Parameter Estimation/Optimisation

Many of the most critical problems in Computer Vision can be reduced to fitting a generic model onto observed data or measurements. An example is identifying 2D shapes (e.g. lines, circles) in an image, where the model is a geometrical structure defined by a few parameters (e.g. slope and intercept, center and radius), and fitting the model onto the data is equivalent to determining the size and position of instances of the shapes in the image. Computer Vision problems also deal with more exotic models such as subspaces, homographies and fundamental matrices. These models partake in a wide range of applications such as 3D reconstruction from multi-view images and segmentation of moving objects in a dynamic scene. Computer Vision applications constantly deal with very complex data, often automatically captured in unconstrained environments. Outliers are inevitably present in the data due to imperfections in sensing, digitisation and preprocessing. Another feature of data in Computer Vision is the existence of multiple model instances (e.g. multiple motion subspaces, planar homographies). Therefore traditional robust regression methods are simply inadequate for Computer Vision. Surmounting the challenges described above is the aim of this research. More specifically we aim to invent new robust estimators that can perform more accurately, autonomously and efficiently in practical Computer Vision applications.


  • 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.

    Professor Mike Brooks; Professor Wojciech Chojnacki.

  • Enhanced parameter estimation for multi-component fitting in computer vision

    Computer vision is concerned with the development of computational methods that endow machines with the capacity to interpret their visual environment. Emerging applications include automated methods for analysing behaviour exhibited in video and improved techniques for generating special effects in movies. Many vision problems require high-accuracy estimation of parameters embedded within a mathematical model, an area that has seen enormous progress over the last decade. This project will develop leading edge techniques for simultaneously computing parameters that characterise multiple components (such as several objects in motion) rather than a single component, a critical remaining challenge in the field.

    Professor Mike Brooks; Professor Wojciech Chojnacki.

  • Improved shape analysis: maximised statistical use of geometry/shape constraints

    This project will improve image analysis to apply such applications as 3D street-scape reconstruction, synthetic inserts into video for special effects, autonomous navigation, and scene understanding. It will do so by maximally exploiting the geometry of planar surfaces (e.g. walls) and straight lines and other simple geometric shapes.

    Professor David Suter.

Robust Statistics

This area of research looks at the developing procedures to analyse data to ensure that the information remains informative and efficient. Otherwise data analysis by non-robust methods can result in biased answers and conclusions. Robust statistics uses methods that identify patterns in the data, focusing on homogenous subset of the data, without being influenced by smaller subgroups.



  • 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.

    Professor D Suter; Associate Professor Ali Bab-Hadiashar.

  • Computer vision from a multi-structural analysis framework

    Computer vision has applications in a wide variety of areas: security (video surveillance), entertainment (special effects), health care (medical imaging), and economy (improved automation and consumer products). This project will improve the accuracy and reliability of such applications. Advances will also lead to new products and industries.

    Professor David Suter.

  • Space-based surveillance with robust computer vision algorithms

    The Earth's orbit hosts Trillions of dollars worth of space assets such as communications and navigational satellites. Space utilisation is also rapidly increasing with participation from new government and civilian agencies. There is thus a pressing need for space environment monitoring, so as to protect valuable assets by preventing collisions and possibly covert sabotage. The project aims to develop computer vision algorithms to detect man- made objects in space. The algorithms are designed to function on nanosatellite platforms, thus enabling space- based space surveillance. This resulting technology will provide always-on monitoring of the Earth's orbit to enhance existing defence infrastructure and protect vital space assets.

    Associate-Professor Tat-Jun Chin; Inovor.