The four-volume set comprising LNCS volumes 3951/3952/3953/3954 constitutes the refereed proceedings of the 9th European Conference on Computer Vision, ECCV 2006. The 192 papers presented cover the entire range of current issues in computer vision. The papers are organized in topical sections on recognition, statistical models and visual learning, 3D reconstruction and multi-view geometry, energy minimization, tracking and motion, segmentation, shape from X, visual tracking, face detection and recognition, and more.

Inhalt

Recognition I.- TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation.- Weakly Supervised Learning of Part-Based Spatial Models for Visual Object Recognition.- Hyperfeatures - Multilevel Local Coding for Visual Recognition.- Statistical Models and Visual Learning.- Riemannian Manifold Learning for Nonlinear Dimensionality Reduction.- Controlling Sparseness in Non-negative Tensor Factorization.- Conditional Infomax Learning: An Integrated Framework for Feature Extraction and Fusion.- Poster Session I.- Degen Generalized Cylinders and Their Properties.- Geodesics Between 3D Closed Curves Using Path-Straightening.- Robust Homography Estimation from Planar Contours Based on Convexity.- Detecting Instances of Shape Classes That Exhibit Variable Structure.- Direct Solutions for Computing Cylinders from Minimal Sets of 3D Points.- Estimation of Multiple Periodic Motions from Video.- Robust Multi-body Motion Tracking Using Commute Time Clustering.- A Tuned Eigenspace Technique for Articulated Motion Recognition.- Real-Time Non-rigid Shape Recovery Via Active Appearance Models for Augmented Reality.- A Fluid Motion Estimator for Schlieren Image Velocimetry.- Bilateral Filtering-Based Optical Flow Estimation with Occlusion Detection.- Geometry and Kinematics with Uncertain Data.- Euclidean Structure from N ? 2 Parallel Circles: Theory and Algorithms.- Overconstrained Linear Estimation of Radial Distortion and Multi-view Geometry.- Camera Calibration with Two Arbitrary Coaxial Circles.- Molding Face Shapes by Example.- Reconstruction of Canal Surfaces from Single Images Under Exact Perspective.- Subspace Estimation Using Projection Based M-Estimators over Grassmann Manifolds.- Learning 2D Hand Shapes Using the Topology Preservation Model GNG.- Towards Optimal Training of Cascaded Detectors.- Learning and Incorporating Top-Down Cues in Image Segmentation.- Learning to Detect Objects of Many Classes Using Binary Classifiers.- A Unifying Framework for Mutual Information Methods for Use in Non-linear Optimisation.- Random Walks, Constrained Multiple Hypothesis Testing and Image Enhancement.- From Tensor-Driven Diffusion to Anisotropic Wavelet Shrinkage.- SURF: Speeded Up Robust Features.- Top-Points as Interest Points for Image Matching.- Machine Learning for High-Speed Corner Detection.- Smooth Image Segmentation by Nonparametric Bayesian Inference.- Shape Analysis and Fuzzy Control for 3D Competitive Segmentation of Brain Structures with Level Sets.- Variational Motion Segmentation with Level Sets.- Ellipse Fitting with Hyperaccuracy.- A Physically-Motivated Deformable Model Based on Fluid Dynamics.- Video and Image Bayesian Demosaicing with a Two Color Image Prior.- Generalized Multi-sensor Planning.- Variational Shape and Reflectance Estimation Under Changing Light and Viewpoints.- Specularity Removal in Images and Videos: A PDE Approach.- 3D Reconstruction and Multi-view Geometry.- Carved Visual Hulls for Image-Based Modeling.- What Is the Range of Surface Reconstructions from a Gradient Field?.- Practical Global Optimization for Multiview Geometry.- Perspective n-View Multibody Structure-and-Motion Through Model Selection.- Confocal Stereo.