British Machine Vision Conference 2000
نویسنده
چکیده
This edition of the IVC journal is devoted to some of the top-rated papers from BMVC2000, the 11th British Machine Vision Conference, hosted by the University of Bristol in September 2000. The conference coincided with a fuel shortage crisis, but there were no delegate cancellations and there were even some new registrations on the ®rst day. Altogether there were around 150 delegates from all over the UK as well as 18 other countries most of whom had contributed papers. In addition to the contributed papers at BMVC2000, there was a pre-conference tutorial presented by Prof. There were 149 original papers submitted to the conference for double-blind refereeing. Three referees reviewed each paper and a total of 38 oral papers and 42 poster papers were accepted. Updated versions of some of the highest ranking papers, as voted by the Programme Committee, were then selected and sent to totally new referees for further review for possible inclusion in this special issue. The papers that appear in this issue are a testament to the high quality of work regularly presented at BMVC conferences. Although a British conference, many papers are international , such as Ahmed and Farag from the USA, Rother from Sweden, or Kru Èger and Sommer from Germany in this issue. The standard is, as usual, internationally outstanding. Face and gesture recognition is currently a very popular area of research in computer vision and this is well represented in this special issue through papers by Bowden and Sarhadi, Cootes et al., Costen et al., and Kru Èger and Sommer concentrating mainly on building and manipulating models. For example, Cootes et al. extend their previous work and report on building models that represent the appearance of a face as seen from two or more different viewpoints simultaneously. There were also a signi®cant number of motion segmentation and tracking papers at the conference. Making a well-earned appearance here are the papers by Karaulova et al. presenting a hierarchical model of dynamics for tracking people with a single camera, also the winner of the best demonstration prize at the conference, the paper by Tweed and Calway on depth ordering of motion layers based on colour region segmentations with motion estimates obtained via block correlation , and the paper by Bromiley et al. who describe statistical techniques to isolate localised differences from global differences in motion sequences. Also Arbel and Ferrie present their interesting work …
منابع مشابه
3D reconstruction, omnidirectional vision and understanding of scenes
This text is related to the invited talk at the British Machine Vision Conference in Cardiff in September 2002 and highlights several recent contributions of our group to computer vision research. The aim is to hint the reader to several quite self-contained topics which we developed: omni-directional vision, scene reconstruction from images, and computational stereo. Pointer to results and ref...
متن کاملBritish Machine Vision Conference ( a )
We describe several established error of t (EOF) functions for use in the least square tting of ellipses, and introduce a further four new EOFs. Four measures are given for assessing the suitability of such EOFs, quantifying their linearity, curvature bias, asymmetry, and overall goodness. These measures enable a better understanding to be gained of the individual merits of the EOF functions.
متن کاملBritish Machine Vision Conference
In the context of part segmentation from 2D edge images, this paper presents some interesting results with a novel method that addresses the problem of ltering a redundant set of part hypotheses that retains only those that are likely to correspond to actual parts. In the proposed method, supporting evidence for hypotheses are put in competition in a Minimum Description-Length (MDL) framework t...
متن کاملBritish Machine Vision Conference 2 Distance Approximations
We describe several established error of t (EOF) functions for use in the least square tting of ellipses, and introduce a further four new EOFs. Four measures are given for assessing the suitability of such EOFs, quantifying their linearity, curvature bias, asymmetry, and overall goodness. These measures enable a better understanding to be gained of the individual merits of the EOF functions.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Image Vision Comput.
دوره 20 شماره
صفحات -
تاریخ انتشار 2002