technology is expected to provide always-on monitoring of the Earth's orbit to enhance existing defence infrastructure and protect vital space assets, including communications and navigational satellites, in Earth’s orbit from collisions and covert sabotage. Increased space use by government and civilian agencies opens up opportunities for the space industry. This project is expected to develop Australia’s space surveillance capabilities, protect space assets and capture a growing market.Read moreRead less
Lifelong robotic navigation using visual perception. Service robots are becoming a major part of our working and personal environments, in much the same way as personal computers already have. This project will develop new methods of practical and useful robot navigation that will enable Australia's industries and services to remain internationally competitive.
Enhanced ultrasound-based imaging using image-based registration and acoustic impedance reconstruction. The project will nurture the development of a new centre for medical image analysis work in Australia at the ANU. This is in line with the vision of ANU's Department of Engineering for the growth of biomedical engineering research. The project is directed at the creation of new surgical and imaging techniques based on ultrasound. These will have a direct effect on improved healthcare and new c ....Enhanced ultrasound-based imaging using image-based registration and acoustic impedance reconstruction. The project will nurture the development of a new centre for medical image analysis work in Australia at the ANU. This is in line with the vision of ANU's Department of Engineering for the growth of biomedical engineering research. The project is directed at the creation of new surgical and imaging techniques based on ultrasound. These will have a direct effect on improved healthcare and new clinical procedures. The creation of a new ultrasound imaging modality will have commercial applications, enhancing the growth of biomedical engineering in Australia. The training of new PhD students and postdoctoral fellows will provide a basis for further development in this area, and its extension to other imaging research in Australia. Read moreRead less
Advanced Interface Technologies for Computational Science & Simulation. The project will research novel computer vision technologies that enable the next generation of visualisation portals for scientific collaboration. The development of new computer vision tools is key to truly natural human-machine interaction. The research outcomes of this project directly align with National Research Priority 3: Frontier Technologies. It supports four of the five relevant priority goals - Breakthrough Scien ....Advanced Interface Technologies for Computational Science & Simulation. The project will research novel computer vision technologies that enable the next generation of visualisation portals for scientific collaboration. The development of new computer vision tools is key to truly natural human-machine interaction. The research outcomes of this project directly align with National Research Priority 3: Frontier Technologies. It supports four of the five relevant priority goals - Breakthrough Science, Frontier Technologies, Smart Information Use, and Promoting an Innovation Culture and Economy. Outcomes of this research are also relevant to Research Priority 4: Safeguarding Australia, and has direct applications to video surveillance technology. Significant commercial opportunities, including licensing and spin-offs exist.Read moreRead less
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE160100090
Funder
Australian Research Council
Funding Amount
$250,000.00
Summary
Computational infrastructure for developing deep machine learning models. Computational infrastructure for developing deep machine learning models:
The computational infrastructure for developing deep machine learning models aims to enable new developments in machine learning of deep neural network models by providing the specialised computing necessary to train and evaluate the networks. In the last three years, deep networks have smashed previous performance ceilings for tasks such as object ....Computational infrastructure for developing deep machine learning models. Computational infrastructure for developing deep machine learning models:
The computational infrastructure for developing deep machine learning models aims to enable new developments in machine learning of deep neural network models by providing the specialised computing necessary to train and evaluate the networks. In the last three years, deep networks have smashed previous performance ceilings for tasks such as object recognition in images, speech recognition and automatic translation, bringing the prospect of machine intelligence closer than ever. Modern machine learning techniques have had huge impact in the last decade in fields such as robotics, computer vision and data analytics. The facility would enable Australian researchers to develop, learn and apply deep networks to problems of national importance in robotic vision and big data analytics. 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