Image Analysis and Processing - ICIAP 2017

Name: Image Analysis and Processing - ICIAP 2017 | 19th International Conference, Catania, Italy, September 11-15, 2017, Proceedings, Part I
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

19th International Conference, Catania, Italy, September 11-15, 2017, Proceedings, Part I

Sebastiano Battiato Giovanni Gallo Raimondo Schettini Filippo Stanco(Herausgeber*in)

Springer (Verlag)

Erschienen am 11. Oktober 2017

XXVII, 767 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-319-68560-1 (ISBN)

53,49 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Preface
Organization
Contents - Part I
Contents - Part II
Video Analysis and Understanding
A Rank Aggregation Framework for Video Interestingness Prediction
1 Introduction
2 Related Work
3 Feature Extraction
3.1 Histogram of Motion Patterns
3.2 Mel-Frequency Cepstral Coefficients
4 Ranking Models
5 Rank Aggregation Framework
5.1 Borda Method
5.2 Reciprocal Rank Fusion
5.3 Multiplicative Rank Aggregation
6 Experiments and Results
7 Conclusions
References
Graph-Based Hierarchical Video Cosegmentation
1 Introduction
2 Graph-Based Hierarchical Clustering
3 Proposed Method
4 Experiments
5 Conclusion
References
Interest Region Based Motion Magnification
1 Introduction
2 Related Work
3 Interest Region Based Motion Magnification
3.1 Object Segmentation
3.2 Scribble Drawing and Alpha Matting
3.3 Video Magnification
3.4 Pipeline
4 Experiments and Discussion
5 Conclusion
References
Investigating the Use of Space-Time Primitives to Understand Human Movements
1 Introduction
2 Shearlet Theory: An Overview
3 Building Dictionaries of Space-Time Primitives
4 Experimental Analysis
4.1 Dataset and Experimental Protocol
4.2 Preliminary Investigation
5 Discussion
References
Organizing Videos Streams for Clustering and Estimation of Popular Scenes
1 Introduction
2 Related Works
3 RECfusion System Overview
3.1 Intraflow Analysis
3.2 Interflow Analysis
3.3 Cluster Tracking
4 Datasets
5 Experimental Settings and Results
6 Conclusion and Future Works
References
360° Tracking Using a Virtual PTZ Camera
1 Introduction
2 Related Works
2.1 360 Image Representation
2.2 PTZ Tracking
3 360 Camera Model
3.1 Equirectangular Projection
3.2 Equirectangular to Virtual Camera Plane Projection
4 Tracking Model
4.1 Tracking Algorithm
5 Results
6 Conclusions
References
Benchmarking Two Algorithms for People Detection from Top-View Depth Cameras
1 Introduction
2 Methods Considered for the Benchmarking
2.1 WATERFILLING
2.2 HOG-SVM
3 The Adopted Dataset
4 Experimental Analysis
4.1 Performance Indices
4.2 Training Procedure
4.3 Analysis of the Experimental Results
5 Conclusions and Future Work
References
Gesture Modelling and Recognition by Integrating Declarative Models and Pattern Recognition Algorithms
1 Introduction
2 Related Work
2.1 Vision-Based Gesture Recognition Approaches
2.2 Gesture Recognition: The Declarative Modelling Approach
3 Combining the Two Approaches with DEICTIC
4 Experiments and Preliminary Results
5 Conclusions
References
How Far Can You Get by Combining Change Detection Algorithms?
