Computer Vision -- ACCV 2010 Workshops
ACCV 2010 International Workshops. Queenstown, New Zealand, November 8-9, 2010. Revised Selected Papers, Part II
Published on 15. September 2011
XXX, 439 pages
978-3-642-22819-3 (ISBN)
Description
The two-volume set LNCS 6468-6469 contains the carefully selected and reviewed papers presented at the eight workshops that were held in conjunction with the 10th Asian Conference on Computer Vision, in Queenstown, New Zealand, in November 2010.
From a total of 167 submissions to all workshops, 89 papers were selected for publication. The contributions are grouped together according to the main workshops topics, which were: computational photography and aesthetics; computer vision in vehicle technology: from Earth to Mars; electronic cultural heritage; subspace based methods; video event categorization, tagging and retrieval; visual surveillance; application of computer vision for mixed and augmented reality.
More details
Other editions
Additional editions
Reinhard Koch | Fay Huang
Computer Vision -- ACCV 2010 Workshops
ACCV 2010 International Workshops. Queenstown, New Zealand, November 8-9, 2010. Revised Selected Papers, Part II
Book
09/2011
1st Edition
Springer
€53.49
Shipment within 7-9 days
Content
- Title
- Preface
- Table of Contents
- Workshop on Application of Computer Vision for Mixed and Augmented Reality
- Computer Vision Technology Applied to MR-Based Pre-visualization in Filmmaking
- Introduction
- Overview of the CREST/MR-PreViz Project
- Significance of MR Technology for PreViz
- Workflow of Filmmaking with MR-PreViz
- CV Technologies in MR-PreViz (1)?|3D Video
- Introduction of 3D Video
- Technical Highlights of 3D Video as a Computer Vision Research
- 3D Video for MR-PreViz
- Camera Tracking Using Landmark Database
- Registration Method Using Landmark Database
- Rehearsal Path Method: Refinement of the Registration Method Using LMDB
- CV Technologies in MR-PreViz (3) - IBL and Relighting
- Conclusions
- References
- Model Based Pose Estimation Using SURF
- Introduction
- Related Work
- Model Definition
- Automatic Model Generation from Images
- Initialization
- Incremental Expansion of the Model
- Model Based Pose Estimation
- Matching
- Pose Estimation
- Model Integration
- Evaluation
- Exemplary Models
- Model Accuracy
- Robustness of the Pose Estimation
- Conclusion
- References
- Real-Time Camera Tracking Using a Global Localization Scheme
- Introduction
- SLAM and Its Varieties
- Global Localization Scheme
- Signature Descriptor
- Game Theoretic Approach
- Experiments and Results
- Matching Performance
- Timing
- Tracking Result
- Conclusion
- References
- Visual Mapping and Multi-modal Localisation for Anywhere AR Authoring
- Anywhere Authoring
- Related Work
- Operational Overview
- Multi-modal Positioning
- Visual Mapping and Relocalisation
- Single Map Relocalisation
- Multiple Maps Relocalisation
- Experiments with Multiple Maps Relocalisation
- Demonstration
- Conclusions
- References
- Augmented Reality System for Visualizing 3-D Region of Interest in Unknown Environment
- Introduction
- Relation to Other Works
- Prototype System Visualizing 3-D Region of Interest
- System Overview
- Detail of Surface Labeling
- Experiment
- Steps toward the Practical Use
- System Initialization
- Density of Reconstructed Points
- Scale-Dependency of Coefficients
- Mesh Segmentation Cue
- ROI Recognition Cue
- Conclusion
- References
- Interactive Video Layer Decomposition and Matting
- Introduction
- Related Work
- Video Decomposition
- User-Assisted Layer Refinement
- Spatial-Temporal Layer Propagation
- Experimental Results
- Conclusion
- References
- Removal of Moving Objects and Inconsistencies in Color Tone for an Omnidirectional Image Database
- Introduction
- Removal of Moving Object and Inconsistencies in Color Tone for Omnidirectional Image Database
- Outline of the Proposed Method
- Pre-processing: Removal of Exceptive Regions for Iteration Process
- Iteration Processing: Estimation of Candidate Region of Moving Object and Linear Color Transformation Parameters
- Post-processing: Compensation of Moving Objects
- Experiments
- Experimental Environment
- Experimental Results
- Conclusion
- References
- Shape Prior Embedded Geodesic Distance Transform for Image Segmentation
- Introduction
- Related Work
- Distance Transform
- Generalized Distance Transform
- Geodesic Distance Transform Using Image Gradients
- Shape Prior Embedded Geodesic Segmentation
- Shape Prior Embedded Geodesic Distance Transform
- Geodesic Morphology Operators
- Segmentation
- Results
- Interactive Image Segmentation
