Outdoor and Large-Scale Real-World Scene Analysis: 15th International Workshop on Theoretical Foundations of Computer Vision, Dagstuhl Castle, Germany, June 26 - July 1, 2011. Revised Selected Papers

Description

This book constitutes the thoroughly refereed post-proceedings of the 15th International Workshop on Theoretic Foundations of Computer Vision, held as a Dagstuhl Seminar in Dagstuhl Castle, Germany, in June/July 2011. The 19 revised full papers presented were carefully reviewed and selected after a blind peer-review process. The topic of this Workshop was Outdoor and Large-Scale Real-World Scene Analysis, which covers all aspects, applications and open problems regarding the performance or design of computer vision algorithms capable of working in outdoor setups and/or large-scale environments. Developing these methods is important for driver assistance, city modeling and reconstruction, virtual tourism, telepresence, and motion capture. Front Matter....Pages - Exploiting Pedestrian Interaction via Global Optimization and Social Behaviors....Pages 1-26 An Evaluation Framework for Stereo-Based Driver Assistance....Pages 27-51 Real-World Stereo-Analysis Evaluation....Pages 52-77 Pyramid Transform and Scale-Space Analysis in Image Analysis....Pages 78-109 Towards Feature-Based Situation Assessment for Airport Apron Video Surveillance....Pages 110-130 Generalized Subgraph Preconditioners for Large-Scale Bundle Adjustment....Pages 131-150 Achievements and Challenges in Recognizing and Reconstructing Civil Infrastructure....Pages 151-176 Equi-affine Invariant Geometries of Articulated Objects....Pages 177-190 Towards Fast Image-Based Localization on a City-Scale....Pages 191-211 Perspective and Non-perspective Camera Models in Underwater Imaging – Overview and Error Analysis....Pages 212-242 An Introduction to Random Forests for Multi-class Object Detection....Pages 243-263 Segmentation and Classification of Objects with Implicit Scene Context....Pages 264-284 Dense 3D Reconstruction from Wide Baseline Image Sets....Pages 285-304 Data-Driven Manifolds for Outdoor Motion Capture....Pages 305-328 On Performance Analysis of Optical Flow Algorithms....Pages 329-355 Camera-Based Fall Detection on Real World Data....Pages 356-375 Semantic Structure from Motion: A Novel Framework for Joint Object Recognition and 3D Reconstruction....Pages 376-397 Hierarchical Surface Reconstruction from Multi-resolution Point Samples....Pages 398-418 Traffic Observation and Situation Assessment....Pages 419-441 Back Matter....Pages -