1 Introduction
2 The Proposed Approach
3 Experimental Setup
4 Results
5 Computational Time
6 Conclusion
References
Robust Tracking of Walking Persons by Elite-Type Particle Filters and RGB-D Images
1 Introduction
2 Elite-Type Particle Filter
2.1 Overall Structure of Tracking Algorithm
2.2 Basic Structure of Elite-Type Particle Filter
2.3 Likelihoods
2.4 Resampling
3 Transitional Management of PF States
4 Parameter Adjustment
5 Experiment
5.1 Specifications
5.2 Results and Discussion
6 Conclusions
References
Video Saliency Detection Based on Boolean Map Theory
1 Introduction
2 Boolean-Map Video Saliency
2.1 Boolean Maps Generation
2.2 Saliency Computation
3 Experimental Results
3.1 Experiments
3.2 Results
4 Conclusion
References
A System for Autonomous Landing of a UAV on a Moving Vehicle
1 Introduction
2 System Architecture
2.1 Hardware Architecture
2.2 Software Architecture
3 Dynamic Target Position Estimation
4 Target Detection and Tracking
4.1 Acquisition Hardware
4.2 Video Analysis
5 Basic Landing Strategy
6 Results
6.1 Simulations
6.2 On Field Trials
7 Conclusions
References
One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network
1 Introduction
1.1 Related Work
2 Time-Dependent Video Frame Prediction
3 Experiments
3.1 Experimental Setup
3.2 Dataset
3.3 Experimental Results
3.4 Ambiguities and Downsides
4 Conclusion
References
Joint Orientations from Skeleton Data for Human Activity Recognition
1 Introduction
2 State of the Art
3 Proposed Approach
4 Experiments
4.1 Office Activity Dataset (OAD)
4.2 Results
5 Conclusions
References
A Tensor Framework for Data Stream Clustering and Compression
Abstract
1 Introduction
2 Architecture of Tensor Stream Clustering and Compression
3 Tensor Model Build and Update Scheme for Data Clustering
4 Stream Compression on Shot Boundaries
5 Experimental Results
6 Conclusions
Acknowledgement
References
Convex Polytope Ensembles for Spatio-Temporal Anomaly Detection
1 Introduction and Related Work
2 Anomaly Detection with Convex Polytopes
2.1 Model Building
2.2 Anomaly Localization
3 Experimental Results
4 Conclusion
References
Human Action Classification Using an Extended BoW Formalism
1 Introduction
2 Related Work
3 Traditional Bag-of-Words
4 An Extended BoW Formalism
5 Experimental Analysis
5.1 Datasets and Protocols
5.2 Experimental Setup
5.3 Comparison with the State-of-the-art
6 Conclusions and Further Works
References
Virtual EMG via Facial Video Analysis
1 Introduction
2 Method
3 Experimental Work
4 Discussion and Conclusions
References
Pattern Recognition and Machine Learning
A Compact Kernel Approximation for 3D Action Recognition
1 Introduction
2 Related Work
3 The Proposed Approximated Feature Map
4 Results
5 Conclusions
A Proofs of All Theoretical Results
References
A Machine Learning Approach for the Online Separation of Handwriting from Freehand Drawing
1 Introduction
2 Related Work
3 The Proposed Method
3.1 Pre-processing Stage
3.2 Feature Extraction Stage
3.3 Machine Learning Stage
3.4 Domain Separation Stage
4 Experimental Results and Discussion
4.1 Dataset
4.2 Results
5 Conclusions
References
Learning to Map Vehicles into Bird's Eye View
1 Introduction
2 Related Work
3 Proposed Dataset
4 Model
5 Experimental Results
6 Conclusions
References
Linear Regularized Compression of Deep Convolutional Neural Networks
1 Introduction
2 Related Works
3 Our Approach
4 Experimental Results
5 Conclusions and Future Works
References
Network Edge Entropy from Maxwell-Boltzmann Statistics
1 Introduction
2 Preliminaries
2.1 Von Neumann Entropy
3 Network Entropy in Maxwell-Boltzmann Statistics
3.1 Thermodynamic Representation
3.2 Maxwell-Boltzmann Statistics
3.3 Edge Entropy Analysis
4 Experiments and Evaluations
4.1 Data Sets
4.2 Experimental Results
5 Conclusion
References
Learning from Enhanced Contextual Similarity in Brain Imaging Data for Classification of Schizophrenia
1 Introduction
2 Learning from Enhanced Contextual Similarity
2.1 CS Enhancement Using DML
2.2 Learning from Enhanced CS of MR Images Using GT
3 Experiments
3.1 Dataset and Representation
3.2 Experimental Analysis
3.3 Experimental Results
3.4 Discussion of the Experimental Results
4 Conclusion
References
3D Object Detection Method Using LiDAR Information in Multiple Frames