- Conclusions
- References
- Shortest Path Based Planar Graph Cuts for Bi-layer Segmentation of Binocular Stereo Video
- Introduction
- Construct Energy Function on Planar Graph
- Contrast Energy on Planar Graph
- Color-Likelihood Energy on Planar Graph
- Stereo Coherence Energy on Planar Graph
- Shortest Path Based Planar Graph Cuts
- Parametric Shortest Paths
- Shortest Path Based Planar Graph Cuts
- Dynamic Tree
- Experiments
- Measure Accuracy of Segmentation
- Measure Efficiency of Segmentation
- Conclusions
- References
- Color Information Presentation for Color Vision Defective by Using a Projector Camera System
- Introduction
- Purpose and Outline of Color Information Presentation
- Color Image Processing
- Registration of Projected Image and Real Object
- Experiment
- Conclusion
- References
- Workshop on Computational Photography and Aesthetics
- Simulating Artworks through Filter Blending
- Curved Brush Strokes
- Pointillism
- Impressionism
- Filter Blending
- Results
- Conclusions and Future Work
- References
- A Data-Driven Approach to Understanding Skill in Photographic Composition
- Introduction
- Experimental Methods
- Results
- Discussion
- Conclusions and Future Work
- References
- Image Information in Digital Photography
- Introduction
- Information-Theoretic Concepts
- Compositional Information Channel
- Image Information Measures
- Saliency
- Specific Information
- Entanglement
- Results and Discussion
- Conclusions
- References
- Automatically Detecting Protruding Objects When Shooting Environmental Portraits
- Introduction
- Algorithm for Protruding Object Detection
- Foreground Region Extraction
- Estimating the Region of Interest (ROI)
- Estimating the Protruding Objects
- System Evaluations and Analysis
- Data Set
- Evaluations
- Conclusions and Future Works
- References
- Artist-Led Suggestions towards an Approach in Content Aware 3D Non-photorealistic Rendering
- Introduction
- Lines That Describe Incomplete Perimeters
- Proposal: A Light Aware NPR
- Lines That Suggest Form
- Lines That Suggest Color
- Conclusion
- References
- Workshop on Computer Vision in Vehicle Technology: From Earth to Mars
- Ground Truth Evaluation of Stereo Algorithms for Real World Applications
- Introduction
- Approach
- Experiments
- Conclusions and Future Work
- References
- Vehicle Ego-Localization by Matching In-Vehicle Camera Images to an Aerial Image
- Introduction
- Construction of Feature-Points Map for Ego-Localization
- Ego-Localization by Matching the In-Vehicle Camera Images to the Map
- Overview
- Transformation of an In-Vehicle Camera Image to a Projected Image
- Sequential Matching between Projected Images
- Matching of the Projected Image to the Feature-Points Map Using Multiple Frames
- Estimation of the Vehicle Position
- Experiment
- Setup
- Evaluation
- Initial Estimation
- Experimental Result
- Discussion
- Conclusion
- References
- A Comparative Study of Two Vertical Road Modelling Techniques
- Introduction
- Related Work
- V -Disparity Images
- B-Spline Road-Modeling
- Region-Growing
- Least-Squares Fitting
- Error Model
- Region-Reduction
- Smoothness Constraint
- Gradient Constraint
- Results
- Conclusions
- References
- The Six Point Algorithm Revisited
- Introduction
- Limits of the 6-pt Algorithm
- Selection Criteria
- Plane+Parallax for Cameras with Unknown Focal Length
- Problem Formulation
- The 4+1 Plane+Parallax Solver
- The Pipeline of Finding Focal Length
- Experiments
- Conclusions
- References
- Multi-body Segmentation and Motion Number Estimation via Over-Segmentation Detection
- Introduction
- Problem Statement
- Measures for Over-Segmentation Detection
- Loss of Spatial Locality
- Split Ratio and Cluster Distance
- Hierarchical Clustering with Supervised Classifiers for Over-Segmentation Detection
- Dual Pass Ordered Residual Method
- Classifiers for Over-Segmentation Detection
- Experiments
- Conclusion and Future Work
- References
- Improvement of a Traffic Sign Detector by Retrospective Gathering of Training Samples from In-Vehicle Camera Image Sequences
- Introduction
- Method
- Retrospective Gathering of Traffic Sign Images
- Construction of a Traffic Sign Detector
- Experiment
- Discussions
- Conclusions
- References
- Statistical Modeling of Long-Range Drift in Visual Odometry
- Introduction
- State of the Art
- Drift Model, Analysis and Quantification
- Experiments
- Discussion and Conclusions
- References
- Object Discrimination and Tracking in the Surroundings of a Vehicle by a Combined Laser Scanner Stereo System
- Introduction
- Sensor Setup
- Calibration
- Stereo System.
