This edited volume explores several issues relating to parametric segmentation including robust operations, model selection criteria and automatic model selection, plus 2D and 3D scene segmentation. Emphasis is placed on robust model selection with techniques such as robust Mallows Cp, least K-th order statistical model fitting (LKS), and robust regression receiving much attention. With contributions from leading researchers, this is a valuable resource for researchers and graduated students working in computer vision, pattern recognition, image processing and robotics.

The 2nd International Workshop on Statistical Methods in Video Processing, SMVP 2004, was held in Prague, Czech Republic, as an associated workshop of ECCV 2004, the 8th European Conference on Computer Vision. A total of 30 papers were submitted to the workshop. Of these, 17 papers were accepted for presentation and included in these proceedings, following a double-blind review process. The workshop had 42 registered participants. The focus of the meeting was on recent progress in the application of - vanced statistical methods to solve computer vision tasks. The one-day scienti?c program covered areas of high interest in vision research, such as dense rec- struction of 3D scenes, multibody motion segmentation, 3D shape inference, errors-in-variables estimation, probabilistic tracking, information fusion, optical ?owcomputation, learningfornonstationaryvideodata, noveltydetectionin- namic backgrounds, background modeling, grouping using feature uncertainty, and crowd segmentation from video. We wish to thank the authors of all submitted papers for their interest in the workshop.Wealsowishtothankthemembersofourprogramcommitteeandthe external reviewers for their commitment of time and e?ort in providing valuable recommendations for each submission. We are thankful to Vaclav Hlavac, the General Chair of ECCV 2004, and to Radim Sara, for the local organization of the workshop and registration management. We hope you will ?nd these proceedings both inspiring and of high scienti?c qualit

Outlier-contaminated data is a fact of life in computer vision. For computer vision applications to perform reliably and accurately in practical settings, the processing of the input data must be conducted in a robust manner. In this context, the maximum consensus robust criterion plays a critical role by allowing the quantity of interest to be estimated from noisy and outlier-prone visual measurements. The maximum consensus problem refers to the problem of optimizing the quantity of interest according to the maximum consensus criterion. This book provides an overview of the algorithms for performing this optimization. The emphasis is on the basic operation or "inner workings" of the algorithms, and on their mathematical characteristics in terms of optimality and efficiency. The applicability of the techniques to common computer vision tasks is also highlighted. By collecting existing techniques in a single article, this book aims to trigger further developments in this theoretically interesting and practically important area.