Contents

Cover

Title Page

Copyright

Preface

Part I: Basic Concepts and Theory

Chapter 1: Introduction to Visual Attention

1.1 The Concept of Visual Attention

1.2 Types of Selective Visual Attention

1.3 Change Blindness and Inhibition of Return

1.4 Visual Attention Model Development

1.5 Scope of This Book

References

Chapter 2: Background of Visual Attention – Theory and Experiments

2.1 Human Visual System (HVS)

2.2 Feature Integration Theory (FIT) of Visual Attention

2.3 Guided Search Theory

2.4 Binding Theory Based on Oscillatory Synchrony

2.5 Competition, Normalization and Whitening

2.6 Statistical Signal Processing

References

Part II: Computational Attention Models

Chapter 3: Computational Models in the Spatial Domain

3.1 Baseline Saliency Model for Images

3.2 Modelling for Videos

3.3 Variations and More Details of BS Model

3.4 Graph-based Visual Saliency

3.5 Attention Modelling Based on Information Maximizing

3.6 Discriminant Saliency Based on Centre–Surround

3.7 Saliency Using More Comprehensive Statistics

3.8 Saliency Based on Bayesian Surprise

3.9 Summary

References

Chapter 4: Fast Bottom-up Computational Models in the Spectral Domain

4.1 Frequency Spectrum of Images

4.2 Spectral Residual Approach

4.3 Phase Fourier Transform Approach

4.4 Phase Spectrum of the Quaternion Fourier Transform Approach

4.5 Pulsed Discrete Cosine Transform Approach

4.6 Divisive Normalization Model in the Frequency Domain

4.7 Amplitude Spectrum of Quaternion Fourier Transform (AQFT) Approach

4.8 Modelling from a Bit-stream

4.9 Further Discussions of Frequency Domain Approach

References

Chapter 5: Computational Models for Top-down Visual Attention

5.1 Attention of Population-based Inference

5.2 Hierarchical Object Search with Top-down Instructions

5.3 Computational Model under Top-down Influence

5.4 Attention with Memory of Learning and Amnesic Function

5.5 Top-down Computation in the Visual Attention System: VOCUS

5.6 Hybrid Model of Bottom-up Saliency with Top-down Attention Process

5.7 Top-down Modelling in the Bayesian Framework

5.8 Summary

References

Chapter 6: Validation and Evaluation for Visual Attention Models

6.1 Simple Man-made Visual Patterns

6.2 Human-labelled Images

6.3 Eye-tracking Data

6.4 Quantitative Evaluation

6.5 Quantifying the Performance of a Saliency Model to Human Eye Movement in Static and Dynamic Scenes

6.6 Spearman's Rank Order Correlation with Visual Conspicuity

References

Part III: Applications of Attention Selection Models

Chapter 7: Applications in Computer Vision, Image Retrieval and Robotics

7.1 Object Detection and Recognition in Computer Vision

7.2 Attention Based Object Detection and Recognition in a Natural Scene

7.3 Object Detection and Recognition in Satellite Imagery

7.4 Image Retrieval via Visual Attention

7.5 Applications of Visual Attention in Robots

7.6 Summary

References

Chapter 8: Application of Attention Models in Image Processing

8.1 Attention-modulated Just Noticeable Difference

8.2 Use of Visual Attention in Quality Assessment

8.3 Applications in Image/Video Coding

8.4 Visual Attention for Image Retargeting

8.5 Application in Compressive Sampling

8.6 Summary

References

Part IV: Summary

Chapter 9: Summary, Further Discussions and Conclusions

9.1 Summary

9.2 Further Discussions

9.3 Conclusions

References

Index