
Advances in Multimedia Information Processing -- PCM 2015
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
The two-volume proceedings LNCS 9314 and 9315, constitute the proceedings of the 16 th Pacific-Rim Conference on Multimedia, PCM 2015, held in Gwangju, South Korea, in September 2015.
The total of 138 full and 32 short papers presented in these proceedings was carefully reviewed and selected from 224 submissions. The papers were organized in topical sections named: image and audio processing; multimedia content analysis; multimedia applications and services; video coding and processing; multimedia representation learning; visual understanding and recognition on big data; coding and reconstruction of multimedia data with spatial-temporal information; 3D image/video processing and applications; video/image quality assessment and processing; social media computing; human action recognition in social robotics and video surveillance; recent advances in image/video processing; new media representation and transmission technologies for emerging UHD services.
More details
Other editions
Additional editions

Content
- Intro
- Preface
- Organization
- Contents - Part II
- Contents - Part I
- 3D Image/Video Processing and Applications
- Motion and Depth Assisted Workload Prediction for Parallel View Synthesis
- Abstract
- 1 Introduction
- 2 The Proposed Parallel Structure
- 3 Adaptive Workload Balancing
- 3.1 Definition of Workload
- 3.2 Workload Prediction
- 3.3 Partition Location Decision
- 4 Experimental Results
- 4.1 The Performance for Workload Prediction
- 4.2 The Performance for View Extrapolation
- 4.3 The Performance for View Interpolation
- 4.4 The Subjective Quality
- 5 Conclusions
- Acknowledgment
- References
- Graph Cuts Stereo Matching Based on Patch-Match and Ground Control Points Constraint
- 1 Introduction
- 2 Proposed Method
- 2.1 Problem Formulation
- 2.2 Disparity Map Computation
- 3 Experiments
- 3.1 Evaluation on the Middlebury Datasets
- 3.2 Disparity Results with and Without GCPs
- 3.3 Performance of Proposed Method
- 4 Conclusion
- References
- Synthesized Views Distortion Model Based Rate Control in 3D-HEVC
- Abstract
- 1 Introduction
- 2 Rate and Distortion Analysis in 3D-HEVC
- 2.1 R-D Model for the Coded Texture Views
- 2.2 R-D Model for Synthesized Views
- 2.3 A Joint Bit Allocation Based RC Scheme for 3D-HEVC
- 3 Experimental Results
- 3.1 Control Accuracy
- 3.2 R-D Performance
- 4 Conclusions
- References
- Efficient Depth Map Upsampling Method Using Standard Deviation
- Abstract
- 1 Introduction
- 2 Related Work
- 3 Efficient Depth Map Upsampling Using Edge Information
- 3.1 Edge Region
- 3.2 Blending Function
- 3.3 Adaptive Multilateral Upsampling
- 4 Experimental Results
- 5 Conclusion
- Acknowledgements
- References
- Orthogonal and Smooth Subspace Based on Sparse Coding for Image Classification
- Abstract
- 1 Introduction
- 2 SIFT Sparse Codes Using Spatial Pyramid Max Pooling
- 2.1 The Sparse Codes
- 2.2 Spatial Pyramid Max Pooling
- 3 Orthogonal and Smooth Subspace Method
- 4 Parameters Selecting
- 5 Experiments
- 6 Conclusion
- Acknowledgement
- References
- Video/Image Quality Assessment and Processing
- Sparse Representation Based Image Quality Assessment with Adaptive Sub-dictionary Selection
- Abstract
- 1 Introduction
- 2 Dictionary Based Sparse Representation