1 Introduction
2 Proposed Method
2.1 2D-Object Detection and 3D-Environment Reconstruction Using LiDAR
2.2 Supplementing Information Through Object Matching in Multi Frame
3 Experimental Results
3.1 Implementation Details
3.2 KITTI Detection Accuracy
3.3 KITTI Orientation Accuracy
4 Conclusion
References
Colorizing Infrared Images Through a Triplet Conditional DCGAN Architecture
1 Introduction
2 Related Work
3 Proposed Approach
4 Experimental Results
5 Conclusions
References
Complexity and Accuracy of Hand-Crafted Detection Methods Compared to Convolutional Neural Networks
1 Introduction
2 Object Detection
2.1 Traditional Approaches
2.2 Neural Networks
2.3 Optimized Aggregated Channel Feature Detection
2.4 Convolutional Neural Network Detection
3 Experimental Evaluation
3.1 Datasets
3.2 Metrics for Complexity and Accuracy
3.3 Accuracy Results
3.4 Complexity Results
4 Conclusion and Future Work
References
Emotion Recognition Based on Occluded Facial Expressions
1 Introduction
2 Related Work
3 Methodology
3.1 Preprocessing
3.2 Facial Expression Reconstruction
3.3 Facial Feature Extraction
3.4 Feature Reduction
3.5 Classification
4 Results
5 Conclusions and Future Work
References
Exploiting Context Information for Image Description
1 Introduction
2 Related Work
3 System Architecture
3.1 Probabilistic Ontology
3.2 Combination Models
4 Experimental Assessment
4.1 Results and Discussion
5 Conclusions and Future Work
References
Generating Knowledge-Enriched Image Annotations for Fine-Grained Visual Classification
1 Introduction
2 Related Work
3 Generating Knowledge-Enriched Visual Annotations
3.1 The Fruit Ontology
3.2 The Annotation Tool
3.3 The Fruit Image Dataset
4 Comparison to Existing Datasets for Fine-Grained Recognition
5 Conclusions
References
Histological Image Analysis by Invariant Descriptors
1 Introduction
2 Texture Descriptors
2.1 Image Moments
2.2 Co-occurrence Matrices
2.3 LBP Descriptors
3 Datasets
4 Experimental Evaluation
5 Conclusions
References
Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation
1 Introduction
2 Related Work
3 DIAL: DomaIn Alignment Layers
3.1 Source and Target Predictors
3.2 Training and Inference
4 Experiments
4.1 Experimental Setup
4.2 Results
5 Conclusions
References
Multi-stage Neural Networks with Single-Sided Classifiers for False Positive Reduction and Its Evaluation Using Lung X-Ray CT Images
1 Introduction
2 Multi-stage Neural Networks with Single-Sided Classifiers
3 Experiments
3.1 Lung CT Image Data Set
3.2 Proposed Multi-stage Classifiers
3.3 Baseline Classifiers
4 Experimental Results
5 Conclusion
References
On the Importance of Domain Adaptation in Texture Classification
1 Introduction
2 Materials and Methods
2.1 Databases
2.2 Features
2.3 Domain Adaptation Classifiers
2.4 Experimental Setup
3 Results
4 Conclusion
References
Rotation Invariant Co-occurrence Matrix Features
1 Introduction
2 Background
2.1 Displacement Type
2.2 Features Extraction
3 Our Approach
3.1 Proposed Displacement
3.2 Proposed Feature Combination
4 Datasets
5 Experimental Evaluation
6 Conclusion
References
Visual and Textual Sentiment Analysis of Brand-Related Social Media Pictures Using Deep Convolutional Neural Networks
1 Introduction
2 Related Work
3 Methods
3.1 Visual Feature Extractor
3.2 Textual Feature Extractor
3.3 Overall Sentiment Classifier
3.4 GfK Verein Dataset
4 Results and Discussion
5 Conclusions
References
Deep Multibranch Neural Network for Painting Categorization
1 Introduction
1.1 Contribution
1.2 Prior Works
2 Our Approach
2.1 Input Preprocessing
2.2 Deep Network Structure
3 Experiments
3.1 Dataset
3.2 Training
3.3 Results
4 Conclusions
References
Weighty LBP: A New Selection Strategy of LBP Codes Depending on Their Information Content
1 Introduction
2 Related Work
3 The Proposed LBP Reduction
3.1 Entropy to Select Representatives in a Set
3.2 Binary Similarity and Distance Measures
4 Experimental Results
5 Conclusions
References
Indoor Actions Classification Through Long Short Term Memory Neural Networks
1 Introduction
2 Neural Networks for Indoor Activity Classification
2.1 MLP Multilayer Perceptron
2.2 Deep Neural Networks
2.3 LSTM
3 Action Detection Through Classification
4 Conclusions
References
Feature Clustering with Fading Affect Bias: Building Visual Vocabularies on the Fly
