This book constitutes the refereed proceedings of the Third Pacific Rim Symposium on Image and Video Technology, PSIVT 2008, held in Tokyo, Japan, in January 2009.
The 39 revised full papers and 57 posters were carefully reviewed and selected from 247 submissions. The symposium features 8 major themes including all aspects of image and video technology: image sensors and multimedia hardware; graphics and visualization; image and video analysis; recognition and retrieval; multi-view imaging and processing; computer vision applications; video communications and networking; and multimedia processing. The papers are organized in topical sections on faces and pedestrians; panoramic images; local image analysis; organization and grouping; multiview geometry; detection and tracking; computational photography and forgeries; coding and steganography; recognition and search; and reconstruction and visualization.
Inhalt
Faces and Pedestrians.- A Self-tuning People Identification System from Split Face Components.- Using Face Quality Ratings to Improve Real-Time Face Recognition.- A Method for Visualizing Pedestrian Traffic Flow Using SIFT Feature Point Tracking.- Co-occurrence Histograms of Oriented Gradients for Pedestrian Detection.- Panoramic Images.- Sensor Pose Estimation from Multi-center Cylindrical Panoramas.- Monocular 3D Reconstruction of Objects Based on Cylindrical Panoramas.- Omnidirectional Image Stabilization by Computing Camera Trajectory.- Local Image Analysis.- Rotation and Scale Invariant Texture Analysis with Tunable Gabor Filter Banks.- Local Image Descriptors Using Supervised Kernel ICA.- Fast Simplex Optimization for Active Appearance Model.- LazySOM: Image Compression Using an Enhanced Self-Organizing Map.- Organization and Grouping.- Inverse Halftoning Based on Bayesian Theorem.- Live Video Segmentation in Dynamic Backgrounds Using Thermal Vision.- Image-Based Techniques for Shredded Document Reconstruction.- Contour Grouping with Partial Shape Similarity.- Multiview Geometry.- Compact Fundamental Matrix Computation.- Detecting Incorrect Feature Tracking by Affine Space Fitting.- Outlier Removal by Convex Optimization for L-Infinity Approaches.- The Five Points Pose Problem: A New and Accurate Solution Adapted to Any Geometric Configuration.- Detection and Tracking.- Vehicle Detection from Aerial Images Using Local Shape Information.- Estimating 3D Flow for Driver Assistance Applications.- A New Method for Moving Object Extraction and Tracking Based on the Exclusive Block Matching.- Visual Tracking Using Particle Filters with Gaussian Process Regression.- Computational Photography and Forgeries.- Image Inpainting Considering Brightness Change and Spatial Locality of Textures and Its Evaluation.- A Digital Image Denoising Method with Edge Preservation Using Dyadic Lifting Schemes.- A Self-governing Hybrid Model for Noise Removal.- Detecting Video Forgeries Based on Noise Characteristics.- Coding and Steganography.- An Approach to Trajectory Estimation of Moving Objects in the H.264 Compressed Domain.- Enhanced Side Information Generator with Accurate Evaluations in Block-Based Wyner-Ziv Video Coding.- Watermarking of Raw Digital Images in Camera Firmware: Embedding and Detection.- An Advanced Least-Significant-Bit Embedding Scheme for Steganographic Encoding.- Recognition and Search.- Can Geotags Help Image Recognition?.- Principal Component Hashing: An Accelerated Approximate Nearest Neighbor Search.- Novel Approaches for Exclusive and Continuous Fingerprint Classification.- A Novel Visual Speech Representation and HMM Classification for Visual Speech Recognition.- Reconstruction and Visualization.- Shape Reconstruction by Combination of Structured-Light Projection and Photometric Stereo Using a Projector-Camera System.- Image-Based Rendering by Virtual 1D Cameras.- Implicit Surface Reconstruction with an Analogy of Polar Field Model.- Dense Stereo Correspondence with Contrast Context Histogram, Segmentation-Based Two-Pass Aggregation and Occlusion Handling.