Call number:
S 99.0139(379)
In:
Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover, Nr. 379
Type of Medium:
Series available for loan
Pages:
v, 165 Seiten
,
Illustrationen, Diagramme, Karte
ISBN:
978-3-7696-5291-8
,
9783769652918
ISSN:
0174-1454
Series Statement:
Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover Nr. 379
Language:
English
Note:
Dissertation, Gottfried Wilhelm Leibniz Universität Hannover, 2021
,
Contents
1. Introduction
1.1. Motivation and Research Goal
1.2. Outline
2. Basics
2.1. Archaeology
2.2. Geographic Information System
2.2.1. Spatial Reference System
2.2.2. Coordinate Reference Systems
2.2.3. Raster and Vector Data
2.2.4. GIS Software
2.2.5. GIS Data File Formats
2.3. Remote Sensing
2.3.1. Passive and Active Remote Sensing
2.3.2. LiDAR Systems
2.3.3. Processing LiDAR Data
2.3.4. Digital Terrain Models and Derived Rasters
2.4. Deep Learning
2.4.1. Neurons
2.4.2. Layers
2.4.3. Objective Functions
2.4.4. Evaluation Metrics
2.4.5. Backpropagation
2.4.6. Gradient Descent
2.4.7. Gradient Descent Optimization Algorithms
2.4.8. Supervised Learning
2.4.9. Transfer Learning
2.4.10. Unsupervised Learning
2.4.11. Self Supervised Learning
3. Related Work
3.1. Remote Sensing in Archaeology
3.2. Deep Learning in Remote Sensing
3.3. Deep Learning in Point Clouds and Digital Terrain Models
3.4. Deep Learning in Archaeology
4. Datasets
4.1. Digital Terrain Model and Relief Visualization Dataset
4.2. Archaeological Monuments in the Harz
4.2.1. Areal Dataset
4.2.2. Linear Dataset
4.2.3. Stone Quarries Dataset
4.3. Data Preparation for Deep Learning Models
4.3.1. Data Processing for Self Supervised Learning Pretext
4.3.2. Data Processing for Classification
4.3.3. Data Processing for Instance Segmentation
4.3.4. Data Processing for Semantic Segmentation
5. Methodology
5.1. Pretext Methods
5.1.1. Relief Visualization Network (RVNet)
5.1.2. Relief Visualization GAN (RVGan)
5.2. Downstream Method
5.2.1. Classification of Archaeological Monuments and Terrain Structures
5.2.2. Instance Segmentation of Archaeological Monuments and Terrain Structures
5.2.3. Semantic Segmentation of Archaeological Monuments and Terrain Structures
6. Experiments and Results
6.1. Self Supervised Learning Pretext Experiments
6.2. Classification
6.3. Instance Segmentation
6.3.1. Areal Dataset
6.3.2. Linear Dataset
6.4. Semantic Segmentation
6.4.1. Areal Dataset
6.4.2. Linear Dataset
6.4.3. Stone Quarries Dataset
6.5. Evaluation on 4 Test Regions with Distinct Objects
6.6. Qualitative Evaluations
6.6.1. Qualitative Results for Areal Dataset
6.6.2. Qualitative Results for the Linear Dataset
6.6.3. Qualitative Results for Stone Quarries Dataset
6.7. Summary
7. Discussions and Conclusions
7.1. Discussions
7.1.1. Assessment of Pretext Methods
7.1.2. Assessment of Downstream Methods
7.1.3. Assessment of Selected Core Deep Learning Architectures
7.1.4. Assessment of Predictions for each Category
7.2. Summary and Outlook
List of Figures
List of Tables
Bibliography
Acknowledgements
Resume
A. Appendix
A.1. Self Supervised Learning Pretext
A.2. Classification
A.3. Areal Dataset
A.4. Linear Dataset
,
Sprache der Kurzfassungen: Englisch, Deutsch
Location:
Lower compact magazine
Branch Library:
GFZ Library