- 3 Proposed Image Quality Model
- 3.1 Adaptive Sub-dictionary Selection
- 3.2 Sparse Feature Similarity
- 3.3 Auxiliary Feature Similarity
- 3.4 Sparse-Feature-Based Pooling
- 4 Experimental Results and Discussions
- 5 Conclusion
- Acknowledgements
- References
- Single Image Super-Resolution via Iterative Collaborative Representation
- 1 Introduction
- 2 Related Work
- 3 Iterative Collaborative Representation for Super-Resolution
- 3.1 Image SR Based on Collaborative Representation
- 3.2 Learning Phase in ICR
- 3.3 Reconstruction Phase in ICR
- 4 Experimental Results
- 4.1 Experimental Settings
- 4.2 Performance
- 4.3 Visual Results
- 5 Conclusion
- References
- Influence of Spatial Resolution on State-of-the-Art Saliency Models
- Abstract
- 1 Introduction
- 2 Objective Experiment
- 2.1 Test Models
- 2.2 Metric and Database
- 2.3 Experiment Design
- 2.4 Relationship between Two Experiments
- 3 Result and Contribution
- 3.1 Result of the First Experiment
- 3.2 Result of the Second Experiment
- 3.3 Contribution
- 4 Conclusion and Discussion
- Acknowledgement
- References
- Depth Map Upsampling via Progressive Manner Based on Probability Maximization
- 1 Introduction
- 2 Proposed Method
- 2.1 Our Model
- 2.2 Progressive Framework
- 3 Experimental Results
- 3.1 Upsample the Clean LR Depth Map
- 3.2 Upsample the Noised LR Depth Map
- 4 Conclusions
- References
- Perceptual Quality Improvement for Synthesis Imaging of Chinese Spectral Radioheliograph
- Abstract
- 1 Introduction
- 2 Synthesis Imaging Principle of CSRH
- 3 Image Reconstruction for CSRH Image System
- 3.1 Image Reconstruction with Sparse Constraint
- 3.2 Sparse Representation of Image by Dictionary
- 3.3 Optimization Formulation for CSRH Imaging System
- 4 Experimental Results
- 5 Conclusion
- Acknowledgment
- Social Media Computing
- Real-Life Voice Activity Detection Based on Audio-Visual Alignment
- 1 Introduction
- 2 Visual Voice Activity Detection
- 3 Audio Voice Activity Detection
- 4 Audio-Visual Voice Activity Detection
- 5 Experimental Results
- 6 Conclusion
- References
- Emotion Recognition from EEG Signals by Leveraging Stimulus Videos
- 1 Introduction
- 2 Emotion Recognition from EEG Signals with the Help of Stimulus Videos
- 2.1 Feature Extraction
- 2.2 Modeling Relations Between EEG Signals and Stimulus Videos by RBM
- 2.3 New EEG Features Generated Through the Learned RBM
- 3 Experimental Results and Analysis
- 3.1 Experimental Conditions
- 3.2 Results and Analysis
- 3.3 Compared with Related Works
- 4 Conclusions
- References
- Twitter Event Photo Detection Using both Geotagged Tweets and Non-geotagged Photo Tweets
- 1 Introduction
- 2 Related Work
- 3 Previous System
- 4 Proposed System
- 4.1 Overview
- 4.2 Target Data
- 4.3 Preparation
- 4.4 Detect Event Word Burst Using N-Gram
- 4.5 Estimate Locations of Non-geotagged Photos
- 4.6 Select Event Photos and Representative Photos
- 5 Experimental Results
- 6 Conclusions
- References
- Weather-Adaptive Distance Metric for Landmark Image Classification
- Abstract
- 1 Introduction
- 2 Related Works
- 3 Weather-Adaptive Distance Metric
- 3.1 Common Distance Metric
- 3.2 Weather-Adaptive Distance Metric
- 4 Experiments
- 4.1 Experimental Settings
- 4.2 Distributions of Distances
- 4.3 Performance of Landmark Classification
- 5 Conclusion
- Acknowledgements
- References
