Computer Vision - ACCV 2010: 10th Asian Conference on Computer Vision, Queenstown, New Zealand, November 8-12, 2010, Revised Selected Papers, Part III (Lecture Notes in Computer Science)

Annotation The four-volume set LNCS 6492-6495 constitutes the thoroughly refereed post-proceedings of the 10th Asian Conference on Computer Vision, ACCV 2009, held in Queenstown, New Zealand in November 2010. All together the four volumes present 206 revised papers selected from a total of 739 Submissions. All current issues in computer vision are addressed ranging from algorithms that attempt to automatically understand the content of images, optical methods coupled with computational techniques that enhance and improve images, and capturing and analyzing the world's geometry while preparing the higher level image and shape understanding. Novel gemometry techniques, statistical learning methods, and modern algebraic procedures are dealt with as well Front Matter....Pages - Approximate and SQP Two View Triangulation....Pages 1-14 Adaptive Motion Segmentation Algorithm Based on the Principal Angles Configuration....Pages 15-26 Real-Time Detection of Small Surface Objects Using Weather Effects....Pages 27-38 Automating Snakes for Multiple Objects Detection....Pages 39-51 Monocular Template-Based Reconstruction of Smooth and Inextensible Surfaces....Pages 52-66 Multi-class Leveraged κ -NN for Image Classification....Pages 67-81 Video Based Face Recognition Using Graph Matching....Pages 82-94 A Hybrid Supervised-Unsupervised Vocabulary Generation Algorithm for Visual Concept Recognition....Pages 95-108 Image Inpainting Based on Probabilistic Structure Estimation....Pages 109-120 Text Localization and Recognition in Complex Scenes Using Local Features....Pages 121-132 Pyramid-Based Multi-structure Local Binary Pattern for Texture Classification....Pages 133-144 Unsupervised Moving Object Detection with On-line Generalized Hough Transform....Pages 145-156 Interactive Event Search through Transfer Learning....Pages 157-170 A Compositional Exemplar-Based Model for Hair Segmentation....Pages 171-184 Descriptor Learning Based on Fisher Separation Criterion for Texture Classification....Pages 185-198 Semi-supervised Neighborhood Preserving Discriminant Embedding: A Semi-supervised Subspace Learning Algorithm....Pages 199-212 Segmentation via NCuts and Lossy Minimum Description Length: A Unified Approach....Pages 213-224 A Phase Discrepancy Analysis of Object Motion....Pages 225-238 Image Classification Using Spatial Pyramid Coding and Visual Word Reweighting....Pages 239-249 Class-Specific Low-Dimensional Representation of Local Features for Viewpoint Invariant Object Recognition....Pages 250-261 Learning Non-coplanar Scene Models by Exploring the Height Variation of Tracked Objects....Pages 262-275 Optimal Regions for Linear Model-Based 3D Face Reconstruction....Pages 276-289 Color Kernel Regression for Robust Direct Upsampling from Raw Data of General Color Filter Array....Pages 290-301 The Large-Scale Crowd Density Estimation Based on Effective Region Feature Extraction Method....Pages 302-313 TILT: Transform Invariant Low-Rank Textures....Pages 314-328 Translation-Symmetry-Based Perceptual Grouping with Applications to Urban Scenes....Pages 329-342 Towards Hypothesis Testing and Lossy Minimum Description Length: A Unified Segmentation Framework....Pages 343-354 A Convex Image Segmentation: Extending Graph Cuts and Closed-Form Matting....Pages 355-368 Linear Solvability in the Viewing Graph....Pages 369-381 Inference Scene Labeling by Incorporating Object Detection with Explicit Shape Model....Pages 382-395 Saliency Density Maximization for Object Detection and Localization....Pages 396-408 Modified Hybrid Bronchoscope Tracking Based on Sequential Monte Carlo Sampler: Dynamic Phantom Validation....Pages 409-421 Affine Warp Propagation for Fast Simultaneous Modelling and Tracking of Articulated Objects....Pages 422-435 kPose: A New Representation For Action Recognition....Pages 436-447 Identifying Surprising Events in Videos Using Bayesian Topic Models....Pages 448-459 Face Detection with Effective Feature Extraction....Pages 460-470 Multiple Order Graph Matching....Pages 471-482 Abstraction and Generalization of 3D Structure for Recognition in Large Intra-Class Variation....Pages 483-496 Exploiting Self-similarities for Single Frame Super-Resolution....Pages 497-510 On Feature Combination and Multiple Kernel Learning for Object Tracking....Pages 511-522 Correspondence-Free Multi Camera Calibration by Observing a Simple Reference Plane....Pages 523-534 Over-Segmentation Based Background Modeling and Foreground Detection with Shadow Removal by Using Hierarchical MRFs....Pages 535-546 MRF-Based Background Initialisation for Improved Foreground Detection in Cluttered Surveillance Videos....Pages 547-559 Adaptive ε LBP for Background Subtraction....Pages 560-571 Continuous Surface-Point Distributions for 3D Object Pose Estimation and Recognition....Pages 572-585 Efficient Structured Support Vector Regression....Pages 586-598 Cage-Based Tracking for Performance Animation....Pages 599-612 Modeling Dynamic Scenes Recorded with Freely Moving Cameras....Pages 613-626 Learning Image Structures for Optimizing Disparity Estimation....Pages 627-640 Image Reconstruction for High-Sensitivity Imaging by Using Combined Long/Short Exposure Type Single-Chip Image Sensor....Pages 641-652 On the Use of Implicit Shape Models for Recognition of Object Categories in 3D Data....Pages 653-666 Phase Registration of a Single Quasi-Periodic Signal Using Self Dynamic Time Warping....Pages 667-678 Latent Gaussian Mixture Regression for Human Pose Estimation....Pages 679-690 Top-Down Cues for Event Recognition....Pages 691-702 Robust Photometric Stereo via Low-Rank Matrix Completion and Recovery....Pages 703-717 Robust Auxiliary Particle Filter with an Adaptive Appearance Model for Visual Tracking....Pages 718-731 Sustained Observability for Salient Motion Detection....Pages 732-743 Markerless and Efficient 26-DOF Hand Pose Recovery....Pages 744-757 Stick It! Articulated Tracking Using Spatial Rigid Object Priors....Pages 758-769 A Method for Text Localization and Recognition in Real-World Images....Pages 770-783 Back Matter....Pages -