ORCID Profile
0000-0001-9612-5884
Current Organisation
University of Adelaide
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: SPIE
Date: 14-12-1998
DOI: 10.1117/12.333782
Publisher: IEEE
Date: 09-2007
Publisher: Narosa Publishing House
Date: 1998
Publisher: IEEE
Date: 12-2008
Publisher: IEEE
Date: 2005
Publisher: IEEE
Date: 12-2009
Publisher: Springer Science and Business Media LLC
Date: 09-2005
Publisher: Institution of Engineering and Technology (IET)
Date: 2008
Publisher: SPIE
Date: 10-01-1997
DOI: 10.1117/12.263233
Publisher: IEEE Comput. Soc
Date: 2003
Publisher: IEEE Comput. Soc. Press
Date: 1995
Publisher: IEEE
Date: 12-2007
Publisher: IEEE
Date: 12-2007
Publisher: SPIE
Date: 22-12-2001
DOI: 10.1117/12.410875
Publisher: Elsevier BV
Date: 02-2004
Publisher: IEEE Comput. Soc. Press
Date: 1996
Publisher: IEEE
Date: 2005
DOI: 10.1109/ICCV.2005.94
Publisher: IEEE
Date: 11-2009
Publisher: IEEE Comput. Soc
Date: 2003
Publisher: IEEE
Date: 12-2007
Publisher: IEEE
Date: 11-2008
Publisher: Springer Science and Business Media LLC
Date: 2001
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2012
Publisher: Springer Berlin Heidelberg
Date: 2007
Publisher: Springer Science and Business Media LLC
Date: 1992
DOI: 10.1007/BF00128131
Publisher: IEEE
Date: 12-2007
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2007
Abstract: Tracking objects in video using the mean shift (MS) technique has been the subject of considerable attention. In this work, we aim to remedy one of its shortcomings. MS, like other gradient ascent optimization methods, is designed to find local modes. In many situations, however, we seek the global mode of a density function. The standard MS tracker assumes that the initialization point falls within the basin of attraction of the desired mode. When tracking objects in video this assumption may not hold, particularly when the target's displacement between successive frames is large. In this case, the local and global modes do not correspond and the tracker is likely to fail. A novel multibandwidth MS procedure is proposed which converges to the global mode of the density function, regardless of the initialization point. We term the procedure annealed MS, as it shares similarities with the annealed importance s ling procedure. The bandwidth of the procedure plays the same role as the temperature in conventional annealing. We observe that an over-smoothed density function with a sufficiently large bandwidth is unimodal. Using a continuation principle, the influence of the global peak in the density function is introduced gradually. In this way, the global maximum is more reliably located. Since it is imperative that the computational complexity is minimal for real-time applications, such as visual tracking, we also propose an accelerated version of the algorithm. This significantly decreases the number of iterations required to achieve convergence. We show on various data sets that the proposed algorithm offers considerable promise in reliably and rapidly finding the true object location when initialized from a distant point.
Publisher: IEEE
Date: 11-2008
Publisher: Elsevier BV
Date: 12-1998
Publisher: IEEE
Date: 08-2007
DOI: 10.1109/ICIG.2007.64
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2014
Publisher: Elsevier BV
Date: 03-1992
Publisher: Elsevier BV
Date: 02-1986
Publisher: Elsevier BV
Date: 12-2008
Publisher: IEEE
Date: 12-2010
Publisher: SPIE-Intl Soc Optical Eng
Date: 21-03-2013
Publisher: SPIE
Date: 16-09-1994
DOI: 10.1117/12.186044
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2000
DOI: 10.1109/34.888714
Publisher: Springer Science and Business Media LLC
Date: 14-07-2007
Publisher: Springer Science and Business Media LLC
Date: 1997
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2004
DOI: 10.1109/TPAMI.2004.1262197
Abstract: Problems requiring accurate determination of parameters from image-based quantities arise often in computer vision. Two recent, independently developed frameworks for estimating such parameters are the FNS and HEIV schemes. Here, it is shown that FNS and a core version of HEIV are essentially equivalent, solving a common underlying equation via different means. The analysis is driven by the search for a nondegenerate form of a certain generalized eigenvalue problem and effectively leads to a new derivation of the relevant case of the HEIV algorithm. This work may be seen as an extension of previous efforts to rationalize and interrelate a spectrum of estimators, including the renormalization method of Kanatani and the normalized eight-point method of Hartley.
Publisher: Springer Science and Business Media LLC
Date: 13-03-2015
Publisher: IEEE
Date: 11-2006
DOI: 10.1109/AVSS.2006.33
Publisher: Optica Publishing Group
Date: 1994
Publisher: IEEE
Date: 2005
Publisher: IEEE
Date: 2005
Publisher: Optica Publishing Group
Date: 10-1997
Publisher: IEEE
Date: 2005
Publisher: SPIE
Date: 13-09-1995
DOI: 10.1117/12.220897
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2003
No related grants have been discovered for Michael Brooks.