- Power of Tags: Predicting Popularity of Social Media in Geo-Spatial and Temporal Contexts
- 1 Introduction
- 2 Related Work
- 2.1 DF-W Algorithm
- 3 Experimental Results
- 3.1 Data Collection
- 3.2 Spatial Analysis
- 3.3 Temporal Analysis
- 4 Conclusions and Future Work
- References
- Human Action Recognition in Social Robotics and Video Surveillance
- Recent Advances in Image/Video Processing
- Score Level Fusion of Multibiometrics Using Local Phase Array
- 1 Introduction
- 2 Biometric Recognition Using Local Phase Array
- 2.1 Feature Extraction
- 2.2 Matching
- 3 Score Fusion Approaches
- 3.1 Density-Based Approach
- 3.2 Transformation-Based Approach
- 4 Experiments and Discussion
- 4.1 Virtual Multibiometric Databases
- 4.2 Performance Evaluation
- 5 Conclusion
- References
- Histogram-Based Near-Lossless Data Hiding and Its Application to Image Compression
- 1 Introduction
- 2 Preliminary
- 2.1 LSB Substitution-Based DH
- 2.2 HS-Based DH
- 2.3 NLL DH
- 3 Proposed Method
- 3.1 Example Algorithms
- 3.2 Features
- 4 Experimental Results
- 5 Conclusions
- References
- Hierarchical Learning for Large-Scale Image Classification via CNN and Maximum Confidence Path
- Abstract
- 1 Introduction
- 2 Related Work
- 3 Image Presentation and Visual Tree Construction
- 3.1 Image Representation Based on CNN Features
- 3.2 Visual Tree Construction
- 4 Hierarchical Learning
- 4.1 Classifier Training
- 4.2 Hierarchical Prediction
- 5 Experimental Results
- 6 Conclusions
- Acknowledgements
- References
- Single Camera-Based Depth Estimation and Improved Continuously Adaptive Mean Shift Algorithm for Tracking Occluded Objects
- Abstract
- 1 Introduction
- 2 Color Shift Model-Based Depth Estimation
- 3 Tracking Algorithm for Occlusion Handling
- 4 Experimental Results
- 5 Conclusion
- Acknowledgment
- References
- A Flexible Programmable Camera Control and Data Acquisition Hardware Platform
- 1 Introduction
- 2 Methodology
- 2.1 Difficulties and Solutions
- 2.2 Implementation
- 3 Test and Related Experiments
- 3.1 Tests
- 3.2 Related Experiments and Results
- 4 Conclusions
- References
- Recognition of Human Group Activity for Video Analytics
- Abstract
- 1 Introduction
- 2 The Proposed Method
- 2.1 Overview
- 2.2 Problem Definition
- 2.3 Group Activity Descriptors
- 2.3.1 Individual Activity Descriptor
- 2.3.2 Pair Activity Descriptor
- 2.3.3 Inter-Subgroup Activity Descriptor
- 2.4 Activity Classification with Group Activity Descriptors
- 3 Experimental Results
- 4 Conclusion
- Acknowledgment
- References
- An Incremental SRC Method for Face Recognition
- Abstract
- 1 Introduction
- 2 Pipeline Overview
- 3 Dictionaries of the Incremental SRC Method
- 3.1 Building Dictionaries
- 3.2 Selecting Out the Bad Components
- 3.3 Global Result
- 4 Our Incremental SRC Framework
- 4.1 Basic Problem of Incremental SRC Method
- 4.2 Divide Samples into Multiple Groups
- 4.3 Decision Among the Groups
- 5 Experimental Results
- 5.1 Experiments Under No Occlusions
- 5.2 Experiments Under Occlusions
- 6 Conclusions
- Acknowledgments
- References
- A Survey on Media Interaction in Social Robotics
- 1 Introduction
- 2 Visual Media Interaction
- 2.1 Facial Expression
- 2.2 Hand Gesture Recognition
- 2.3 Body Action Recognition
- 2.4 Event Detection
- 3 Multimodal Media Interaction
- 3.1 Audio Interaction
- 3.2 Tactile Interaction
- 4 Conclusions
- References
