Painer Variation Based Dense 3D Reconstruction

Application on Monocular Mini-Laparoscopic Sequences
1. Auflage 2016
ISBN: 978-3-658-12698-8
Verlag: Springer
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 87 Seiten

Reihe: BestMasters

In his master thesis, Sven Painer develops, implements, and evaluates a method to reconstruct the liver surface from monocular mini-laparoscopic sequences. The principal focus of his research is to create a basis for helping clinicians to write reports with quantitative descriptions of the liver surface. A Structure from Motion approach is performed to do a sparse reconstruction of the liver surface and subsequently this information is used in a variation based dense 3D reconstruction. The algorithms are formulated in a causal way, enabling the implementation to be run in real-time on an adequate hardware platform. The results show a significant performance increase and pave the way to give clinicians a feedback during video capturing to improve the quality of the reconstruction in the near future.

Sven Painer is working as a PhD student at the Vision Systems Institute at Hamburg University of Technology. He continues the work on 3D reconstruction that he started during his master thesis.

Autoren/Hrsg.

Painer, Sven

Inhaltsverzeichnis

1;Institute Profile;6
2;Preface;7
3;Acknowledgements;8
4;Contents;9
5;List of Figures;11
6;List of Tables;13
7;Chapter 1;14
7.1;Introduction;14
7.1.1;1.1 Motivation;14
7.1.2;1.2 Task Definition;15
8;Chapter 2;16
8.1;Theoretical Background;16
8.1.1;2.1 Legendre-Fenchel Transformation;16
8.1.2;2.2 Photometric Invariants;17
8.1.3;2.3 Sparse Reconstruction;19
8.1.3.1;2.3.1 Tracking;19
8.1.3.2;2.3.2 Keyframe Selection and Pose Estimation;20
8.1.4;2.4 Dense Reconstruction;23
8.1.4.1;2.4.1 Variational Approach;23
9;Chapter 3;30
9.1;Implementation;30
9.1.1;3.1 Configuration;30
9.1.2;3.2 CUDA Framework;32
9.1.3;3.3 Sparse Reconstruction;33
9.1.3.1;3.3.1 Structure from Motion;34
9.1.3.2;3.3.2 Tracking;34
9.1.3.3;3.3.3 Pose Estimation;35
9.1.3.4;3.3.4 Triangulation;36
9.1.3.5;3.3.5 Bundle Adjustment;36
9.1.4;3.4 Dense Reconstruction;37
10;Chapter 4;40
10.1;Evaluation;40
10.1.1;4.1 Ground Truth Data;40
10.1.2;4.2 Sparse Reconstruction;41
10.1.3;4.3 Dense Reconstruction;42
10.1.4;4.4 Performance;45
11;Chapter 5;47
11.1;Conclusion;47
12;Appendix A;49
12.1;Class Diagrams of CUDA Framework;49
13;Appendix B;52
13.1;Class Diagrams of Sparse Reconstruction;52
14;Appendix C;57
14.1;Evaluation Results of Sparse Reconstruction;57
15;Bibliography;86