1 Introduction
2 Method Overview
3 Parameter Estimation
4 Experimental Results
5 Conclusions
References
HoP: Histogram of Patterns for Human Action Representation
1 Introduction
2 Related Work
3 Representation by Histogram of Frequent Patterns
3.1 Codebook of Frequent Patterns
3.2 Histogram of Frequent Patterns
4 Experimental Results
4.1 Results
5 Conclusions and Future Work
References
Revisiting Human Action Recognition: Personalization vs. Generalization
1 Introduction
2 Datasets and Feature Encoding
3 Evaluation Strategies
4 Experimental Results and Discussion
4.1 Quantitative Statistical Analysis
5 Divide et Impera. Two-Stage Recognition Pipeline
6 Conclusions
References
Multiview Geometry and 3D Computer Vision
Efficient Confidence Measures for Embedded Stereo
1 Introduction
2 Related Work
3 Hardware Strategies for Confidence Implementation
4 Confidence Measures Suited for Hardware Implementation
4.1 Hardware Friendly
4.2 Hardware Challenging
5 Experimental Results
5.1 Evaluation Protocol
5.2 Experimental Evaluation on Middlebury 2014 and KITTI 2015
6 Conclusions
References
3D Reconstruction from Specialized Wide Field of View Camera System Using Unified Spherical Model
1 Introduction
1.1 Proposed System
2 Methodology
2.1 Unified Spherical Camera Model
2.2 Camera Calibration Using Zero-Degree Overlapping Constraint
2.3 Epipolar Geometry of Omnidirectional Camera
3 Experimental Results
3.1 Estimation of Intrinsic Parameters
3.2 Estimation of Extrinsic Parameters
3.3 Estimation the Three Dimensional Registration Error
3.4 3D Reconstruction Using the Camera Rig
4 Conclusions
References
A Matrix Decomposition Perspective on Calibrated Photometric Stereo
1 Introduction
2 The Geometry of Single-Light Images
3 Robust Matrix Completion and Decomposition
4 Detecting Shadows
5 Evaluation the DiLiGenT Dataset
6 Conclusion
References
Dynamic 3D Scene Reconstruction and Enhancement
1 Introduction
2 Related Work
3 Dynamic Scene 3D Reconstruction
4 Robust Point Cloud Registration
4.1 3-Point RANSAC Registration
4.2 Robust ICP Registration
4.3 Dual-Weighted ICP Registration
4.4 Discussions
5 3D Reconstruction Enhancement
6 Experiments
7 Conclusion and Future Work
References
Feature Points Densification and Refinement
1 Introduction
2 Feature Points Densification and Refinement
2.1 Initialization
2.2 Feature Patches Warp
2.3 Feature Densification and Refinement
3 Results
4 Conclusions
References
Fast and Accurate Facial Landmark Localization in Depth Images for In-Car Applications
1 Introduction
2 Related Work
3 Proposed Method
3.1 Image Pre-processing
3.2 Model Architecture
3.3 Training
4 Experimental Results
4.1 MotorMark Dataset
4.2 Quantitative Evaluation
5 Conclusions and Future Work
References
Emotion Recognition by Body Movement Representation on the Manifold of Symmetric Positive Definite Matrices
1 Introduction
2 Related Work
3 Manifold of Symmetric Positive Definite Matrices
4 Representation of Body Movement
5 Emotion Classification
6 Experiments
6.1 Results and Comparative Evaluation
7 Conclusions
References
Lifting 2D Object Detections to 3D: A Geometric Approach in Multiple Views
1 Introduction
2 Related Work
3 Lifting 2D Bounding Boxes to 3D
3.1 Vertex Enumeration Solution
3.2 Bounded Computational Geometry Method
3.3 Interval Analysis
3.4 Interval-Based Triangulation
4 Experiments
4.1 ACCV Dataset Evaluation
4.2 TUW Dataset Evaluation
4.3 ScanNet Dataset
5 Conclusion
References
Image Analysis, Detection and Recognition
A Computer Vision System for the Automatic Inventory of a Cooler
1 Introduction
2 The Pipeline
2.1 Edge Detection
2.2 Shape Detection
2.3 Color Classification
3 Experimental Results
3.1 Random Shelf Configurations
3.2 Ordered Shelf Configurations
4 Conclusions
References
A Convexity Measure for Gray-Scale Images Based on hv-Convexity
1 Introduction
2 The Proposed Gray-Scale Convexity Measure
2.1 Preliminaries
2.2 Measure of hv-Convexity for Binary Images
2.3 Extension of the Convexity Measure to Gray-Scale Images
3 Evaluation and Experiments
4 Conclusion
References
A Hough Voting Strategy for Registering Historical Aerial Images to Present-Day Satellite Imagery
1 Introduction
2 Related Work
3 Methodology