- Recognizing 3D Continuous Letter Trajectory Gesture Using Dynamic Time Warping
- 1 Introduction
- 2 Related Work
- 3 The Proposed Continuous Letter Trajectory Recognition System
- 3.1 Traditional Dynamic Time Warping Algorithm
- 3.2 Dynamic Time Warping with Structured Points
- 3.3 Determine the Output Letter
- 4 Experimental Results and Analysis
- 5 Conclusions
- References
- Rapid 3D Face Modeling from Video
- Abstract
- 1 Introduction
- 2 System Overview
- 3 Generating Individual 3D Geometric Face Model
- 3.1 Extracting 2D Facial Feature Points
- 3.2 Deforming Generic Face Model
- 4 Synthesizing Individual Facial Texture Image
- 5 Texture Mapping
- 6 Experiments and Evaluation
- 7 Conclusions and Future Work
- References
- New Media Representation and Transmission Technologies for Emerging UHD Services
- Comparison of Real-time Streaming Performance Between UDP and TCP Based Delivery Over LTE
- Abstract
- 1 Introduction
- 2 Related Work
- 2.1 Features of UDP and TCP
- 2.2 Estimate Available Bandwidth
- 3 Experiment Method and Mathematical Model
- 3.1 Measure Method
- 4 Comparison Between UDP and TCP
- 4.1 Maximum Available Bitrate
- 4.2 Distribution of {\varvec J}_{{\varvec i}}
- 4.3 Instantaneous Change of Rate
- 4.4 Correlation
- 5 Conclusion
- Acknowledgement
- References
- Video Streaming for Multi-cloud Game
- Abstract
- 1 Introduction
- 2 Background
- 2.1 Cloud Gaming
- 2.2 Response Delay
- 2.3 Distributed Process
- 2.4 P2P(Peer to Peer)
- 2.5 Raptor
- 2.6 Multi-cloud
- 3 Proposed System
- 3.1 Optimizing Number of Encoding Server
- 3.2 Optimizing Number of Sending Server
- 4 Conclusion
- Acknowledgement
- References
- Performance Analysis of Scaler SoC for 4K Video Signal
- Abstract
- 1 Introduction
- 2 Scaling Algorithm
- 3 Optimization of Scaler SoC
- 3.1 Constrained Coefficients of Scaler in SoC
- 3.2 Quantized Phase of Scaler in SoC
- 3.3 Constrained Coefficients of LPF in SoC
- 4 Simulation Results
- 4.1 Performance for Constrained Coefficients of Scaler
- 4.2 Performance for Quantized Phase of Scaler
- 4.3 Performance for Constrained Coefficients of LPF
- 5 Conclusions
- References
- Deblocking Filter for Depth Videos in 3D Video Coding Extension of HEVC
- Abstract
- 1 Introduction
- 2 Deblocking Filter
- 2.1 Boundary Strength
- 2.2 Strong/Normal Filter
- 3 Proposed Method
- 3.1 Boundary Strength and Filter Type
- 3.2 Impulse Response
- 4 Experiment Results
- 5 Conclusion
- Acknowledgements
- References
- Sparcity-Induced Structured Transform in Intra Video Coding for Screen Contents
- Abstract
- 1 Introduction
- 2 Proposed Method
- 2.1 Structured Sparse Transform Design
- 2.2 Codec Design
- 3 Experimental Results
- 4 Conclusion
- Acknowledgement
- References
- Special Poster Sessions
- High-Speed Periodic Motion Reconstruction Using an Off-the-shelf Camera with Compensation for Rolling Shutter Effect
- 1 Introduction
- 2 Brief Review of Coded Strobing Photography
- 2.1 Camera Observation Model and Signal Model
- 2.2 High-Speed Periodic Motion Reconstruction via Structured Sparse Reconstruction
- 3 Proposed Method
- 3.1 High-Speed Periodic Motion Reconstruction Based on Random Delay
- 3.2 Compensation for Rolling Shutter Effect
- 4 Experiments
- 4.1 High-Speed Periodic Motion Reconstruction
- 4.2 Compensation for Rolling Shutter Effect
- 5 Conclusion
- References
- Robust Feature Extraction for Shift and Direction Invariant Action Recognition
