BLOGS WEBSITE

Category: Tracking

ACVT conducts research in the fields of camera calibration, visual tracking, novel-view synthesis, automatic visual surveillance, and simultaneous localisation and mapping. This area is led by Laureate Professor Ian Reid. Visual SLAM. By observing a static scene with a camera, it is possible to estimate the trajectory of the camera and simultaneously build a map of the environment. When done in real time this has the potential to turn a simple webcam into a flexible and powerful geometric sensing device. The area has had a major impact in the robotics community because for the first time a visual sensor could deliver timely geometric information about an unstructured environment. Visual Geometry. Advances in the field of visual geometry based upon an understanding of projective geometry as applied to making physical geometric measurements from uncalibrated images. Camera Self-Calibration. Calibration of cameras using invariant eigenvectors from projective transformations, mapping scene structure from one location to another. Also, work has been done in methods for self-calibration of rotating and zooming camera. Stereo Reconstruction. Use of novel graph construction methods that permit second-order interactions to build piecewise planar reconstructions. Human motion capture. Development of the first markerless motion capture system. Through the deployment of annealed particle filtering and extensions to incorporate a genetic “crossover” operator that enabled efficient exploration of the huge multi-modal configuration space. Visual tracking and active vision. The ability to track an object of interest is a fundamental enabling technology for many video analysis tasks. A distinguishing feature of the area has been an emphasis on real-time methods, and incorporating these into robotic pan–tilt–zoom platforms for closed-loop visual tracking. The significant processing power of a modern desktop computer has permitted greater sophistication in visual tracking, and recent work has shown how a target can be segmented from its background while being tracked in real time. A further development in computing hardware has led to work in tracking human heads in surveillance video. Visual surveillance and activity recognition. Visual tracking combined with our work on SLAM in radar yielded a system for marine situation awareness that tracks targets in radar, self-localises without the need for GPS, and drives a custom high-performance pan–tilt–zoom platform to gather visual data about any designated target.

CVPR 2015 Best Workshop Paper Award

In conjunction with the success of the Australian Centre for Robotic Vision’s workshops at CVPR2015 in Boston: Workshop on Semantics for Visual Reconstruction, Localization and Mapping Workshop on Visual Place Recognition in Changing Environments An ACRV team was also successful in attaining the Best Workshop Paper Award for the IEEE – Workshop on Computer Vision […]

Posted in News, Tracking | Tagged , , |

Comments Off on CVPR 2015 Best Workshop Paper Award

Twelve papers at CVPR

The ACVT had 12 papers accepted to IEEE Computer Vision and Pattern Recognition 2015 (CVPR’15), one of the top 2 conferences in Computer Vision, which must be an Australian record. In terms of h5-index, CVPR ranks as the 7th venue in all Engineering and Computer Science after Nano and Nature journals. To put this in […]

Posted in 3D Modelling, Machine Learning, News, Parameter Estimation, Research, Tracking | Tagged |

Comments Off on Twelve papers at CVPR

Best Paper Award for Prof Ian Reid at 3DV2014

Professor Ian Reid and colleagues from Oxford have been awarded the Best Paper Award at the International Conference on 3D Vision, held in Tokyo, Japan from 8-11 December 2014 The paper, titled “3D Tracking of Multiple Objects with Identical Appearance using RGB-D Input”, was authored by Carl Yuheng Ren, Victor Prisacariu, Olaf Kaehler, Ian Reid […]

Posted in Events, News, Research, Tracking | Tagged , , , |

Comments Off on Best Paper Award for Prof Ian Reid at 3DV2014

PhD Scholarships in Visual SLAM and Computer/Robotic Vision and Machine Learning for Visual Recognition

The Australian Centre for Visual Technologies (ACVT) at The University of Adelaide has 12 PhD scholarships available for both local and international students interested in pursuing a PhD. These Scholarships are funded from an ARC Laureate Fellowship to Prof Ian Reid entitled “Lifelong Computer Vision Systems”, and an ARC Centre of Excellence in Robotic Vision, […]

Posted in Machine Learning, News, Tracking, Vacancies | Tagged , |

Comments Off on PhD Scholarships in Visual SLAM and Computer/Robotic Vision and Machine Learning for Visual Recognition

ARC Centre of Excellence for Robotic Vision (CE140100016)

ACVT researchers Prof. Ian Reid, Prof. Anton van den Hengel, Associate Prof. Chunhua Shen and Dr. Gustavo Carneiro are part of a team that has been awarded a prestigious ARC Centre of Excellence in Robotic Vision. The Centre has received $19M of funding and will conduct a 7-year program of research with the following focus […]

Posted in 3D Modelling, Machine Learning, News, Research, Tracking | Tagged , , , , |

Comments Off on ARC Centre of Excellence for Robotic Vision (CE140100016)

Lifelong Computer Vision Systems (FL130100102)

Prof. Ian Reid of the ACVT has been awarded an ARC Laureate Fellowship valued at $3,179,946. The aim of the project is to develop robust computer vision systems that can operate over a wide area and over long periods. This is a major challenge because the geometry and appearance of an environment can change over […]

Posted in Projects, Research, Tracking | Tagged , |

Comments Off on Lifelong Computer Vision Systems (FL130100102)

Congratulations to Prof Ian Reid who has been awarded a prestigious Australian Laureate Fellowship

Professor Ian Reid has been awarded a prestigious Australian Laureate Fellowship. The aim of the scheme is to attract and retain outstanding researchers and research leaders of international repute and build and strengthen world-class research capability in Australia. Professor Reid’s project is “Lifelong Computer Vision Systems” which will create new ways of generating detailed environmental maps […]

Posted in News, Tracking | Tagged |

Comments Off on Congratulations to Prof Ian Reid who has been awarded a prestigious Australian Laureate Fellowship

Visual tracking with environmental constraints (LP130100154)

ACVT has been awarded a 3 year ARC Linkage Project valued at $345,000. The industry partner is Champion Data, a Melbourne based sports statistics company. The CIs on the project are Dr Anthony Dick and Prof. Ian Reid. Tracking people in video is a key problem in computer vision, with widespread application in areas such […]

Posted in Projects, Research, Tracking | Tagged , , |

Comments Off on Visual tracking with environmental constraints (LP130100154)

Professor Ian Reid appointed from September 2012

The Australian Centre for Visual Technologies is pleased to announce the appointment ofProfessor Ian Reid from September 2012. Ian is currently a Professor of Engineering Science, running the Active Vision Group at the University of Oxford and will bring to the University of Adelaide an internationally recognised research record in the areas of Computer Vision and visual technologies. Professor Reid’s appointment will ensure that […]

Posted in News, Research, Tracking | Tagged |

Comments Off on Professor Ian Reid appointed from September 2012

Image search for simulator content creation (LP100100791)

ACVT has been awarded a 3 year ARC Linkage Project valued at $300,000. Sydac, a leading Australian Simulation company is the industry partner. The CIs on the project are Prof. Anton van den Hengel and Dr Anthony Dick. 3D content creation represents one of the most labour intensive stages of the process of constructing virtual […]

Posted in 3D Modelling, Machine Learning, Projects, Research, Tracking | Tagged , , , |

Comments Off on Image search for simulator content creation (LP100100791)