- Poster 1.- SUBSMELL: Multimedia with a Simple Olfactory Display.- Fixed-Coefficient Iterative Bilateral Filters for Graph-Based Image Processing.- Texture Retrieval Effectiveness Improvement Using Multiple Representations Fusion.- Recognizing Multiple Objects via Regression Incorporating the Co-occurrence of Categories.- An Adaptive and Efficient Selective Multiple Reference Frames Motion Estimation for H.264 Video Coding.- A Framework for Suspicious Action Detection with Mixture Distributions of Action Primitives.- Framework for Illumination Invariant Vehicular Traffic Density Estimation.- Robust Facial Feature Location on Gray Intensity Face.- Error-Diffused Image Security Improving Using Overall Minimal-Error Searching.- Automatic Segmentation of Non-rigid Objects in Image Sequences Using Spatiotemporal Information.- Robust Simultaneous Low Rank Approximation of Tensors.- Video-Based Modeling of Dynamic Hair.- Optimal Pixel Matching between Images.- Moving Object Segmentation Using Optical Flow and Depth Information.- Usefulness of Retina Codes in Biometrics.- Inclusion of a Second-Order Prior into Semi-Global Matching.- Object Detection under Varying Illumination Based on Adaptive Background Modeling Considering Spatial Locality.- Accelerating Face Detection by Using Depth Information.- Rotated Image Based Photomosaic Using Combination of Principal Component Hashing.- Poster 2.- A Stereo Self-adjustment Methodology for Resuming Active Camera Operation.- Combining Invariant and Corner-Like Features to Optimize Image Matching.- Integrated Expression-Invariant Face Recognition with Constrained Optical Flow.- Automatic Eigentemplate Learning for Sparse Template Tracker.- Tracking without Background Model for Time-of-Flight Cameras.- X-Ray Image Classification and Retrieval Using Ensemble Combination of Visual Descriptors.- Video-Based Motion Capturing for Skeleton-Based 3D Models.- Player Detection and Tracking in Broadcast Tennis Video.- Unsupervised Pedestrian Re-identification for Loitering Detection.- A Fast Macroblock Mode Decision Algorithm for the Baseline Profile in the H.264 Video Coding Standard.- Video Coding Using Spatially Varying Transform.- Comparison of Visible, Thermal Infra-Red and Range Images for Face Recognition.- Enhanced Sports Image Annotation and Retrieval Based Upon Semantic Analysis of Multimodal Cues.- Memory Efficient VLSI Architecture for QCIF to VGA Resolution Conversion.- Towards an Interpretation of Intestinal Motility Using Capsule Endoscopy Image Sequences.- On JPEG2000 Error Concealment Attacks.- Upper-Body Contour Extraction Using Face and Body Shape Variance Information.- Approximated Ground Truth for Stereo and Motion Analysis on Real-World Sequences.- Cooperative Surveillance System with Fixed Camera Object Localization and Mobile Robot Target Tracking.- Poster 3.- On the Security of an MPEG-Video Encryption Scheme Based on Secret Huffman Tables.- H.264/AVC Video Encoder Realization and Acceleration on TI DM642 DSP.- Improved Two-Level Model Averaging Techniques in Drosophila Brain Modeling.- Belief Propagation for Stereo Analysis of Night-Vision Sequences.- Region-Based Super Resolution for Video Sequences Considering Registration Error.- A High Performance H.264 Deblocking Filter.- Steganalysis of JPEG Images with Joint Transform Features.- Hardware Design of Shape-Preserving Contour Tracing for Object of Segmented Images.- Weighted Threshold Secret Image Sharing.- Removal of Specular Reflection Component Using Multi-view Images and 3D Object Model.- An ROI/xROI Based Rate Control Algorithm in H.264|AVC for Video Telephony Applications.- Simplifying the Rate Control Scheme for Distributed Video Coding by Flexible Slepian-Wolf Decoding.- Glass Patterns and Artistic Imaging.- Classification of Similar 3D Objects with Different Types of Features from Multi-view Images.- Recovery Rate of Clustering Algorithms.- Multiple V…