Cremers / Rosenhahn / Yuille Statistical and Geometrical Approaches to Visual Motion Analysis

International Dagstuhl Seminar, Dagstuhl Castle, July 13-18, 2008, Revised Papers
2009
ISBN: 978-3-642-03061-1
Verlag: Springer
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 5604, 323 Seiten, eBook

Reihe: Lecture Notes in Computer Science

Zielgruppe

Research

Autoren/Hrsg.

Cremers, Daniel

Rosenhahn, Bodo

Yuille, Alan L.

Schmidt, Frank R.

Inhaltsverzeichnis

Optical Flow and Extensions.- Discrete-Continuous Optimization for Optical Flow Estimation.- An Improved Algorithm for TV-L 1 Optical Flow.- An Evaluation Approach for Scene Flow with Decoupled Motion and Position.- An Affine Optical Flow Model for Dynamic Surface Reconstruction.- Deinterlacing with Motion-Compensated Anisotropic Diffusion.- Human Motion Modeling.- Real-Time Synthesis of Body Movements Based on Learned Primitives.- 2D Human Pose Estimation in TV Shows.- Recognition and Synthesis of Human Movements by Parametric HMMs.- Recognizing Human Actions by Their Pose.- Biological and Statistical Approaches.- View-Based Approaches to Spatial Representation in Human Vision.- Combination of Geometrical and Statistical Methods for Visual Navigation of Autonomous Robots.- Motion Integration Using Competitive Priors.- Alternative Approaches to Motion Analysis.- Derivation of Motion Characteristics Using Affine Shape Adaptation for Moving Blobs.- Comparison of Point and Line Features and Their Combination for Rigid Body Motion Estimation.- The Conformal Monogenic Signal of Image Sequences.