Autocalibration without decimation. The insertion of computer generated characters into real footage, the removal of objects from video, and the recovery of 3-dimensional architectural or topographic models from photographs are amongst a growing number of processes used in industry which require highly accurate camera calibration. Autocalibration is thus a prerequisite for these and many other emerging image-based technologies. By developing expertise in this area, and particularly by enabling ....Autocalibration without decimation. The insertion of computer generated characters into real footage, the removal of objects from video, and the recovery of 3-dimensional architectural or topographic models from photographs are amongst a growing number of processes used in industry which require highly accurate camera calibration. Autocalibration is thus a prerequisite for these and many other emerging image-based technologies. By developing expertise in this area, and particularly by enabling more flexible and efficient means of autocalibration, we expect to provide Australian industry with a valuable improvement in the state of the art and a competitive edge in a number of important application areas.Read moreRead less
Learning Robotic Navigation and Interaction from Object-based Semantic Maps. Our project aims to develop new learning algorithms that enable robots to perform high-complexity tasks that are currently impossible. Compared to existing methods that rely on low-level sensor data, we aim to achieve this by learning from a high-level graph representation of the environment that captures semantics, affordances, and geometry. The outcome would be robots capable of using human instructions to efficiently ....Learning Robotic Navigation and Interaction from Object-based Semantic Maps. Our project aims to develop new learning algorithms that enable robots to perform high-complexity tasks that are currently impossible. Compared to existing methods that rely on low-level sensor data, we aim to achieve this by learning from a high-level graph representation of the environment that captures semantics, affordances, and geometry. The outcome would be robots capable of using human instructions to efficiently learn complex interaction and navigation behaviours that transfer to unseen environments. Our research should benefit new applications in domains of economic and societal importance that are currently too complex, unsafe, and uncertain for robot assistants, such as aged care, advanced manufacturing and domestic robotics.Read moreRead less
Learning to see in 3D. The project aims to endow machine vision with an ability we, as humans, use almost constantly: to judge 3D properties from a 2D image. This extremely useful ability will be applied to digital images to obtain 3D measurements and aid in automating tasks such as mining, surveying, medical diagnosis, and visual effects in movies.
Combined shape and appearance descriptors for visual object recognition. The quantity of video generated each year is expanding rapidly. This increasing volume of visual information means that it is more likely that any particular event will be recorded, but that the footage will be harder to find. This applies to a collection of home videos as much as to television and movie footage. The object-recognition method to be developed has the potential to alleviate this situation, in which vast amou ....Combined shape and appearance descriptors for visual object recognition. The quantity of video generated each year is expanding rapidly. This increasing volume of visual information means that it is more likely that any particular event will be recorded, but that the footage will be harder to find. This applies to a collection of home videos as much as to television and movie footage. The object-recognition method to be developed has the potential to alleviate this situation, in which vast amounts of video data are available but have little value. Such an outcome would be a boon for Australian industry and offer a valuable export opportunity.Read moreRead less
Deep Learning that Scales. Deep learning has dramatically improved the accuracy of a breathtaking variety of tasks in AI such as image understanding and natural language processing. This project addresses fundamental bottlenecks when attempting to develop deep learning applications at scale. First, this project proposes efficient neural architecture search that is orders of magnitude faster than previously reported, abstracting away the most complex part of deep learning. Second, we will desig ....Deep Learning that Scales. Deep learning has dramatically improved the accuracy of a breathtaking variety of tasks in AI such as image understanding and natural language processing. This project addresses fundamental bottlenecks when attempting to develop deep learning applications at scale. First, this project proposes efficient neural architecture search that is orders of magnitude faster than previously reported, abstracting away the most complex part of deep learning. Second, we will design very efficient binary networks, enabling large-scale deployment of deep learning to mobile devices. Thus this project will overcome two primary limitations of deep learning generally, however, and will greatly increase its already impressive domain of practical application.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
Multi-objective parameter estimation techniques for computer vision. This project will benefit Australia's scientific knowledge and technology base in the area of computer vision. By contributing improved methods for parameter estimation applicable to a wide variety of technical problems, the project will aid the generation of improved software products in a wide variety of domains. Examples include: augmented reality systems, with which virtual reality artifacts may be immersed within real vid ....Multi-objective parameter estimation techniques for computer vision. This project will benefit Australia's scientific knowledge and technology base in the area of computer vision. By contributing improved methods for parameter estimation applicable to a wide variety of technical problems, the project will aid the generation of improved software products in a wide variety of domains. Examples include: augmented reality systems, with which virtual reality artifacts may be immersed within real video; 3D from 2D systems, with which 3D object structure may be computed from image streams; and visual robotic systems, with which the pose of viewed objects may be determined.Read moreRead less
Automated acquisition of surveillance-camera network topology. The development of an automated system for acquisition of camera network topology is a crucial prerequisite to obtaining intelligent surveillance systems operating at the network level. Such systems will contribute improved methods for safeguarding Australia from terrorism and crime by facilitating the tracking of suspicious individuals and vehicles, and detecting anomalous behaviours in busy environments. The leading-edge techniques ....Automated acquisition of surveillance-camera network topology. The development of an automated system for acquisition of camera network topology is a crucial prerequisite to obtaining intelligent surveillance systems operating at the network level. Such systems will contribute improved methods for safeguarding Australia from terrorism and crime by facilitating the tracking of suspicious individuals and vehicles, and detecting anomalous behaviours in busy environments. The leading-edge techniques involved will also constitute smart information use of significant commercial value to Australian industry. Read moreRead less
Deep reinforcement learning for discovering and visualising biomarkers. This project aims to develop novel methods for discovering and visualising optimal bio-markers from chest computed tomography images based on extensions of recently developed deep reinforcement learning techniques. The extensions proposed in this project will advance medical image analysis by allowing an efficient analysis of large dimensionality inputs in their original high resolution. In addition, this project will be the ....Deep reinforcement learning for discovering and visualising biomarkers. This project aims to develop novel methods for discovering and visualising optimal bio-markers from chest computed tomography images based on extensions of recently developed deep reinforcement learning techniques. The extensions proposed in this project will advance medical image analysis by allowing an efficient analysis of large dimensionality inputs in their original high resolution. In addition, this project will be the first approach capable of discovering previously unknown biomarkers associated with important clinical outcomes. The project will validate the approach on a real-world case study data set concerning the prediction of five-year survival of chronic disease.Read moreRead less
New Paradigms for Robust Fitting: Kernelisation and Polyhedral Search. Outliers inevitably exist in visual data due to imperfect data acquisition or preprocessing. To enable computer vision applications that can perform reliably, robust fitting algorithms are necessary to counter the biasing influence of outliers. However, current robust algorithms are unsatisfactory: they are unreliable (due to using randomisation) or too computationally costly (due to using exhaustive search). This project wil ....New Paradigms for Robust Fitting: Kernelisation and Polyhedral Search. Outliers inevitably exist in visual data due to imperfect data acquisition or preprocessing. To enable computer vision applications that can perform reliably, robust fitting algorithms are necessary to counter the biasing influence of outliers. However, current robust algorithms are unsatisfactory: they are unreliable (due to using randomisation) or too computationally costly (due to using exhaustive search). This project will develop new robust algorithms to mitigate these shortcomings. It will do so by investigating two new paradigms of kernelisation and polyhedral search, which offer unprecedented theoretical insights into the problem. The outcomes will contribute towards computer vision applications that are more practical and reliable.Read moreRead less