ALBERT — All Library Books, journals and Electronic Records Telegrafenberg

Hits per page

hits 1 - 10 | 13 hits

Sorting

Series available for loan

Uncertainty estimation for dense stereo matching using Bayesian deep learning (2021)

Mehltretter, Max [VerfasserIn]

Hannover : Leibniz Universität Hannover

Associated volumes

add to mindlist on the mindlist

Details Availability

Call number: S 99.0139(378)

In: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover, Nr. 378

Type of Medium: Series available for loan

Pages: viii, 117 Seiten , Illustrationen, Diagramme

ISSN: 0174-1454

Series Statement: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover Nr. 378

URL: https://d-nb.info/1264856385/04

Language: English

Note: Dissertation, Fakultät für Bauingenieurwesen und Geodäsie der Gottfried Wilhelm Leibniz Universität Hannover, 2021 , 1 Introduction 1.1 Problem Statement 1.2 Contributions 1.3 Thesis Outline 2 Basics 2.1 Dense Stereo Matching 2.1.1 Terminology and Practical Simplifications 2.1.2 Taxonomy of the Matching Process 2.1.3 Challenges and Common Assumptions 2.2 Uncertainty Quantification 2.3 Deep Learning 2.3.1 Convolutional Neural Networks 2.3.2 Bayesian Neural Networks 3 Related Work 3.1 Dense Stereo Matching 3.2 Aleatoric Uncertainty Estimation 3.3 Epistemic Uncertainty Estimation 3.4 Discussion 4 Uncertainty Estimation for Dense Stereo Matching - A New Method 4.1 Overview 4.2 Aleatoric Uncertainty Estimation 4.2.1 CNN-based Cost Volume Analysis 4.2.2 Uncertainty Models 4.3 Epistemic Uncertainty Estimation 4.3.1 Functional Model 4.3.2 Stochastic Model 4.4 Joint Uncertainty Estimation 4.5 Discussion 5 Experimental Setup 5.1 Objectives 5.2 Datasets 5.3 Training and Hyper-parameter Settings 5.3.1 General Remarks 5.3.2 CVA-Net 5.3.3 Probabilistic GC-Net 5.3.4 Combined Approach 5.4 Evaluation Strategy andCriteria 5.4.1 Disparity Error Metrics 5.4.2 Confidence Error Metric 5.4.3 Uncertainty Error Metric 5.4.4 Region Masks 5.4.5 Monte Carlo Sampling 6 Results and Discussion 6.1 CVA-Net Architecture 6.2 Aleatoric Uncertainty Models 6.3 Dense Stereo Matching using a Bayesian Neural Network 6.3.1 Comparison to the Deterministic Baseline 6.3.2 On the Relevance of Aleatoric and Epistemic Uncertainty 6.3.3 The Kullback-Leibler Divergence and the Mode Collapse Problem 6.4 Discussion 7 Conclusions and Outlook Bibliography Acknowledgment

Location: Lower compact magazine

Branch Library: GFZ Library

Permalink

	Location	Call Number	Expected	Availability

Others were also interested in ...

BOOK

Link to Library Catalog

S·F·X

Series available for loan

A hierarchical deep learning framework towards the verification of geospatial databases (2022)

Yang, Chun [VerfasserIn] 1987- ; Rottensteiner, Franz [AkademischeR BetreuerIn] ; Sester, Monika [AkademischeR BetreuerIn] ; [et al.]

Hannover : Leibniz Universität Hannover

Associated volumes

add to mindlist on the mindlist

Details Availability

Call number: S 99.0139(377)

In: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover, Nr. 377

Type of Medium: Series available for loan

Pages: XVI, 146 Seiten , Diagramme, Illustrationen, Karten

ISBN: 978-3-7696-5295-6 , 9783769652956

ISSN: 0065-5325

Series Statement: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover Nr. 377