3.1 Hough Voting from Corresponding Local Interest Point Geometry
3.2 Combination of Votes from Local and Global Features
3.3 Correspondence Zoning
3.4 Implementation Details
4 Experiments
5 Conclusions
References
Automatic Detection of Subretinal Fluid and Cyst in Retinal Images
1 Introduction
2 Methods
2.1 Literature Procedures
2.2 Proposed Method
3 Evaluation
3.1 Image Data
3.2 Results and Discussion
4 Conclusion
References
Computer Aided Diagnosis of Pleural Effusion in Tuberculosis Chest Radiographs
1 Introduction
2 Method
2.1 Lung Segmentation
2.2 Features
2.3 Classification
3 Data
4 Results
5 Conclusion
References
Design of a Classification Strategy for Light Microscopy Images of the Human Liver
Abstract
1 Introduction
2 Materials and Methods
2.1 Steatosis Characterization
2.2 Feature Extraction for Non-steatosis Aspect
2.3 Feature Analysis and Principal Component Analysis
2.4 Binary Classifier Training
3 Numerical Results and Discussion
4 Conclusions and Future Developments
References
Improving Face Recognition in Low Quality Video Sequences: Single Frame vs Multi-frame Super-Resolution
1 Introduction
2 Related Work
3 System Architecture
3.1 Super-Resolution Algorithm
3.2 Feature Extraction and Matching Scheme
4 Experimental Assessment
4.1 Description of Experiments
4.2 Results
5 Conclusions
References
Learning to Weight Color and Depth for RGB-D Visual Search
1 Introduction
2 Previous Work
3 Visual Search Architecture
4 The kNN-rank Approach
5 The HyperRGBD Framework
6 Experimental Evaluation
6.1 Results
7 Final Remarks
References
Mine Detection Based on Adaboost and Polynomial Image Decomposition
1 Introduction
2 Related Work
3 Adaboost Based Polynomial Image Decomposition
3.1 Complete Basis
3.2 Polynomial Image Decomposition (PID)
3.3 Adaboost Based PID
4 Experimental Result and Analysis
4.1 Parameters Setting
4.2 Mine Detection
4.3 Results
5 Conclusion
References
Perceptual-Based Color Quantization
1 Introduction
2 The Proposed CQ Model
2.1 Representative Color Selection
2.2 Estimation of the Least Allowed Bin Size
2.3 PCQ Algorithm
3 Experimental Results and Concluding Remarks
References
Product Recognition in Store Shelves as a Sub-Graph Isomorphism Problem
1 Introduction
2 Related Work
3 Proposed Pipeline
3.1 Unconstrained Product Recognition
3.2 Graph-Based Consistency Check
3.3 Product Verification
4 Experimental Results
5 Conclusion and Future Work
References
Real-Time Incremental and Geo-Referenced Mosaicking by Small-Scale UAVs
1 Introduction
2 Related Work
3 The Mosaicking Algorithm
3.1 Background
3.2 Frame Selection and Correction
3.3 Feature Extraction and Matching
3.4 Transformation and Perspective Computation
3.5 Stitching and GPS Association
4 Experimental Results and Discussion
4.1 Low-Altitude and High-Altitude Mosaicking
4.2 Mosaicking Performance
5 Conclusions
References
Automatic Multi-seed Detection for MR Breast Image Segmentation
1 Introduction
2 Related Works
3 Materials
3.1 Gold Standard
4 Methods
4.1 Pre-processing
4.2 Processing
4.3 Segmentation
5 Results and Discussion
6 Conclusions
References
Efficient Image Segmentation in Graphs with Localized Curvilinear Features
1 Introduction
2 Background
2.1 Live Wire (LW)
2.2 Oriented Image Foresting Transform (OIFT)
3 OIFT with Localized Curvilinear Features (OIFT-LCF)
4 Experimental Results
5 Conclusions
References
Historical Handwritten Text Images Word Spotting Through Sliding Window HOG Features
1 Introduction
2 Related Work
3 Proposed Word Spotting Method
3.1 Word Image Pre-processing
3.2 Feature Extraction and Word Matching
4 Dataset
5 Experimental Results
6 Conclusions
References
Incremental Support Vector Machine for Self-updating Fingerprint Presentation Attack Detection Systems
1 Introduction
2 The Proposed Method
2.1 Incremental SVM for Fingerprint Presentation Attacks Detection
2.2 Prior Work
3 Experimental Results
3.1 Dataset
3.2 Experimental Protocol
3.3 Results
4 Conclusions
References
Tampering Detection and Localization in Images from Social Networks: A CBIR Approach
1 Introduction
2 Related Work
3 Proposed Method
3.1 Content-Based Image Retrieval System
3.2 Tampering Localization
4 Experiments
4.1 Datasets
4.2 CBIR System
4.3 Tampering Localization
5 Conclusion
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken