Taking into account aspects of semantic world models and graph databases, Nico Hempe presents concepts for a new class of modern Multi-Domain VR Simulation Systems based on the principles of the research field of eRobotics. Nico Hempe not only shows how to overcome structural differences between rendering and simulation frameworks to allow attractive and intuitive representations of the generated results, he also demonstrates ways to enable rendering-supported simulations. The outcome is an intuitive multi-purpose development tool for multiple applications, ranging from industrial domains over environmental scenarios up to space robotics.
Author(s): Nico Hempe
Publisher: Springer
Year: 2016
Language: English
Pages: 244
Computer Vision
Preface
Acknowledgements
Contents
Chapter 1 Introduction
Chapter 2 Image formation
Chapter 3 Image processing
Chapter 4 Feature detection and matching
Chapter 5 Segmentation
Chapter 6 Feature-based alignment
Chapter 7 Structure from motion
Chapter 8 Dense motion estimation
Chapter 9 Image stitching
Chapter 10 Computational photography
Chapter 11 Stereo correspondence
Chapter 12 3D reconstruction
Chapter 13 Image-based rendering
Chapter 14 Recognition
Chapter 15 Conclusion
Appendix A Linear algebra and numerical techniques
Appendix B Bayesian modeling and inference
Appendix C Supplementary material
References
Index