- Abstract
- 1 Introduction
- 2 Proposed Method
- 2.1 Optical Flow Histogram
- 2.1.1 Median Flow
- 2.1.2 Sum of Magnitude in Each Range
- 2.1.3 Aligning Direction
- 2.2 Histogram Normalization and Concatenation
- 2.3 Low-Pass Filtering in Frequency Domain
- 3 Experimental Results
- 3.1 KTH Dataset
- 3.2 Smart Class Dataset
- 3.2.1 Single-View
- 3.2.2 Multi-View
- 4 Conclusion
- References
- Real-Time Human Action Recognition Using CNN Over Temporal Images for Static Video Surveillance Cameras
- Abstract
- 1 Introduction
- 2 Hierarchical Action Structure
- 3 Human Action Recognition Using CNN
- 3.1 Temporal Images
- 3.2 CNN Architecture
- 4 Experimental Results
- 5 Conclusions
- Acknowledgements
- References
- Scalable Tamper Detection and Localization Scheme for JPEG2000 Codestreams
- 1 Introduction
- 2 Related Work
- 2.1 JPEG2000 Codestreams [7,8]
- 2.2 JPEG2000 Marker Code
- 3 Proposed Scheme
- 3.1 Conditions for Avoiding Marker Codes
- 3.2 Information Embedding Procedure
- 3.3 Tamper Detection Procedure
- 4 Experimental Results
- 5 Conclusion
- References
- Developing a Visual Stopping Criterion for Image Mosaicing Using Invariant Color Histograms
- 1 Introduction
- 2 Invariant Histogram Based Mosaic Image Quality Monitoring
- 3 Experimental Results
- 4 Conclusion and Future Work
- References
- Intelligent Reconstruction and Assembling of Pipeline from Point Cloud Data in Smart Plant 3D
- Abstract
- 1 Introduction
- 2 Pre-processing of Point Cloud
- 3 Segmentation and Classification of Point Cloud
- 3.1 Normal Estimation
- 3.2 Region Growing
- 3.3 Pipe and Plane Separation
- 3.4 Point Cloud Classification and Recognition
- 4 Detection of Cylinder Parameter Using Hough Transform
- 4.1 Orientation Estimation
- 4.2 Position and Radius Estimation
- 5 Reconstruction and Assembling of Pipeline in SP3D
- 5.1 SP3D Interfacing
- 5.2 Experimental Result
- 6 Conclusion
- References
- A Rotational Invariant Non-local Mean
- 1 Introduction
- 2 Related Works
- 3 Rotational Invariant Non-local Mean
- 4 Experimental Results
- 5 Discussion and Conclusion
- References
- Adaptive Layered Video Transmission with Channel Characteristics
- Abstract
- 1 Introduction
- 2 Review of Scalable Video Coding
- 3 Adaptive Layered Video Transmission with Channel Characteristics
- 3.1 The Framework of Our Transmission System
- 3.2 Subcarrier Allocation
- 3.3 Power Allocation
- 3.4 Modulation Adjustment
- 4 Experimental Results
- 5 Conclusion
- Acknowledgements
- References
- An Accurate and Efficient Nonlinear Depth Quantization Scheme
- Abstract
- 1 Introduction
- 2 Efficient Nonlinear-Depth-Quantization: A Brief Review
- 2.1 Theory of E-NDQ
- 2.2 Analysis of E-NDQ
- 2.3 Accurate-Efficient Nonlinear-Depth-Quantization
- 3 Experimental Results
- 3.1 Efficiency Evaluation on Depth Quantization
- 3.2 Accuracy Evaluation on View Synthesis
- 4 Conclusion
- Acknowledgement
- References
- Synthesis-Aware Region-Based 3D Video Coding
- Abstract
- 1 Introduction
- 2 Review of Block-Based Compressive Sensing
- 3 Synthesis-aware Region-Based 3D Coding with BCS
- 3.1 Region-Division of Original Videos
- 3.1.1 Calculate the Threshold to Detect Boundaries
- 3.1.2 Boundaries Detection Process
- 3.1.3 Region Division of Original Views
- 3.2 Rate Allocation for Different Regions with BCS_SPL
- 4 Experimental Results
