Magnus Heitzler
Biographic Data
| ID | 6746243 |
|---|---|
| NAME | Magnus Heitzler |
| GIVEN NAMES | Magnus |
| FAMILY NAME | Heitzler |
| SIGNATURE | HEITZLER M |
| AFFILIATIONS | ETH Zurich |
| ORCID | 0000-0002-9021-4170 |
| VERIFIED | Yes |
| TOTAL WORKS | 5 |
| TOTAL CITATIONS | 1 |
| AUTHOR COUNT | 5 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2017 |
| LATEST PUBLICATION YEAR | 2024 |
| H-INDEX | 1 |
Scale- and Resolution-Adapted Shaded Relief Generation Using U-Net
On many maps, relief shading is one of the most significant graphical elements. Modern relief shading techniques include neural networks. To generate such shading automatically at an arbitrary scale, one needs to consider how the resolution of the input digital elevation model (DEM) relates to the neural network process and the maps used for training. Currently, there is no clear guidance on which DEM resolution to use to generate relief shading …
A novel framework for road vectorization and classification from historical maps based on deep learning and symbol painting
Road networks in the past are imperative for understanding evolution of transportation infrastructure, urban sprawl, and route planning, etc. Various approaches have been developed for road extraction from historical maps, among which deep learning techniques stand out as the most effective ones. However, little attention has been paid to investigating road vectorization and classification from historical maps. Moreover, road classification via m…
Inferring implicit 3D representations from human figures on pictorial maps
In this work, we present an automated workflow to bring human figures, one of the most frequently appearing entities on pictorial maps, to the third dimension. Our workflow is based on training data and neural networks for single-view 3D reconstruction of real humans from photos. We first let a network consisting of fully connected layers estimate the depth coordinate of 2D pose points. The gained 3D pose points are inputted together with 2D mask…
Terrain Segmentation Using a U-Net for Improved Relief Shading
Since landforms composing land surface vary in their properties and appearance, their shaded reliefs also present different visual impression of the terrain. In this work, we adapt a U-Net so that it can recognize a selection of landforms and can segment terrain. We test the efficiency of 10 separate models and apply an ensemble approach, where all the models are combined to potentially outperform single models. Our algorithm works particularly w…
A Simulation and Visualization Environment for Spatiotemporal Disaster Risk Assessments of Network Infrastructures
Emerging methodologies for risk assessments of civil infrastructure networks require the coupling of several spatiotemporal models that need to be executed multiple times with varying parametrizations to account for model uncertainty and to investigate “what-if” scenarios. These requirements led to the development of a software environment to support the simulation process and the visual analysis of its results. The simulation engine component of…
Inferring implicit 3D representations from human figures on pictorial maps
In this work, we present an automated workflow to bring human figures, one of the most frequently appearing entities on pictorial maps, to the third dimension. Our workflow is based on training data and neural networks for single-view 3D reconstruction of real humans from photos. We first let a network consisting of fully connected layers estimate the depth coordinate of 2D pose points. The gained 3D pose points are inputted together with 2D mask…
A Simulation and Visualization Environment for Spatiotemporal Disaster Risk Assessments of Network Infrastructures
Emerging methodologies for risk assessments of civil infrastructure networks require the coupling of several spatiotemporal models that need to be executed multiple times with varying parametrizations to account for model uncertainty and to investigate “what-if” scenarios. These requirements led to the development of a software environment to support the simulation process and the visual analysis of its results. The simulation engine component of…
Terrain Segmentation Using a U-Net for Improved Relief Shading
Since landforms composing land surface vary in their properties and appearance, their shaded reliefs also present different visual impression of the terrain. In this work, we adapt a U-Net so that it can recognize a selection of landforms and can segment terrain. We test the efficiency of 10 separate models and apply an ensemble approach, where all the models are combined to potentially outperform single models. Our algorithm works particularly w…
Inferring implicit 3D representations from human figures on pictorial maps
In this work, we present an automated workflow to bring human figures, one of the most frequently appearing entities on pictorial maps, to the third dimension. Our workflow is based on training data and neural networks for single-view 3D reconstruction of real humans from photos. We first let a network consisting of fully connected layers estimate the depth coordinate of 2D pose points. The gained 3D pose points are inputted together with 2D mask…
Scale- and Resolution-Adapted Shaded Relief Generation Using U-Net
On many maps, relief shading is one of the most significant graphical elements. Modern relief shading techniques include neural networks. To generate such shading automatically at an arbitrary scale, one needs to consider how the resolution of the input digital elevation model (DEM) relates to the neural network process and the maps used for training. Currently, there is no clear guidance on which DEM resolution to use to generate relief shading …
A novel framework for road vectorization and classification from historical maps based on deep learning and symbol painting
Road networks in the past are imperative for understanding evolution of transportation infrastructure, urban sprawl, and route planning, etc. Various approaches have been developed for road extraction from historical maps, among which deep learning techniques stand out as the most effective ones. However, little attention has been paid to investigating road vectorization and classification from historical maps. Moreover, road classification via m…
Computer Science (5 works) · Artificial Intelligence (4 works) · Cartography (3 works) · Geography (3 works) · Computer vision (2 works) · Deep learning (2 works) · Geographic Information Systems Studies (2 works) · Landslides and related hazards (2 works) · Remote Sensing and LiDAR Applications (2 works) · Segmentation (2 works)