URL: Table of Contents

Language: English , German

Note: Dissertation, Gottfried Wilhelm Leibniz Universität Hannover, 2021 , Contents 1. Introduction 1.1. Motivation 1.2. Goal and Contributions 1.3. Structure of this Thesis 2. Fundamentals 2.1. Classification 2.2. Artificial Neural Network 2.2.1. Perceptron 2.2.2. Multilayer Percptrons 2.2.3. Training 2.2.3.1. Loss Function 2.2.3.2. Gradient Descent Optimization 2.2.3.3. Step Learning Policy 2.3. Convolution Neural Networks 2.3.1. Components 2.3.1.1. Convolution 2.3.1.2. Pooling 2.3.1.3. Batch Normalization 2.3.2. CNN for Image Classification 2.3.3. CNN for Semantic Segmentation 2.3.3.1. Fully Convolution Networks 2.3.3.2. U-Net 2.3.4. Training 2.3.5. Data Augmentation 3. Related Work 3.1. CNN in general 3.1.1. Image Classification 3.1.2. Semantic Segmentation 3.2. Land Cover Classification 3.3. Land Use Classification 3.3.1. Methods not based on CNN 3.3.2. CNN-based Methods 3.4. Discussion 3.4.1. Land Cover Classification 3.4.2. Land Use Classification 4. Methodology 4.1. Overview 4.2. Land Cover Classification 4.2.1. Network Architecture 4.2.2. Network Variants 4.2.2.1. Network without skip-connections 4.2.2.2. Network with elementwise addition skip-connections 4.2.2.3. Network with learnable skip-connections 4.2.3. Training 4.3. Hierarchical Land Use Classification 4.3.1. Polygon Shape Representation 4.3.2. Patch Preparation 4.3.2.1. Tiling 4.3.2.2. Scaling 4.3.2.3. Combination of tiling and scaling 4.3.3. Network Architecture 4.3.3.1. Base Network for Mask Representation: LuNet-lite 4.3.3.2. LuNet-lite with Multi-Task Learning 4.3.3.3. Achieving Consistency with the Class Hierarchy 4.3.3.4. Network Architecture for Implicit Representation 4.3.4. Training 4.3.4.1. LuNet-lite 4.3.4.2. LuNet-lite-MT 4.3.4.3. LuNet-lite-JO and LuNet-lite-BG-JO 4.3.5. Inference at Object Level 5. Datasets and Test Setup 5.1. Datasets 5.1.1. Hameln 5.1.2. Schleswig 5.1.3. Mecklenburg-Vorpommern (MV) 5.1.4. Vaihingen and Potsdam 5.2. Evaluation Metrics 5.3. Experimental Setup 5.3.1. Land Cover Classification 5.3.1.1. Test Setup 5.3.1.2. Overview of all Experiments 5.3.1.3. Prediction Variability of FuseNet-lite 5.3.1.4. Impact of the Hyperparameter Settings 5.3.1.5. Effectiveness of the learnable Skip-Connections 5.3.1.6. Performance of FuseNet-lite 5.3.1.7. Combining Datasets 5.3.2. Land Use Classification 5.3.2.1. Input Configurations 5.3.2.2. Test Setup 5.3.2.3. Overview of all Experiments 5.3.2.4. Prediction Variability of LuNet-lite-JO 5.3.2.5. Impact of the Hyperparameter Settings 5.3.2.6. Impact of Joint Optimization 5.3.2.7. Impact of the Polygon Representation 5.3.2.8. Impact of Land Cover Information 5.3.2.9. Impact of the Patch Generation 5.3.2.10. Evaluation on all Datasets 5.3.2.11. Combining Datasets 6. Experiments 6.1. Evaluation of Land Cover Classification 6.1.1. Prediction Variability of FuseNet-lite 6.1.2. Investigations of the Hyperparameter Settings 6.1.2.1. Base Learning Rate 6.1.2.2. Mini Batch Size 6.1.2.3. The Weight of the Penalty Term in the Focal Loss 6.1.3. Effectiveness of the learnable Skip-Connections 6.1.4. Evaluation on the individual Datasets 6.1.4.1. Hameln, Schleswig and MV 6.1.4.2. Vaihingen and Potsdam 6.1.4.3. Answers to the Questions raised in Section 5.3.1.6 6.1.5. Training on the combined Datasets 6.1.6. Discussion 6.2. Evaluation of Land Use Classification 6.2.1. Prediction Variability of LuNet-lite-JO 6.2.2. Investigations of the Hyperparameter Settings 6.2.2.1. Base Learning Rate 6.2.2.2. Mini Batch Size 6.2.2.3. The Weight of the Penalty Term in the Focal Loss 6.2.3. Impact of Joint Optimization 6.2.4. Impact of the Polygon Representation 6.2.5. Impact of Land Cover Information 6.2.6. Impact of the Patch Generation Approach 6.2.7. Evaluation on all Datasets 6.2.8. Training on combined Datasets 6.2.9. Discussion 7. Conclusion and Outlook 7.1. Conclusion 7.2. Outlook References , Sprache der Kurzfassungen: Englisch, Deutsch

Location: Lower compact magazine

Branch Library: GFZ Library

Permalink

	Location	Call Number	Expected	Availability

Others were also interested in ...

BOOK

Link to Library Catalog

S·F·X

Series available for loan

Kalman filtering with state constraints applied to multi-sensor systems and georeferencing (2020)

Vogel, Sören [VerfasserIn] 1988-

Hannover : Leibniz Universität Hannover

Associated volumes

add to mindlist on the mindlist

Details Availability

Call number: S 99.0139(364)

In: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover, Nr. 364

Type of Medium: Series available for loan

Pages: XVI, 121 Seiten , Illustrationen, Diagramme

ISBN: 978-3-7696-5268-0

Series Statement: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Universität Hannover Nr. 364

Language: English

Note: List of Figures List of Tables Acronyms 1 Introduction 1.1 Motivation 1.2 Objective and Outline 2 Fundamentals of Recursive State-space Filtering 2.1 Parameter Estimation 2.1.1 Gauss-Markov Model 2.1.2 Gauss-Helmert Model 2.1.3 Recursive Parameter Estimation 2.2 Recursive State-space Filtering 2.2.1 Iterated Extended Kalman Filter for Gauss-Markov Models 2.2.2 Iterated Extended Kalman Filter for Gauss-Helmert Models 2.3 State Constraints 2.3.1 Hard Constraints 2.3.2 Soft Constraints 2.3.3 Non-linear Constraints 3 Methodological Contributions 3.1 Versatile Recursive State-space Filter 3.2 Kalman Filtering with State Constraints for Gauss-Helmert Models 3.2.1 Implicit Pseudo Observations 3.2.2 Constrained Objective Function 3.2.3 Improvement of Implicit Contradictions 3.3 Recursive Gauss-Helmert Model 3.4 Example of Application 3.4.1 Monte-Carlo Simulation and Consistency 3.4.2 Results 3.4.3 Conclusions 4 Kinematic Multi-sensor Systems and Their Efficient Calibration 4.1 Kinematic Multi-sensor Systems 4.2 Calibration of Laser Scanner-based Multi-sensor Systems 4.2.1 Motivation 4.2.2 Experimental Setup 4.2.3 Classical Methods 4.2.4 Novel Recursive Calibration Approach 4.2.5 Comparison and Discussion 5 Information-based Georeferencing 5.1 Motivation 5.2 Experimental Setup 5.2.1 Kinematic Laser Scanner-based Multi-sensor Systems 5.2.2 Scenarios and Measuring Process 5.2.3 Additional Object Space Information 5.3 State of the Art Methods 5.4 Novel Information-based Georeferencing Approach 5.4.1 Basic Idea 5.4.2 Transformation of the Laser Scanner Observations 5.4.3 Assignment of the Laser Scanner Observations 5.4.4 Application of the Versatile Recursive State-space Filter 5.5 Comparison and Discussion 5.5.1 Mapping Within an Inner Courtyard 5.5.2 Georeferencing of an Autonomous Vehicle Within an Urban Canyon 5.5.3 Conclusions 6 Conclusions 6.1 Summary 6.2 Outlook A Appendix A.1 Pseudocode of the Versatile Recursive State-space Filter A.2 Analysis for the Selection of a Suitable Measurement and Process Noise Bibliography Acknowledgments CurriculumVitae , Zusammenfassung in englisch und deutsch Seite v-vii

Location: Lower compact magazine

Branch Library: GFZ Library

Permalink

	Location	Call Number	Expected	Availability

Others were also interested in ...

BOOK

Link to Library Catalog

S·F·X

Series available for loan

Characterizing slope instability kinematics by integrating multi-sensor satellite remote sensing observations (2023)

Zhuge, Xia [VerfasserIn]

Hannover : Leibniz Universität Hannover

Associated volumes

add to mindlist on the mindlist

Details Availability

Call number: S 99.0139(389)

In: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover, Nr. 389

Type of Medium: Series available for loan

Pages: xvii, 137 Seiten , Illustrationen, Diagramme, Karten

ISBN: 978-3-7696-5319-9 , 9783769653199

ISSN: 0174-1454

Series Statement: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover Nr. 389

