Learning clique potentials for high-order graphical models. This project aims to develop algorithms for computers to automatically learn about visual scenes and objects from images. Using our algorithms, computers will be able to find objects and describe scenes in single images or large image collections such as online photo albums.
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE130100156
Funder
Australian Research Council
Funding Amount
$210,000.00
Summary
Computational infrastructure for machine learning in computer vision. The many trillions of images stored on computers around the world, including more than 100 billion on Facebook alone, represent exactly the information needed to develop artificial vision. All we need do is extract it. This project will develop the computational infrastructure required to allow Australian researchers to achieve this goal.
Discovery Early Career Researcher Award - Grant ID: DE120102948
Funder
Australian Research Council
Funding Amount
$375,000.00
Summary
Interactive computer vision for image interpretation. This project aims at pushing forward the fundamental research in interactive computer vision. The outcome of this project will enable reliable and efficient solutions to real world image interpretation tasks, such as medical image analysis, financial document processing, and impact evaluation from natural disasters.
The vision we rely on every day to read and recognise faces depends upon the health of the central portion of our retina, the macula. Age-related Macular Degeneration (AMD) is the leading cause of blindness in Australia and the western world. Researchers at the Australian National University are collaborating to bring a new test for AMD severity to the market within 3 years. The objective is to provide doctors with a rapid, cost-effective tool to help them manage treatment.
Discovery Early Career Researcher Award - Grant ID: DE140100180
Funder
Australian Research Council
Funding Amount
$394,305.00
Summary
Advancing Dense 3D Reconstruction of Non-rigid Scenes by Using a Moving Camera. This project will advance the fundamental research in geometric computer vision and develop a new framework for efficient dense three-dimensional reconstruction of non-rigid scenes by using a moving camera. It is expected that this project will bring about breakthroughs in geometric computer vision with many daily applications, including three-dimensional natural human-computer interaction, three-dimensional reconstr ....Advancing Dense 3D Reconstruction of Non-rigid Scenes by Using a Moving Camera. This project will advance the fundamental research in geometric computer vision and develop a new framework for efficient dense three-dimensional reconstruction of non-rigid scenes by using a moving camera. It is expected that this project will bring about breakthroughs in geometric computer vision with many daily applications, including three-dimensional natural human-computer interaction, three-dimensional reconstruction from historical movies and three-dimensional realistic animations. Its outcomes will enable users to capture and manipulate their surrounding dynamic world in three-dimensions easily and conveniently. This project will alleviate many of the major difficulties (dense correspondences, long sequences, complex deformations) with conventional non-rigid reconstruction methods.Read moreRead less
Foundations of Vision Based Control of Robotic Vehicles. Automated and partially automated robotic vehicles are an emerging technology in society. The safety and performance of such systems depends crucially on their sensing and control algorithms. Vision sensing is one of the few sensor modalities that has the potential to adequately represent the complexity of a real world environment. By providing simple and effective vision based control algorithms this project develops Frontier Technologi ....Foundations of Vision Based Control of Robotic Vehicles. Automated and partially automated robotic vehicles are an emerging technology in society. The safety and performance of such systems depends crucially on their sensing and control algorithms. Vision sensing is one of the few sensor modalities that has the potential to adequately represent the complexity of a real world environment. By providing simple and effective vision based control algorithms this project develops Frontier Technologies for Building and Transforming Australian Industries by enabling a wide range of robotic vehicle applications, including aerial, submersible, and wheeled vehicles.Read moreRead less
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
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
Suction pipette measurements of mammalian rod photoreceptor recovery following intense bleaching exposures. The aim of this project is to discover the events and processes that prevent retinal photoreceptors from recovering instantaneously following the cessation of exposure to extremely bright illumination. Recordings will be made from single rod photoreceptors cells isolated from the mammalian retina. The work will uncover the relative roles of the 'photoproducts' created when rhodopsin abso ....Suction pipette measurements of mammalian rod photoreceptor recovery following intense bleaching exposures. The aim of this project is to discover the events and processes that prevent retinal photoreceptors from recovering instantaneously following the cessation of exposure to extremely bright illumination. Recordings will be made from single rod photoreceptors cells isolated from the mammalian retina. The work will uncover the relative roles of the 'photoproducts' created when rhodopsin absorbs light: e.g. intermediates such as metarhodopsin and opsin. The molecular knowledge obtained will help us to understand why it is that the visual system recovers so slowly after the eye has experienced very intense light.Read moreRead less