- Cross Calibration Laser Scanner.
- Stereo Processing
- Object Segmentation
- Stereo Camera
- Laser Scanner
- Object Shaping
- Object Tracking
- Results
- Conclusion
- References
- Realistic Modeling ofWater Droplets for Monocular Adherent Raindrop Recognition Using Bézier Curves
- Introduction
- Related Work
- Raindrop Recognition
- Raindrop Shape Model
- Bézier Representation
- Bézier Curve Fitting
- Results
- Model Parameters
- Comparison
- Conclusion
- References
- Illumination Invariant Cost Functions in Semi-Global Matching
- Introduction and Related Literature
- Cost Functions
- Semi-Global Matching
- Methodologies and Datasets
- Results and Discussion
- Conclusions
- References
- Relative Pose Estimation for Planetary Entry Descent Landing
- Introduction
- Fundamental Matrix Computation for Quasi-Planar Surfaces
- The Degeneracy of Planar Surfaces
- Pure Translation Model
- Plane Plus Parallax Model
- Comparative Analysis and Discussion
- The Data
- Results
- References
- Workshop on e-Heritage
- AR Cultural Heritage Reconstruction Based on Feature Landmark Database Constructed by Using Omnidirectional Range Sensor
- Introduction
- Landmark Database Construction Considering Local 3-D Structure
- Acquisition of Depth Map and Surface Texture
- Acquisition of Landmark Information
- Geometric Registration: Extrinsic Camera Parameter Estimation Using Landmark Database
- Experiments
- Quantitative Evaluation of Pattern Compensation
- Quantitative Evaluation of Estimated Camera Parameters
- Conclusion
- References
- Augmented Reality-Based On-Site Tour Guide: A Study in Gyeongbokgung
- Introduction
- Methodology
- Framework
- Context-Awareness
- Augmentation
- Demonstrations
- Discussion
- Conclusion
- References
- 3D Reconstruction of a Collapsed Historical Site from Sparse Set of Photographs and Photogrammetric Map
- Introduction
- History of the Project
- Creating 3D Models from Photographs and the Photogrammetric Map
- Optimizing Splines
- Building Mesh from Splines
- Estimating Camera Parameters
- Estimating Transformation Matrix
- Photograph Registration
- Post Processing
- Result and Discussion
- References
- Recognition and Analysis of Objects in Medieval Images
- Introduction
- Related Work
- Benchmarking, Analysis, and Recognition
- Database and Benchmarking
- Object Analysis
- Object Recognition
- Discussion and Conclusions
- References
- 3D Shape Restoration via Matrix Recovery
- Introduction
- Low-Rank Matrix Recovery
- Problem Statement
- Applying to the Shape Restoration Problem
- Shape Correspondence and Vectorization
- Sparse Correspondences
- Dense Correspondences and Vectorization
- Experimental Results
- Conclusion and Discussion
- References
- A Development of a 3D Haptic Rendering System with the String-Based Haptic Interface Device and Vibration Speakers
- Introduction
- Noncontact Method of Measuring and Modeling of Asperity Information
- Environment of Noncontact Measuring
- Estimation of Asperity Information
- Displaying Tactile and Haptic Sense Based on Measuring
- Preprocessing
- Somatosensory Rendering
- Tactile Rendering
- Multisensory Display System
- Multisensory Display for Digital Archive Model
- Modeling of Noh-cloth Based on Measuring
- Conclusion
- References
- A Texture-Based Direct-Touch Interaction System for 3D Woven Cultural Property Exhibition
- Introduction
- Digital Archiving and Modeling
- 3D Graphic Modeling
- 3D Haptic Modeling
- Realtime and Direct-Touch Interaction System for 3D Woven Cultural Property Exhibition
- System Architecture
- Direct-Touch and Texture-Based Haptic Rendering
- Results
- Conclusion and Future Work
- References
- Workshop on Subspace Methods
- High Dimensional Correspondences from Low Dimensional Manifolds - An Empirical Comparison of Graph-Based Dimensionality Reduction Algorithms
- Introduction
- Related Work
- Spectral Methods for Dimensionality Reduction
- Linear Methods