Language: English

Note: Dissertation, Gottfried Wilhelm Leibniz Universität Hannover, 2023 , Contents List of Abbreviations xv 1 Introduction 1.1 Research Objectives 1.2 Outline and Structure of Thesis 2 Theoretical Background 2.1 Introduction 2.2 Glance at Landslide Hazards 2.2.1 Overview 2.2.2 Landslide Types 2.2.2.1 Type of Movement 2.2.2.2 Material Classification 2.2.2.3 Landslide Depth 2.2.3 Landslide Distribution 2.2.4 Landslide Implications and Measurements 2.2.5 Slow-moving Landslide 2.3 Landslide Remote Sensing 2.3.1 Overview 2.3.2 Airborne Remote Sensing 2.3.3 Spaceborne Remote Sensing 2.4 Spaceborne Optical Imagery 2.4.1 Overview 2.4.2 Pixel Offset Tracking (POT) 2.5 Spaceborne Radar Imagery 2.5.1 Synthetic Aperture Radar (SAR) Basic 2.5.1.1 SAR Geometry 2.5.1.2 SAR Acquisition Mode 2.5.1.3 SAR Distortion 2.5.1.4 SAR Mission 2.5.2 Interferometric SAR (InSAR) 2.5.2.1 Workflow of InSAR Processing 2.5.2.2 Coherence and Decorrelation 2.5.2.3 Topographic and Orbital Errors 2.5.2.4 Atmospheric Artifacts 2.5.2.5 Sensitivity of Line-of-sight (LOS) to Slope Motion 2.5.3 Advanced Multi-temporal InSAR (MT-InSAR) 2.5.3.1 Scattering Mechanism 2.5.3.2 Interferogram Stacking 2.5.3.3 Persistent Scatterer Interferometry (PSI) 2.5.3.4 Small Baseline Subsets (SBAS) 2.5.4 Corner Reflector InSAR (CR-InSAR) 2.5.4.1 Overview 2.5.4.2 Conventional Designs 2.5.4.3 Our Experimental Designs 2.5.4.4 CR-InSAR Processing 3 Methodological Contribution 3.1 Challenges in Landslide Monitoring Using Spaceborne Remote Sensing 3.2 Proposed Methodology 3.2.1 Analytically-based Modeling for Inverse Velocity 3.2.2 Identification of Small-scale CR-like Objectives 3.2.3 Modeling 4D Slope Instability Dynamics 4 Pre- and Co-failure: Slope Instability Monitoring Using Spaceborne Remote Sensing 4.1 Abstract 4.2 Introduction 4.3 Environmental and Geomorphological Settings 4.4 Data and Methodology 4.4.1 Remote Sensing Optical Images 4.4.2 MT-InSAR Analysis Using Sentinel-1 SAR Data 4.4.3 Auxiliary Data 4.4.4 Inverse-velocity Theory for Anticipating the Time of Failure 4.5 Results 4.5.1 Horizontal Displacement Based on High-resolution Optical Images 4.5.2 MT-InSAR Analysis 4.5.3 Influence of Precipitation on the Kinematics of the Landslide 4.5.4 INV Results for Anticipating the Time of Failure 4.5.5 Comparison of NDVI and Coherence Values 4.6 Discussion 4.7 Conclusion 4.8 Acknowledgements 4.9 Supplementary Materials 4.9.1 Comparison of River Courses 4.9.2 Detailed Parameters of Exploited SAR Data 4.9.3 Comparison of Baseline Graphs 5 Post-failure: Slope Instability Monitoring Using Artificial Corner Reflectors 5.1 Abstract 5.2 Introduction 5.3 Experiments and Methodology 5.3.1 Experimental Design 5.3.2 Selection Strategy for CRs 5.3.3 Radar Cross-section (RCS) 5.3.4 Signal-to-clutter Ratio (SCR) 5.3.5 CR-InSAR Processing 5.4 Results and Discussion 5.5 Conclusion 5.6 Acknowledgments 5.7 Supplementary Materials 5.7.1 Calculation of SCR 5.7.2 Selection Strategy 5.7.3 Radar Intensity Map 5.7.4 Site Photo of Interference Reflector 6 Post-failure: Characterizing 4D Slope Instability Dynamics 6.1 Abstract 6.2 Introduction 6.3 Geographical Setting of the Study Area 6.4 Methodology 6.4.1 Optical Images Processing 6.4.2 Multi-temporal InSAR Processing 6.4.3 Spatiotemporal Independent Component Analysis (ICA) of Displacement 6.4.4 Multi-sensor Integration Modeling 6.5 Results 6.5.1 Horizontal Deformation Based on Planet Images 6.5.2 MT-InSAR Results 6.5.3 Feature Extraction Using ICA 6.5.4 4D Deformation Modeling 6.6 Discussion 6.6.1 Early Post-failure Deformation from Planet 6.6.2 Post-failure Kinematics from MT-InSAR 6.6.3 ICA-based Spatiotemporal Features of Deformation 6.6.4 Resolving 4D Post-failure Kinematics 6.7 Conclusion 6.8 Acknowledgments 7 Summary and Future Perspectives 7.1 Summary 7.2 Future Perspectives List of Figures List of Tables Bibliography , Sprache der Kurzfassungen: Englisch, Deutsch

Location: Lower compact magazine

Branch Library: GFZ Library

Permalink

	Location	Call Number	Expected	Availability

Others were also interested in ...

BOOK

Link to Library Catalog

S·F·X

Series available for loan

Learning multi-view 2D to 3D label transfer for semi-supervised semantic segmentation of point clouds (2022)

Peters, Torben [VerfasserIn]

Hannover : Leibniz Universität Hannover

Associated volumes

add to mindlist on the mindlist

Details Availability

Call number: S 99.0139(380)

In: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover, Nr. 380

Description / Table of Contents: Semantic segmentation is an important task in computer vision to help machines gain a high-level understanding of the environment, similar to the human vision system. For example it is used in self-driving cars which are equipped with various sensors such as cameras and 3D laser scanners to gain a complete understanding of their environment. In recent years the field has been dominated by Deep Neural Networks (DNNs), which are notorious for requiring large amounts of training data. Creating these datasets is very time consuming and costly. Moreover, the datasets can only be applied to a specific type of sensor. The present work addresses this problem. It will be shown that knowledge from publicly available image datasets can be reused to minimize the labeling costs for 3D point clouds. For this purpose, the labels from classified images are transferred to 3D point clouds. To bridge the gap between sensor modalities, the geometric relationship of the sensors in a fully calibrated system is used. Due to various errors the naive label transfer can lead to a significant amount of incorrect class label assignments in 3D. Within the work the different reasons and possible solutions are shown in order to improve the label transfer.