- 5 Conclusion
- Acknowledgements
- References
- A Paradigm for Dynamic Adaptive Streaming over HTTP for Multi-view Video
- 1 Introduction
- 2 DASH-based Multi-view Video Streaming Approach
- 2.1 Problems
- 2.2 Solutions
- 3 Experimental Results
- 4 Conclusions
- References
- Adaptive Model for Background Extraction Using Depth Map
- 1 Introduction
- 2 Method
- 2.1 Background Model from GMM
- 2.2 The Exploit-Ability of Depth Map
- 2.3 Depth-Color Consistency Check
- 3 Experimental Results
- 4 Conclusion
- References
- An Efficient Partition Scheme for Depth-Based Block Partitioning in 3D-HEVC
- Abstract
- 1 Introduction
- 2 DBBP Coding in 3D-HEVC
- 2.1 Depth-Based Block Partitioning
- 2.2 New Observations
- 3 Proposed Scheme
- 3.1 Discussions on Similarity in Segment Mask Generation and Partition Determination
- 3.2 An Efficient Partition Scheme
- 4 Experimental Results
- 5 Conclusion
- References
- Image Classification with Local Linear Decoding and Global Multi-feature Fusion
- Abstract
- 1 Introduction
- 2 Convolved Feature Analysis Based on Local Linear Decoder
- 2.1 Local Linear Feature Decoder
- 2.2 Convolved Feature Analysis Based on Local Network
- 3 Global Multi-feature Fusion
- 4 Experiments
- 4.1 Datasets
- 4.2 Feature Selection and Analysis Results
- 5 Performance Comparison
- 6 Conclusions
- Acknowledgments
- References
- Hashing with Inductive Supervised Learning
- Abstract
- 1 Introduction
- 2 Related Work
- 3 The Proposed Method
- 3.1 Inductive Supervised Learning for Hashing
- 3.2 Base Set Embedding
- 3.3 Hashing with Classifier
- 4 Experiment Results
- 5 Conclusion
- References
- Graph Based Visualization of Large Scale Microblog Data
- Abstract
- 1 Introduction
- 2 Related Work
- 3 Graph Construction
- 3.1 Preprocess Method
- 3.2 Feature Extraction
- 3.3 Duplicates Removal Method
- 3.4 Edge Construction
- 4 Microblog Retrieval
- 5 Graph Based Microblog Visualization
- 5.1 The Framework
- 5.2 The Interface
- 6 Experimental Results and Discussion
- 6.1 The Experimental Result for Randomly Selected Data
- 6.2 The Experimental Result for Brand Related Data
- 7 Conclusion
- Acknowledgements
- References
- Boosting Accuracy of Attribute Prediction via SVD and NMF of Instance-Attribute Matrix
- 1 Introduction
- 2 Preliminaries to Matrix Factorization
- 2.1 Singular Value Decomposition Model
- 2.2 Non-negative Matrix Factorization Model
- 3 Boosting Accuracy of Attribute Prediction Based on Matrix Factorization
- 3.1 Baseline Algorithm
- 3.2 Boosting Accuracy of Attribute Prediction by SVD
- 3.3 Boosting Accuracy of Attribute Prediction by NMF
- 4 Experiments
- 4.1 Data Set and Parameters Tuning
- 4.2 Experimental Results
- 5 Conclusion
- References
- Fatigue Detection Based on Fast Facial Feature Analysis
- Abstract
- 1 Introduction
- 2 Facial Landmark Detection and Tracking by SDM
- 3 Extraction and Definition of Visual Fatigue Rules
- 3.1 Acquisition and Processing of Feature Data
- 3.2 Metrics for Fatigue Description
- 3.3 Driver Fatigue Computation Rules
- 4 Experimental Results and Analysis
- References
- A Packet-Layer Model with Content Characteristics for Video Quality Assessment of IPTV
- Abstract
- 1 Introduction
- 2 Packet-Layer Video Quality Assessment Model
- 2.1 Framework
- 2.2 Structural Decomposition
- 2.3 Temporal Sensitivity Function
- 2.4 Loss-Related Feature
- 2.5 Video Perceptual Quality Prediction
