Computer Vision -- ACCV 2009: 9th Asian Conference on Computer Vision, Xi'an, China, September 23-27, 2009, Revised Selected Papers, Part II(Image Processing, Computer Vision, Pattern Recognition, and Graphics)

It givesus greatpleasureto presentthe proceedings of the 9th Asian Conference on Computer Vision (ACCV 2009), held in Xi’an, China, in September 2009. This was the ?rst ACCV conference to take place in mainland China. We received a total of 670 full submissions, which is a new record in the ACCV series. Overall, 35 papers were selected for oral presentation and 131 as posters, yielding acceptance rates of 5.2% for oral, 19.6% for poster, and 24.8% in total. In the paper reviewing, we continued the tradition of previous ACCVsbyconductingtheprocessinadouble-blindmanner.Eachofthe33Area Chairs received a pool of about 20 papers and nominated a number of potential reviewers for each paper. Then, Program Committee Chairs allocated at least three reviewers to each paper, taking into consideration any con?icts of interest and the balance of loads. Once the reviews were ?nished, the Area Chairs made summaryreportsforthepapersintheirpools,basedonthereviewers’comments and on their own assessments of the papers.

Table of Contents:
Poster Session 1: Stereo, Motion Analysis, and Tracking.- A Dynamic Programming Approach to Maximizing Tracks for Structure from Motion.- Dense and Accurate Spatio-temporal Multi-view Stereovision.- Semi-supervised Feature Selection for Gender Classification.- Planar Scene Modeling from Quasiconvex Subproblems.- Fast Depth Map Compression and Meshing with Compressed Tritree.- A Three-Phase Approach to Photometric Calibration for Multi-projector Display Using LCD Projectors.- Twisted Cubic: Degeneracy Degree and Relationship with General Degeneracy.- Two-View Geometry and Reconstruction under Quasi-perspective Projection.- Similarity Scores Based on Background Samples.- Human Action Recognition Using Spatio-temporal Classification.- Face Alignment Using Boosting and Evolutionary Search.- Tracking Eye Gaze under Coordinated Head Rotations with an Ordinary Camera.- Orientation and Scale Invariant Kernel-Based Object Tracking with Probabilistic Emphasizing.- Combining Edge and Color Features for Tracking Partially Occluded Humans.- Incremental Multi-view Face Tracking Based on General View Manifold.- Hierarchical Model for Joint Detection and Tracking of Multi-target.- Heavy-Tailed Model for Visual Tracking via Robust Subspace Learning.- Efficient Scale-Space Spatiotemporal Saliency Tracking for Distortion-Free Video Retargeting.- Visual Saliency Based Object Tracking.- People Tracking and Segmentation Using Efficient Shape Sequences Matching.- Monocular Template-Based Tracking of Inextensible Deformable Surfaces under L 2-Norm.- A Graph-Based Feature Combination Approach to Object Tracking.- A Smarter Particle Filter.- Robust Real-Time Multiple Target Tracking.- Dynamic Kernel-Based Progressive Particle Filter for 3D Human Motion Tracking.- Bayesian 3D Human Body Pose Tracking from Depth Image Sequences.- Crowd Flow Characterization with Optimal Control Theory.- Human Action Recognition Using HDP by Integrating Motion and Location Information.- Detecting Spatiotemporal Structure Boundaries: Beyond Motion Discontinuities.- An Accelerated Human Motion Tracking System Based on Voxel Reconstruction under Complex Environments.- Automated Center of Radial Distortion Estimation, Using Active Targets.- Rotation Averaging with Application to Camera-Rig Calibration.- Single-Camera Multi-baseline Stereo Using Fish-Eye Lens and Mirrors.- Generation of an Omnidirectional Video without Invisible Areas Using Image Inpainting.- Accurate and Efficient Cost Aggregation Strategy for Stereo Correspondence Based on Approximated Joint Bilateral Filtering.- Detecting Critical Configurations for Dividing Long Image Sequences for Factorization-Based 3-D Scene Reconstruction.- Scene Gist: A Holistic Generative Model of Natural Image.- A Robust Algorithm for Color Correction between Two Stereo Images.- Efficient Human Action Detection Using a Transferable Distance Function.- Crease Detection on Noisy Meshes via Probabilistic Scale Selection.- Improved Uncalibrated View Synthesis by Extended Positioning of Virtual Cameras and Image Quality Optimization.- Region Based Color Image Retrieval Using Curvelet Transform.- Extracting Spatio-temporal Local Features Considering Consecutiveness of Motions.- Multi-view Texturing of Imprecise Mesh.- Poster Session 2: Segmentation, Detection, Color and Texture.- Semantic Classification in Aerial Imagery by Integrating Appearance and Height Information.- Real-Time Video Matting Based on Bilayer Segmentation.- Transductive Segmentation of Textured Meshes.- Levels of Details for Gaussian Mixture Models.- A Blind Robust WatermarkingScheme Based on ICA and Image Dividing Blocks.- MIFT: A Mirror Reflection Invariant Feature Descriptor.- Detection of Vehicle Manufacture Logos Using Contextual Information.- Part-Based Object Detection Using Cascades of Boosted Classifiers.- A Novel Self-created Tree Structure Based Multi-view Face Detection.- Multilinear Nonparametric Feature Analysis.- A Harris-Like Scale Invariant Feature Detector.- Probabilistic Cascade Random Fields for Man-Made Structure Detection.- A Novel System for Robust Text Location and Recognition of Book Covers.- A Multi-scale Bilateral Structure Tensor Based Corner Detector.- Pedestrian Recognition Using Second-Order HOG Feature.- Fabric Defect Detection and Classification Using Gabor Filters and Gaussian Mixture Model.- Moving Object Segmentation in the H.264 Compressed Domain.- Video Segmentation Using Iterated Graph Cuts Based on Spatio-temporal Volumes.- Spectral Graph Partitioning Based on a Random Walk Diffusion Similarity Measure.- Iterated Graph Cuts for Image Segmentation.- Contour Extraction Based on Surround Inhibition and Contour Grouping.- Confidence-Based Color Modeling for Online Video Segmentation.- Multicue Graph Mincut for Image Segmentation.