Type of Medium: Series available for loan

Pages: v, 175 Seiten , Illustrationen, Diagramme

ISBN: 978-3-7696-5301-4 , 9783769653014

ISSN: 0174-1454

Series Statement: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover Nr. 380

URL: https://publikationen.badw.de/de/048254461/pdf/CC%20BY

Language: English

Note: Dissertation, Gottfried Wilhelm Leibniz Universität Hannover, 2022 , Contents 1 Introduction 2 Theoretical Background 2.1 Cameras and Laserscanning 2.1.1 Cameras 2.1.2 Laserscanning 2.2 Machine Learning Fundamentals 2.2.1 Types of Learning 2.2.2 Supervised Learning - Illustrated by Decision Trees 2.2.3 Boosting 2.3 Deep Learning 2.3.1 Basics 2.3.2 Self-Attention 2.3.3 Generative Adversarial Networks 3 Related Work 3.1 Classification and Semantic Segmentation (2D) 3.2 Semantic Segmentation (3D) 3.3 Semi-Supervised Learning 3.4 Conditional Generative Adversarial Networks 3.5 Multi-View Fusion, Prediction and Labeling 3.6 Shape Completion 4 Multi-View Label Transfer and Correction 4.1 2D to 3D Label Transfer 4.1.1 Regular and Self-Occlusions 4.1.2 Dynamic Occlusions 4.1.3 Naive Label Transfer and Label Policy-Based Noise 4.2 Label Noise Correction 4.2.1 Scanstrip-Based Noise Correction 4.2.2 Semi-Supervised Scanstrip-Based Noise Correction 4.2.3 Conclusion 4.3 Multi-View Outlier Correction and Label Transfer 4.3.1 Multi-View Network 4.3.2 Label Transfer Network 4.3.3 Conclusion 5 Self-Supervised Point Cloud Rendering and Completion 5.1 Photo-Realistic Point Cloud Rendering 5.1.1 Network Architecture 5.1.2 Loss Function 5.1.3 Image Stitching 5.2 Self-Supervised Shape Completion 5.2.1 Subregion-Based GAN model 5.2.2 Loss Function 5.2.3 Network Architecture 6 Preparation of MMS data 6.1 Preprocessing of the Mobile Mapping Dataset 6.1.1 Semantic Segmentation of the MMS-Dataset 6.1.2 Human annotated MMS-Dataset 6.2 Massively Parallel Point Cloud Rendering Using Hadoop 6.3 Datasets of Self-Occluded Objects 6.3.1 Real Dataset 6.3.2 Synthetic Datasets 7 Experiments and Results for Multi-View Label Transfer 7.1 Introduction 7.2 Baseline 7.3 Training, Validation and Test Set 7.4 Scanstrip-Based Correction 7.4.1 Point-Wise Correction 7.4.2 Supervised Scanstrip-Based Correction 7.4.3 Semi-Supervised Scanstrip-Based Correction 7.4.4 Qualitative Evaluation 7.4.5 Conclusion and Discussion 7.5 Multi-View Error Correction 7.5.1 Baseline 7.5.2 Training, Validation and Test Sets 7.5.3 Training Procedure 7.5.4 Ablation Studies and Results 7.5.5 Qualitative Evaluation 7.5.6 Retraining Semantic Segmentation Network 7.5.7 Results of the Retraining Process 7.5.8 Conclusion and Discussion 7.6 Multi-View Label Transfer Learning 7.6.1 Training Procedure 7.6.2 Ablation Studies and Results 7.6.3 Qualitative Evaluation 7.6.4 Conclusion and Discussion 7.7 Summary and Conclusion 8 Experiments and Results for Self-Supervised Completion 8.1 Photorealistic Point Cloud Rendering 8.1.1 Training Procedure 8.1.2 Quantitative Evaluation 8.1.3 Qualitative Evaluation 8.1.4 Multi-View Error Correction in GAN Images 8.1.5 Conclusion and Discussion 8.2 Self-Supervised Shape Completion 8.2.1 Training Procedure 8.2.2 Quantitative Evaluation 8.2.3 Qualitative Evaluation 8.2.4 Conclusion and Discussion 9 Conclusion and Discussion 9.1 Summary and Discussion 9.1.1 Scanstrip-Based Label Error Correction 9.1.2 End-To-End Multi-View Label Transfer 9.1.3 Self-Supervised Completion 9.1.4 Conclusion 9.2 Outlook List of Figures List of Tables Bibliography Resume Acknowledgements , Sprache der Kurzfassungen: Englisch, Deutsch

Location: Lower compact magazine

Branch Library: GFZ Library

Permalink

	Location	Call Number	Expected	Availability

Others were also interested in ...

BOOK

Link to Library Catalog

S·F·X

Series available for loan

Self supervised learning for detection of archaeological monuments in LiDAR data (2021)

Kazimi, Bashir [VerfasserIn]

Hannover : Leibniz Universität Hannover

Associated volumes

add to mindlist on the mindlist

Details Availability

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

Permalink

	Location	Call Number	Expected	Availability

Others were also interested in ...