- 3 Experimental Results
- 3.1 Experimental Setting
- 3.2 Experimental Results
- 4 Conclusion
- References
- Frame Rate and Perceptual Quality for HD Video
- Abstract
- 1 Introduction
- 2 Subjective Experiment
- 2.1 Experiment Materials
- 2.2 Environment Setup
- 2.3 Experiment Design
- 3 Experimental Results and Analysis
- 3.1 MOS Results
- 3.2 ANOVA on MOS
- 3.3 Model Validation
- 3.4 MOS Results Analysis
- 4 Conclusion
- Acknowledgement
- References
- No-Reference Image Quality Assessment Based on Singular Value Decomposition Without Learning
- 1 Introduction
- 2 Proposed Method
- 2.1 Relationship Between Singular Values and Type of Image Distortions
- 2.2 Quality Metric Based on Singular Values
- 3 Experimental Results
- 3.1 Protocol
- 3.2 Performance Comparisons
- 3.3 Computational Complexity
- 4 Conclusion
- References
- An Improved Brain MRI Segmentation Method Based on Scale-Space Theory and Expectation Maximization Algorithm
- Abstract
- 1 Introduction
- 2 GMM Based EM Algorithm
- 3 Density Estimation and Initialization for EM
- 3.1 Kernel Density Estimation
- 3.2 Initialization Based on Scale-Space Theory
- 4 Experimental Results
- 4.1 Determining the Number of Clusters
- 4.2 Initialization Impact on Segmentation Results
- 5 Conclusion
- Acknowledgement
- References
- User-Driven Sports Video Customization System for Mobile Devices
- 1 Introduction
- 2 System Framework
- 2.1 Semantic Annotation of Sports Video
- 2.2 Video Encoding
- 2.3 Personalized Customization for Mobile Devices
- 2.4 User Client Design
- 3 Extended-HMM Based Approach for Time Recognition
- 3.1 Introduction to Hidden Markov Model
- 3.2 HMM Method
- 3.3 Extended-HMM Method
- 4 Event Based Video Encoding Approach
- 5 Experimental Results
- 5.1 Time Recognition
- 5.2 Video Encoding
- 6 Conclusions
- References
- Auditory Spatial Localization Studies with Different Stimuli
- Abstract
- 1 Introduction
- 2 Experimental Setup
- 3 Method and Subjects
- 4 Data Processing and Results
- 5 Conclusion and Discussion
- References
- Multichannel Simplification Based on Deviation of Loudspeaker Positions
- 1 Introduction
- 2 Reproduction Based on Area Among Loudspeakers
- 3 Analysis of Reproduced Sound Field
- 3.1 Least-Squares Errors Within the Reproduced Region
- 3.2 Effect of Position Deviation Among Three Loudspeakers
- 4 Experiments
- 4.1 Simulation
- 4.2 Subjective Experiment
- 5 Conclusion
- A Appendix
- References
- Real-Time Understanding of Abnormal Crowd Behavior on Social Robots
- 1 Introduction
- 2 The Proposed Algorithm
- 2.1 Crowd Aggregation Detection
- 2.2 Crowd Escape Detection
- 3 Experiment Results and Analysis
- 3.1 Dataset
- 3.2 Experiments
- 4 Conclusions
- References
- Sparse Representation Based Approach for RGB-D Hand Gesture Recognition
- Abstract
- 1 Introduction
- 2 Proposed Method
- 2.1 Hand Gesture Segmentation and Alignment
- 2.2 Multi-attribute Sparse Coding for Gesture Recognition
- 3 Experimental Results
- 4 Conclusions
- Acknowledgements
- References
- Eye Gaze Correction for Video Conferencing Using Kinect v2
- Abstract
- 1 Introduction
- 2 Proposed Method
- 2.1 System Design
- 2.2 Preprocessing
- 2.3 Eye Gaze Correction
- 2.4 Color Inpainting
- 3 Experiment Result
- 4 Conclusion
- Acknowledgement
- References
- Temporally Consistence Depth Estimation from Stereo Video Sequences
- Abstract
