Category: Parameter Estimation
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.
Congratulations to TJ, Pulak, Anders and David. Their paper, Efficient Globally Optimal Consensus Maximisation with Tree Search, recently was awarded a Best Paper Honourable Mention at CVPR. CVPR is the premier annual conference for Computer Vision research, and this recognition is a fantastic achievement for the team! Only 3 Best Paper Honourable Mention awards were […]
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 […]
Prof. David Suter and Dr Tat-Jun Chin have been awarded a 3 year ARC Discovery Grant valued at $330,000. 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 […]
Dr Anders Eriksson of the ACVT has been awarded a 3 year ARC DECRA Fellowship valued at $375,000. Computer vision concerns itself with understanding the real world through the analysis of images. With the number of images and video available over the internet reaching several billions, and growing, this has begun to revolutionize the field. […]
ARC Success! Congratulations to Anton van den Hengel, Ian Reid, Anthony Dick, TJ Chin, Chunhua Shen and David Suter!
Congratulations to Anton van den Hengel, Ian Reid, Anthony Dick, TJ Chin, Chunhua Shen and David Suter! Well done on the following ARC 2013 grants that were recently awarded: Prof Ian Reid and Dr Anthony Dick have secured $358,000 of ARC funding over the next three years for the below DP: Title: Recognising and reconstructing […]
ACVT researchers have 2 articles in the latest IEEE Transactions on Pattern Analysis and Machine Intelligence from April 2012 (vol. 34 no. 4). PAMI is the best journal in the field. The papers are; Accelerated Hypothesis Generation for Multistructure Data via Preference Analysis, Tat-Jun Chin, Jin Yu, David Suter,http://doi.ieeecomputersociety.org/10.1109/TPAMI.2011.169 UBoost: Boosting with the Universum, Chunhua Shen, Peng […]
On Monday 12th December, the ACVT welcomes two visitors: Professor Kenichi Kanatani, Professor of Computer Science at Okayama University, Japan, and Dr Andrew Comport, “Chargé de Recherches” (Tenure Researcher) with the Centre National de Recherche Scientifique (CNRS) in France. Along with Professor Wojciech Chojnacki, Senior Research Fellow in the School of Computer Science at The University […]
Well done to Javen who has been awarded $375,00o of DECRA funding through the ARC in the 2012 round!! Only 277 proposals were awarded from over 2,100 applications. This is a fabulous result for Javen, congratulations! Title: Compressive sensing based probabilistic graphical models (PGM) Project Summary: The aim of the project is to develop fast, large scale […]
Profs David Suter and Anton van den Hengel were both awarded ARC Discovery Grants to begin in 2011. They are: Computer vision from a multistructural analysis framework, Prof D. Suter. 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 […]
Prof. David Suter has been awarded a 3 year ARC Discovery Grant valued at $300,000. 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 […]