BOOK

Link to Library Catalog

S·F·X

Series available for loan

Simulation framework for collaborative navigation : Development – Analysis – Optimization (2020)

Fernandez, Nicolas Garcia [VerfasserIn] 1988-

Hannover : Leibniz Universität Hannover

Associated volumes

add to mindlist on the mindlist

Details Availability

Call number: S 99.0139(363)

In: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover, Nr. 363

Type of Medium: Series available for loan

Pages: 165 Seiten , Diagramme, Karten

ISBN: 9783769652673

Series Statement: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Universität Hannover Nr. 363

URL: Volltext

Language: English

Note: 1 Introduction 1.1 Motivation and Research Questions 1.2 Objective Definition and Contributions 1.3 Outline of the Thesis 2 Theory and Related Work in Geodetic Network Analysis 2.1 Parameter Estimation in a Gauß - Markov Model 2.2 Parameter Estimation in a Gauß - Helmert Model 2.3 Geodetic Network Optimization: Theoretical Background and Related Work 2.3.1 Network Quality Criteria 2.3.2 Objective Functions and Optimality Criteria 2.3.3 Types of Optimization Problems 2.4 Discussion 3 Theoretical Background in Positioning and Navigation 3.1 Global Navigation Satellite Systems 3.1.1 GNSS Observables 3.1.2 GNSS positioning techniques 3.2 Inertial Navigation Systems 3.2.1 Coordinate Frames 3.2.2 Mechanization in the Navigation Frame 3.2.3 INS/GNSS Integration 3.3 Filtering Techniques 3.3.1 Bayes Filter 3.3.2 Kalman Filter 3.3.3 Linearized Kalman Filter 3.3.4 Extended Kalman Filter 3.4 Multi-Sensor Fusion 3.4.1 Laser Scanner 3.4.2 Stereo Cameras 3.4.3 Localization Versus Simultaneous Location and Mapping 4 State of the art in Collaborative Positioning 4.1 Introduction 4.2 Communication Architectures 4.3 Collaborative Positioning 4.3.1 GNSS Collaborative Positioning Approaches 4.3.2 Inertial Measurement Collaborative Positioning 4.3.3 Collaborative Positioning with Laser Scanner 4.3.4 Collaborative Positioning with Vision-Based Sensors 4.3.5 Collaborative Positioning Using Other Sensors 4.4 Simulation Technologies 4.4.1 Simulation Environments: Overview 4.4.2 Monte Carlo Methods 4.5 Discussion 5 Simulation Framework for Collaborative Scenarios 5.1 Design and Implementation 5.1.1 Vehicle Trajectories Simulator 5.1.2 Environmental Model 5.1.3 Measurement Generation 5.1.4 Collaborative-Extended Kalman Filter 5.1.5 Collaborative SLAM 5.1.6 Localization with Landmark Uncertainty 5.2 Application Example 5.2.1 Scenario and Setup 5.2.2 Sample Run 5.3 Discussion 6 Sensitivity Analysis of Dynamic Sensor Networks 6.1 Geodetic Network Optimization Problems for Dynamic Networks 6.2 Best Sensor Combination 6.2.1 Scenario and Sensor Setup 6.2.2 Sensitivity Results 6.3 Vehicle Dynamics Evaluation 6.3.1 Simulation Scenario and Setup 6.3.2 Process Noise Assessment 6.3.3 Process Noise to Measurement Noise Selection 6.4 Summary and Conclusions 7 Collaboration Versus Single Vehicle Estimation 7.1 Collaborative Navigation: Concept 7.2 Experiment Scenario and Setup 7.3 Collaboration Results 7.3.1 Accuracy and Precision Analysis 7.3.2 Integrity Analysis 7.4 Summary and Discussion 8 Conclusions 8.1 Summary 8.2 Outlook , Zusammenfassung in Englisch und Deutsch Seite i-iii

Location: Lower compact magazine

Branch Library: GFZ Library

Permalink

	Location	Call Number	Expected	Availability

Others were also interested in ...

BOOK

Link to Library Catalog

S·F·X

Series available for loan

Probabilistic Pose Estimation and 3D Reconstruction of Vehicles from Stereo Images (2020)

Coenen, Maximilian Alexander [VerfasserIn] 1987- ; Rottensteiner, Franz [AkademischeR BetreuerIn] ; Brenner, Claus [AkademischeR BetreuerIn] ; [et al.]

Hannover : Leibniz Universität Hannover

Associated volumes

add to mindlist on the mindlist

Details Availability

Call number: S 99.0139(362)

In: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover, Nr. 362

Type of Medium: Series available for loan

Pages: XV, 143 Seiten , Illustrationen, Diagramme

Series Statement: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover Nr. 362

