Computer Vision: Accv 2007

ISBN-13: 9783540763857 / Angielski / Miękka / 2007 / 994 str.

Sing Bing Kang

Opis

This title is part of a two volume set that constitutes the refereed proceedings of the 8th Asian Conference on Computer Vision, ACCV 2007. Coverage in this volume includes shape and texture, face and gesture, camera networks, face/gesture/action detection and recognition, learning, motion and tracking, human pose estimation, matching, face/gesture/action detection and recognition, low level vision and phtometory, motion and tracking, human detection, and segmentation.

Spis treści

Plenary and Invited Talks.- Less Is More: Coded Computational Photography.- Optimal Algorithms in Multiview Geometry.- Machine Vision in Early Days: Japan’s Pioneering Contributions.- Shape and Texture.- Coarse-to-Fine Statistical Shape Model by Bayesian Inference.- Efficient Texture Representation Using Multi-scale Regions.- Fitting.- Comparing Timoshenko Beam to Energy Beam for Fitting Noisy Data.- A Family of Quadratic Snakes for Road Extraction.- Poster Session 1: Calibration.- Multiperspective Distortion Correction Using Collineations.- Camera Calibration from Silhouettes Under Incomplete Circular Motion with a Constant Interval Angle.- Mirror Localization for Catadioptric Imaging System by Observing Parallel Light Pairs.- Calibrating Pan-Tilt Cameras with Telephoto Lenses.- Camera Calibration Using Principal-Axes Aligned Conics.- Poster Session 1: Detection.- 3D Intrusion Detection System with Uncalibrated Multiple Cameras.- Non-parametric Background and Shadow Modeling for Object Detection.- Road Sign Detection Using Eigen Color.- Localized Content-Based Image Retrieval Using Semi-Supervised Multiple Instance Learning.- Object Detection Combining Recognition and Segmentation.- An Efficient Method for Text Detection in Video Based on Stroke Width Similarity.- Multiview Pedestrian Detection Based on Vector Boosting.- Pedestrian Detection Using Global-Local Motion Patterns.- Poster Session 1: Image and Video Processing.- Qualitative and Quantitative Behaviour of Geometrical PDEs in Image Processing.- Automated Billboard Insertion in Video.- Improved Background Mixture Models for Video Surveillance Applications.- High Dynamic Range Scene Realization Using Two Complementary Images.- Automated Removal of Partial Occlusion Blur.- Poster Session 1: Applications.- High Capacity Watermarking in Nonedge Texture Under Statistical Distortion Constraint.- Attention Monitoring for Music Contents Based on Analysis of Signal-Behavior Structures.- View Planning for Cityscape Archiving and Visualization.- Face and Gesture.- Synthesis of Exaggerative Caricature with Inter and Intra Correlations.- Pose-Invariant Facial Expression Recognition Using Variable-Intensity Templates.- Gesture Recognition Under Small Sample Size.- Tracking.- Motion Observability Analysis of the Simplified Color Correlogram for Visual Tracking.- On-Line Ensemble SVM for Robust Object Tracking.- Multi-camera People Tracking by Collaborative Particle Filters and Principal Axis-Based Integration.- Poster Session 2: Camera Networks.- Finding Camera Overlap in Large Surveillance Networks.- Information Fusion for Multi-camera and Multi-body Structure and Motion.- Task Scheduling in Large Camera Networks.- Poster Session 2: Face/Gesture/Action Detection and Recognition.- Constrained Optimization for Human Pose Estimation from Depth Sequences.- Generative Estimation of 3D Human Pose Using Shape Contexts Matching.- An Active Multi-camera Motion Capture for Face, Fingers and Whole Body.- Tracking and Classifying of Human Motions with Gaussian Process Annealed Particle Filter.- Gait Identification Based on Multi-view Observations Using Omnidirectional Camera.