- 1 Introduction
- 2 Temporal Domain Stereo Matching
- 2.1 Local Stereo Matching
- 2.2 Iterative Stereo Matching
- 2.3 Motion Prediction Stereo Matching
- 2.4 Global Matching Based Stereo Matching
- 2.5 Given Depth Based Stereo Matching
- 3 Experiment Results
- 4 Conclusion
- Acknowledgments
- References
- A New Low-Complexity Error Concealment Method for Stereo Video Communication
- Abstract
- 1 Introduction
- 2 Stereo Video EC Method Based on GMSD
- 2.1 Pixel-wise TGMSD and VGMSD Map of Right-View
- 2.2 MB-Wise TGMSD and VGMSD of the Right View
- 2.3 EC with Different Prediction Modes
- 3 Experimental Results and Discussions
- 4 Conclusion
- Acknowledgements
- References
- Hole Filling Algorithm Using Spatial-Temporal Background Depth Map for View Synthesis in Free View Point Television
- Abstract
- 1 Introduction
- 2 Proposed Hole Filling Algorithm
- 2.1 Background Modeling
- 2.2 Hole Pixels Labeling and Local BG Estimation
- 2.3 Frame Updating and New Exemplar-Based Inpainting
- 3 Experimental Results
- 4 Conclusion and Future Works
- Acknowledgment
- References
- Pattern Feature Detection for Camera Calibration Using Circular Sample
- Abstract
- 1 Introduction
- 2 Corner Detection
- 3 Circular Samples
- 4 Test Results
- 5 Conclusions
- Acknowledgements
- References
- Temporal Consistency Enhancement for Digital Holographic Video
- Abstract
- 1 Introduction
- 2 Digital Holographic Video
- 2.1 Holographic Video System
- 2.2 Computer Generated Hologram
- 2.3 Hologram Reconstruction
- 3 Proposed Temporal Consistency Enhancement
- 4 Experimental Results
- 5 Conclusion
- Acknowledgment
- References
- Efficient Disparity Map Generation Using Stereo and Time-of-Flight Depth Cameras
- Abstract
- 1 Introduction
- 2 Problem Statement
- 3 Depth Fusion System
- 4 Experimental Results
- 5 Conclusions
- Acknowledgment
- References
- Super-Resolution of Depth Map Exploiting Planar Surfaces
- 1 Introduction
- 2 Planar Surface Detection
- 3 The Proposed Approach
- 3.1 Super-Resolution Process
- 4 Experimental Results
- 5 Conclusion
- References
- Hierarchical Interpolation-Based Disocclusion Region Recovery for Two-View to N-View Conversion System
- 1 Introduction
- 2 Two-View to N-View Conversion System
- 3 Hierarchical Interpolation-Based Disocclusion Region Recovery
- 4 Experimental Results
- 5 Conclusion
- References
- UEP Network Coding for SVC Streaming
- Abstract
- 1 Introduction
- 2 Proposed Scheme
- 2.1 Background: NOW RLC and EW RLC
- 2.2 Proposed UEP EW Network Coding Using Distortion Degree
- 3 Experimental Results
- 4 Conclusion
- Acknowledgement
- References
- Overview on MPEG MMT Technology and Its Application to Hybrid Media Delivery over Heterogeneous Networks
- Abstract
- 1 Introduction
- 2 Overview on MPEG MMT Technology
- 3 Hybrid Media Delivery Based on MMT
- 4 Conclusion
- References
- A Framework for Extracting Sports Video Highlights Using Social Media
- Abstract
- 1 Introduction
- 2 Related Work
- 2.1 Content-Based Sport Video Summarization
- 2.2 Sport Video Summarization by External Knowledge
- 3 Proposed Framework
- 3.1 Content Retrieval and Context Preprocessing Stage
- 3.2 Event Detection Stage
- 3.3 Semantic Annotation Stage
- 4 Performance Evaluation
- 4.1 Event Detection
- 4.2 Event Semantic Annotation
- 5 Conclusion
- References
- Author Index
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.