de
en
Schliessen
Detailsuche
Bibliotheken
Projekt
Impressum
Datenschutz
zum Inhalt
Detailsuche
Schnellsuche:
OK
Ergebnisliste
Titel
Titel
Inhalt
Inhalt
Seite
Seite
Im Dokument suchen
Narayan, Vikram: Random center- surround approaches for modeling visual saliency. 2013
Inhalt
Dedication
Acknowledgments
Abstract
Contents
1 Introduction
1.1 Visual Attention
1.2 Saliency Maps
1.3 Thesis Contributions
2 Review of Saliency Models
2.1 Categories of Saliency Models
2.2 Hierarchical approaches
2.3 Spectral approaches
2.4 Power law based approaches
2.5 Image contrast based approaches
2.6 Entropy-based approaches
2.7 Center-surround approaches
2.8 Hybrid approaches
2.9 Top-Down approaches
2.10 Applications
2.10.1 Developmental Robotics
2.10.2 Digital Photography
2.10.3 Image Segmentation
2.11 Summary
3 Bottom-Up Attention Models
3.1 Random Pixels based Saliency (PR1)
3.2 Random Rectangular Sub-Window based Saliency (PR2)
3.3 Random Fixation based Saliency (PR3)
3.4 Experimental Results
3.4.1 Qualitative analysis
3.4.2 Experiments on salient region detection task
3.4.3 Experiments on eye-gaze prediction task
3.4.4 Performance due to change in parameters
3.4.5 Computational Run-Time
3.4.6 Saliency Models for Eye-Gaze Prediction in an Interactive Scenario
3.5 Discussion and Conclusion
4 Saliency model in the context of Goal-Directed Action
4.1 Related Work
4.1.1 Computer Vision
4.1.2 Reinforcement Learning
4.1.3 Interaction Studies
4.2 Motivation and Contributions
4.3 Proposed Model
4.4 Experiments
4.5 Discussion and Conclusion
5 Conclusion and Future Work