- Gender Classification Based on Fusion of Multi-view Gait Sequences.- Poster Session 2: Learning.- MAPACo-Training: A Novel Online Learning Algorithm of Behavior Models.- Optimal Learning High-Order Markov Random Fields Priors of Colour Image.- Hierarchical Learning of Dominant Constellations for Object Class Recognition.- Multistrategical Approach in Visual Learning.- Poster Session 2: Motion and Tracking.- Cardiac Motion Estimation from Tagged MRI Using 3D-HARP and NURBS Volumetric Model.- Fragments Based Parametric Tracking.- Spatiotemporal Oriented Energy Features for Visual Tracking.- Synchronized Ego-Motion Recovery of Two Face-to-Face Cameras.- Optical Flow–Driven Motion Model with Automatic Variance Adjustment for Adaptive Tracking.- A Noise-Insensitive Object Tracking Algorithm.- Discriminative Mean Shift Tracking with Auxiliary Particles.- Poster Session 2: Retrival and Search.- Efficient Search in Document Image Collections.- Human Pose Estimation.- Hand Posture Estimation in Complex Backgrounds by Considering Mis-match of Model.- Learning Generative Models for Monocular Body Pose Estimation.- Human Pose Estimation from Volume Data and Topological Graph Database.- Matching.- Logical DP Matching for Detecting Similar Subsequence.- Efficient Normalized Cross Correlation Based on Adaptive Multilevel Successive Elimination.- Exploiting Inter-frame Correlation for Fast Video to Reference Image Alignment.- Poster Session 3: Face/Gesture/Action Detection and Recognition.- Flea, Do You Remember Me?.- Multi-view Gymnastic Activity Recognition with Fused HMM.- Real-Time and Marker-Free 3D Motion Capture for Home Entertainment Oriented Applications.- Tracking Iris Contour with a 3D Eye-Model for Gaze Estimation.- Eye Correction Using Correlation Information.- Eye-Gaze Detection from Monocular Camera Image Using Parametric Template Matching.- An FPGA-Based Smart Camera for Gesture Recognition in HCI Applications.- Poster Session 3: Low Level Vision and Phtometory.- Color Constancy Via Convex Kernel Optimization.- User-Guided Shape from Shading to Reconstruct Fine Details from a Single Photograph.- A Theoretical Approach to Construct Highly Discriminative Features with Application in AdaBoost.- Robust Foreground Extraction Technique Using Gaussian Family Model and Multiple Thresholds.- Feature Management for Efficient Camera Tracking.- Measurement of Reflection Properties in Ancient Japanese Drawing Ukiyo-e.- Texture-Independent Feature-Point Matching (TIFM) from Motion Coherence.- Where’s the Weet-Bix?.- How Marginal Likelihood Inference Unifies Entropy, Correlation and SNR-Based Stopping in Nonlinear Diffusion Scale-Spaces.- Poster Session 3: Motion and Tracking.- Kernel-Bayesian Framework for Object Tracking.- Markov Random Field Modeled Level Sets Method for Object Tracking with Moving Cameras.- Continuously Tracking Objects Across Multiple Widely Separated Cameras.- Adaptive Multiple Object Tracking Using Colour and Segmentation Cues.- Image Assimilation for Motion Estimation of Atmospheric Layers with Shallow-Water Model.- Probability Hypothesis Density Approach for Multi-camera Multi-object Tracking.- Human Detection.- AdaBoost Learning for Human Detection Based on Histograms of Oriented Gradients.- Multi-posture Human Detection in Video Frames by Motion Contour Matching.- A Cascade of Feed-Forward Classifiers for Fast Pedestrian Detection.- Combined Object Detection and Segmentation by Using Space-Time Patches.- Segmentation.- Embedding a Region Merging Prior in Level Set Vector-Valued Image Segmentation.- A Basin Morphology Approach to Colour Image Segmentation by Region Merging.- Detecting and Segmenting Un-occluded Items by Actively Casting Shadows.- A Local Probabilistic Prior-Based Active Contour Model for Brain MR Image Segmentation.