Tracking Human Motion with Multiple Cameras Using an Articulated Model -- Shape Recovery of Specular Surface Using Color Highlight Stripe and Light Source Coding -- Geometric Mesh Denoising via Multivariate Kernel Diffusion -- Automatic Segmentation of Scanned Human Body Using Curve Skeleton Analysis -- Multi-view Player Action Recognition in Soccer Games -- Heart Cavity Segmentation in Ultrasound Images Based on Supervised Neural Networks -- Automatic Fitting of a Deformable Face Mask Using a Single Image -- Re-projective Pose Estimation of a Planar Prototype -- Tracking and Retexturing Cloth for Real-Time Virtual Clothing Applications -- A Novel Approach to Spatio-Temporal Video Analysis and Retrieval -- A Bag of Words Approach for 3D Object Categorization -- An Improved Structured Light Inspection of Specular Surfaces Based on Quaternary Coding -- Robust Detection and Tracking of Multiple Moving Objects with 3D Features by an Uncalibrated Monocular Camera -- Automatic Golf Ball Trajectory Reconstruction and Visualization -- Integrated Digital Image Correlation for the Identification of Mechanical Properties -- Recovery of 3D Solar Magnetic Field Model Parameter Using Image Structure Matching -- From Interactive Positioning to Automatic Try-On of Garments -- Level Set Segmentation of Knee Bones Using Normal Profile Models -- Detection of Overlapped Ellipses by Combining Region and Edge Data -- Flash Lighting Space Sampling -- Error Analysis of Stereo Calibration and Reconstruction -- Spatio-Temporal Tracking of Faces by Stereo Vision -- Spatio-Temporal Scene Analysis Based on Graph Algorithms to Determine Rigid and Articulated Objects -- Low-Cost Multi-image Based 3D Human Body Modeling -- Modified Histogram Based Fuzzy Filter -- Color Transfer in Images Based on Separation of Chromatic and Achromatic Colors -- Realistic Face Animation for Audiovisual Speech Applications: A Densification Approach Driven by Sparse Stereo Meshes -- Meshless Virtual Cloth -- New Human Face Expression Tracking -- A Model-Based Approach for Human Body Reconstruction from 3D Scanned Data -- Region-Based vs. Edge-Based Registration for 3D Motion Capture by Real Time Monoscopic Vision -- Supporting Diagnostics of Coronary Artery Disease with Multi-resolution Image Parameterization and Data Mining -- Interpreting Face Images by Fitting a Fast Illumination-Based 3D Active Appearance Model -- EEG Data Driven Animation and Its Application -- Facade Structure Parameterization Based on Similarity Detection from Single Image -- Epipolar Angular Factorisation of Essential Matrix for Camera Pose Calibration -- Integrated Noise Modeling for Image Sensor Using Bayer Domain Images -- Searching High-Dimensional Neighbours: CPU-Based Tailored Data-Structures Versus GPU-Based Brute-Force Method
Summary
This book constitutes the refereed proceedings of the 4th International Conference on Computer Vision/Computer Graphics Collaboration Techniques, MIRAGE 2009, held in Rocquencourt, France, in May 2009. The 41 revised full papers presented were carefully reviewed and selected from a total of 83 submissions. The papers cover a wide range of topics with focus on Computer Vision/Computer Graphics collaboration techniques involving image analysis/synthesis approaches especially concerning theoretical, computational, experimental or industrial aspects of model-based image analysis and image-based model synthesis