- Graph-Based Methods
- Transformations between Different Subspaces
- Experiments
- Assignment Accuracy of Cartoon Faces with and without Glasses
- Classification Accuracy of Handwritten and Digital Digits
- Discussion and Outlook
- References
- Multi-label Classification for Image Annotation via Sparse Similarity Voting
- Introduction
- Sparse Representation for Multi-labeling
- Multi-class Classification and Multi-labeling
- Sparse Representation of Test Data
- Dimensionality Reduction
- Multi-label Estimation by Similarity Voting
- Algorithms
- Multi-label Classification
- Sparse Decomposition
- Kernelization
- Experiment
- Concluding Remarks
- References
- Centered Subset Kernel PCA for Denoising
- Introduction
- KPCA and Subset KPCA
- Centered Subset KPCA
- Pre-image of Centered SubKPCA
- Experiment
- Preliminary Experiment I - Centered vs. Non-Centered
- Preliminary Experiment II - Relation between the Number of Samples and Performance
- Centered Subset KPCA
- Conclusion
- References
- On the Behavior of Kernel Mutual Subspace Method
- Introduction
- Kernel Mutual Subspace Method
- Mutual Subspace Method (MSM)
- Kernel Mutual Subspace Method (KMS)
- Experiment on ETH80 Animal Database
- Experimental Setup
- KMS Parameters
- Experimental Results
- Conclusions
- References
- Compound Mutual Subspace Method for 3D Object Recognition: A Theoretical Extension of Mutual Subspace Method
- Introduction
- Compound Mutual Subspace Method (CPMSM)
- The Basic Principle of CPMSM
- Calculation of Similarity in CPMSM
- Measure of Similarity between Two Subspaces
- Definition of Difference Subspace
- Flow of the Classification Process Using Similarity in CPMSM
- Validation of the Proposed Method by Using a Database Containing Face Images
- Setup of Experiment for Face Recognition
- Extraction of Frequently Misclassified Pairs
- Classification Results for Frequently Misclassified Pairs
- Conclusions
- References
- Dynamic Subspace Update with Incremental Nystr\"{o}m Approximation
- Introduction
- Nyström Approximation
- Incremental Subspace Update
- Refinement Strategies
- Error Reduction
- Compression Strategy
- Experimental Results
- Accuracy and Efficiency
- Visual Tracking
- Conclusions
- References
- Background Modeling via Incremental Maximum Margin Criterion
- Introduction
- Incremental Maximum Margin Criterion (IMMC)
- Updating Incrementally Leading Eigenvectors
- Updating Incrementally the Other Eigenvectors
- Application to Background Modeling
- Experimental Results
- Conclusion
- References
- Trace Norm Regularization and Application to Tensor Based Feature Extraction
- Introduction
- Properties of Trace Norm Regularization and Previous Works
- Why Trace Norm Induces Rank Reduction
- Trace Norm Regularization in Vector Approximation Problems
- Algorithm for the Case f(X X X X)=12"026B30D A - XB"026B30D F2
- Minimization Algorithm
- Comparison with Other Optimization Methods
- Application to Tensor Based Feature Extraction
- Tensor Algebra and Multi-linear PCA
- Tensor Based Feature Extraction Using Trace Norm Regularization
- Experimental Results
- Eigenface vs. Traceface
- Handwritten Digit Recognition by Tensor Feature Extraction
- Conclusion
- References
- Fast and Robust Face Recognition for Incremental Data
- Introduction
- The Proposed Algorithm
- Pre-processing
- Holistic Features Extraction
- Features Classifier
- The Effect of Sbp to the Discrimination
- Experimental Setup and Results
- Conclusion and Future Works
- References
- Extracting Scene-Dependent Discriminant Features for Enhancing Face Recognition under Severe Conditions
- Introduction
- Proposed Algorithm
- Problem: Matching Facial Images with Different Shapes
- Solution: Adaptive Extraction of Discriminant Features
- Fusing Fitting Confidence with Similarity for Recognition
- Experiments
- Conclusions
- References
- A Brief History of the Subspace Methods
- References
- Author Index