URL: Inhaltsverzeichnis

Language: English

Note: 1 Introduction 1.1 Contributions 1.2 Thesis outline 2 Basics 2.1 Convolutional Neural Networks 2.1.1 Training 2.1.2 CNN Architectures 2.2 Active Shape Model 2.3 Monte Carlo based optimisation 3 State of the art 3.1 Data driven approaches 3.1.1 Viewpoint prediction 3.1.2 3D pose prediction 3.1.3 3D pose and shape prediction 3.2 Model driven approaches 3.2.1 Shape priors 3.2.2 Scene priors 3.2.3 Shape aware reconstruction 3.2.4 Optimisation 3.3 Discussion 4 Methodology 4.1 Overview 4.1.1 Input 4.1.2 Problem statement 4.1.3 Scene layout 4.1.4 Detection of vehicles 4.2 Subcategory-aware 3D shape prior 4.2.1 Geometrical representation 4.2.2 Mode Learning 4.3 Multi-Task CNN 4.3.1 Input branch 4.3.2 Vehicle type branch 4.3.3 Viewpoint branch 4.3.4 Keypoint/Wireframe branch 4.3.5 Training 4.4 Probabilistic vehicle reconstruction 4.4.1 3D likelihood 4.4.2 Keypoint likelihood 4.4.3 Wireframe likelihood 4.4.4 Position prior 4.4.5 Orientation prior 4.4.6 Shape prior 4.4.7 Inference 4.5 Discussion 5 Experimental setup 5.1 Objectives 5.2 Test data 5.2.1 KITTI benchmark 5.2.2 ICSENS data set 5.3 Parameter settings and training 5.3.1 Learning the ASM 5.3.2 Training of the CNN 5.4 Evaluation strategy and evaluation criteria 5.4.1 Detection 5.4.2 Multi-Task CNN 5.4.3 Probabilistic model for vehicle reconstruction 5.4.4 Comparison to related methods 6 Results and discussion 6.1 Detection 6.2 Evaluation of the CNN components 6.2.1 Evaluation of the viewpoint branch 6.2.2 Evaluation of the vehicle type branch 6.3 Ablation studies of the model components 6.3.1 Analysis of the observation likelihoods 6.3.2 Analysis of the state priors 6.4 Analysis of the full model for vehicle reconstruction 6.4.1 Evaluation of the pose 6.4.2 Evaluation of the shape 6.4.3 Analysis of further aspects 6.5 Comparison to related methods 6.6 Discussion 6.6.1 Likelihood terms 6.6.2 State priors 6.6.3 Full model 6.6.4 Inference 7 Conclusion and outlook , Sprache der Kurzfassungen: Englisch, Deutsch

Location: Lower compact magazine

Branch Library: GFZ Library

Permalink

	Location	Call Number	Expected	Availability

Others were also interested in ...

BOOK

Link to Library Catalog

S·F·X

Series available for loan

Integrated Estimation of UAV Image Orientation with a Generalised Building Model (2020)

Unger, Jakob Daniel [VerfasserIn] 1986- ; Heipke, Christian [AkademischeR BetreuerIn] ; Rottensteiner, Franz [AkademischeR BetreuerIn] ; [et al.]

Hannover : Leibniz Universität Hannover

Associated volumes

add to mindlist on the mindlist

Details Availability

Call number: S 99.0139(361)

In: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover, Nr. 361

Type of Medium: Series available for loan

Pages: 108 Seiten , Illustrationen, Diagramme

Series Statement: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover Nr. 361

URL: Inhaltsverzeichnis

Language: English , German

Note: 1 Introduction 1.1 Motivation 1.2 Problem Statement and Contributions 1.3 Structure 2 State-of-the-art 2.1 Integration of Object Knowledge in Image Space 2.2 Integration of Object Knowledge in Object Space 2.3 Discussion 3 Photogrammetric Pose Estimation with a Generalised Building Model 3.1 Overview 3.2 Hybrid Bundle Adjustment 3.2.1 Modelling Relations of Object Points to Model Planes 3.2.2 Functional Model 3.2.3 Stochastic Model 3.2.4 Robust Estimation 3.2.5 Determination of Initial Values 3.3 Workflow 3.3.1 Global Adjustment 3.3.2 Sliding Window Adjustment 4 Assignment Under Generalisation Effects 4.1 Generalisation Effects 4.2 Direct Assignment: Point-Plane-Matching 4.3 Indirect Assignment: Plane-Plane-Matching 4.3.1 Indirect Assignment without ROIs 4.3.2 Indirect Assignment with ROIs 4.4 Summary of the Assignment Parameters 5 Experiments 5.1 Setup of the experiments 5.1.1 Scenarios 5.1.2 Sequences 5.1.3 Evaluation 5.1.4 Structure of the Experiments 5.2 Dataset 5.2.1 Hardware 5.2.2 Data 5.3 Parameter Settings and Implementation 6 Results and Discussion 6.1 The Short Sequence: Generalisation & Systematic Effects 6.2 The Long Sequence: Generalisation & Systematic Effects, Block Deformations... 6.3 Check Point Errors versus Estimated Standard Deviations 6.4 Sliding Window versus Global Adjustment 6.5 Assignment Strategies 6.6 The Full Sequence 6.7 Parameter Variation 6.7.1 Fictitious Distance Observations of Tie Points 6.7.2 Maximum Distance of Tie Points to Model Planes 6.7.3 Estimation of Vertex Coordinates 6.7.4 Window Size Nws and Overlap AW 7 Conclusion and Outlook , Kurzfassungen in Deutscher und Englischer Sprache

Location: Lower compact magazine

Branch Library: GFZ Library

Permalink

	Location	Call Number	Expected	Availability

Others were also interested in ...

BOOK

Link to Library Catalog

S·F·X

Series available for loan

Schema-Matching in räumlichen Datensätzen durch Zuordnung von Objektinstanzen (2020)

Kieler, Birgit [VerfasserIn] 1979- ; Sester, Monika [AkademischeR BetreuerIn] ; Haunert, Jan-Henrik [AkademischeR BetreuerIn] ; [et al.]

Hannover : Leibniz Universität Hannover

Associated volumes

add to mindlist on the mindlist

Details Availability

Call number: S 99.0139(359)

In: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover, Nr. 359

Type of Medium: Series available for loan

Pages: 134 Seiten , Diagramme, Karten

Series Statement: Wissenschaftliche Arbeiten der Fachrichtung Geodäsie und Geoinformatik der Leibniz Universität Hannover Nr. 359

URL: Inhaltsverzeichnis

Language: German , English

Note: 1 Einleitung 1.1 Motivation 1.2 Zielsetzung 1.3 Gliederung 2 Verwandte Arbeiten 2.1 Grundbegriffe 2.1.1 Raumbezogene Objekte 2.1.2 Ähnlichkeit 2.1.3 Relation 2.1.4 Schema 2.2 Data-Matching 2.2.1 Klassifikation von Zuordnungsverfahren auf Objektebene 2.2.2 Herausforderungen bei der Objektzuordnung 2.2.3 Ausgewählte, merkmalsbasierte Verfahren 2.2.4 Ausgewählte, relationale Verfahren 2.3 Schema-Matching 2.3.1 Klassifikation von Zuordnungsverfahren auf Schemaebene 2.3.2 Herausforderungen bei der Zuordnung auf Schemaebene 2.3.3 Ausgewählte Schema-Matching-Verfahren im geographischen Kontext 3 Grundlagen 3.1 Ähnlichkeitsmaße 3.1.1 Geometrische Ähnlichkeit 3.1.2 Topologische Ähnlichkeit 3.1.3 Semantische Ähnlichkeit 3.2 Relationstypen 3.2.1 Relationen auf Objektebene 3.2.2 Relationen auf Schemaebene 3.3 Graphentheorie 3.3.1 Graph-Definitionen 3.3.2 Graph-Matching 3.3.3 Graph-Partitionierung / Graph-Cut 3.4 Ganzzahlige lineare Programmierung 4 Entwicklung von Data-Matching-Verfahren für verschiedene Objektgeometrien 4.1 Zuordnung von Polygonobjekten 4.1.1 Geometrischer Parameter 4.1.2 Heterogenitätsparameter 4.1.3 Erzeugung eines kombinierten Ergebnisses für das Schema-Matching 4.2 Zuordnung von unterschiedlichen Objektgeometrien 5 Entwicklung von Schema-Matching-Verfahren basierend auf Instanzdaten 5.1 Formale Problemdefinition 5.1.1 Synthetisches Beispiel 5.2 Einfache Lösungsverfahren 5.2.1 Beschränkung auf 1:1-Zuordnungen (Max-Match) 5.2.2 Beschränkung auf zwei Cluster (Min-Cut) 5.3 Einsatz von Heuristiken 5.4 Einsatz der ganzzahligen linearen Programmierung 5.4.1 Optimierungsziele und Bedingungen 5.4.2 Kombination von Optimierungszielen 5.4.3 Einführung einer festen Clustergröße (MaxScoreHardConstraintFixedSize) 5.4.4 Optimale Lösung ohne Nullcluster (MaxScoreHardConstraintFixedSizeNonEmpty) 5.4.5 Vereinfachtes Programm (MaxScoreHardConstraintFixedSizeUnique) 6 Experimente mit Realdaten und Untersuchungsergebnisse 6.1 Datenquellen und Datenvorverarbeitung 6.1.1 Datenquellen 6.1.2 Testgebiete 6.1.3 Datenvorverarbeitung 6.2 Ergebnisse des Data-Matching 6.2.1 Testgebiet A: ALKIS OSM in Hannover 6.2.2 Testgebiet B: ALKIS ATKIS in Hameln 6.2.3 Testgebiet C: ATKIS GDF in Hannover-Wedemark 6.2.4 Zusammenfassung der Data-Matching-Ergebnisse 6.3 Ergebnisse des Schema-Matching 6.3.1 Testgebiet B: ALKIS ATKIS in Hameln 6.3.2 Testgebiet A: ALKIS OSM in Hannover 6.3.3 Testgebiet C: ATKIS GDF in Hannover-Wedemark 6.3.4 Zusammenfassung aller Schema-Matching-Ergebnisse 7 Zusammenfassung und Ausblick , Kurzfassungen in Deutscher und Englischer Sprache

Location: Lower compact magazine

Branch Library: GFZ Library

Permalink

	Location	Call Number	Expected	Availability

Others were also interested in ...

BOOK

Link to Library Catalog

S·F·X

hits 1 - 10 | 13 hits