When and where do changes occur in dynamic natural landscapes? A new method has been published that enables the automatic extraction of surface changes from entire time series of 3D point clouds. The developed method of spatiotemporal segmentation extracts changes regarding their surface change history, which makes it particularly useful for natural scenes that are [...]
Read Full Post »
This new video by the 3DGeo group presents the challenges of 3D Earth observation and our advances in 4D change analysis in the frame of the Auto3Dscapes project:
Direct link to the video: https://youtu.be/Fdwq-Cp0mFY
Many thanks to Claudia Denis and David Jäger for helping to realize the video! We are also very happy about the fruitful ongoing [...]
Read Full Post »
Posted in 3D, Lidar Group, Publications, Research on Dec 9th, 2019
How can surface change processes be detected and delineated in large time series of 3D point clouds? A paper on the extraction of 4D objects-by-change has just been published in the ISPRS Journal of Photogrammetry and Remote Sensing. It presents an automatic method for 4D change analysis that includes the temporal domain by using [...]
Read Full Post »
Posted in Lidar Group, Publications, Research on Jun 14th, 2019
This week, the 3DGeo participated in the ISPRS Geospatial Week 2019 with two presentations among the sessions of the Laser Scanning Workshop with many interesting talks and poster.
Presentations were given by Ashutosh Kumar in the Machine Learning Session and Katharina Anders in the Change Detection Session.
Highlight: The work by Ashutosh Kumar on feature relevance in [...]
Read Full Post »
Posted in 3D, Lidar Group, Publications, Research on May 31st, 2019
Can you imagine how much sand is being moved on the beach in the course of a week? Did you ever observe truckloads of sand being transported on the beach in the absence of storms and bulldozers? It is hardly possible to estimate to the naked eye, but can be quantified with permanent terrestrial laser [...]
Read Full Post »
Posted in 3D, Lidar Group, Publications, Research on May 31st, 2019
A paper investigating the relevance of (pre-calculated) features for 3D point cloud classification using deep learning was just published in the ISPRS Annals of Photogrammetry and Remote Sensing.
The study presents a non-end-to-end deep learning classifier for 3D point clouds using multiple sets of input features and compares it with an implementation of the state-of-the-art [...]
Read Full Post »
Posted in Events, Lidar Group, Research, Teaching on Apr 5th, 2019
From 01-04 April 2019, the 3DGeo and FCGL research groups organized STAP19, a compact course and workshop on Spatial and Temporal Analysis of Geographic Phenomena at the Interdisciplinary Center for Scientific Computing (IWR, Heidelberg University).
In a mix of lectures, invited talks and hands-on sessions, the participants learned about processing and analysis of 3D geodata, particularly [...]
Read Full Post »
Posted in Events, Lidar Group on Feb 8th, 2019
Three invited speakers are now joining the compact course and workshop STAP19 on Spatial and Temporal Analysis of Geographic Phenomena organized by the 3DGeo and FCGL at IWR in Heidelberg.
Dr. Gottfried Mandlburger (Institute for Photogrammetry, University of Stuttgart) will give a talk on methods of feature and information extraction from geographic 3D point clouds. He [...]
Read Full Post »
Posted in 3D, Lidar Group, Software on Jan 30th, 2019
A series of video tutorials of GigaMesh has recently become available on YouTube. GigaMesh is a software framework for displaying, processing and visualizing large meshes of 3D spatial data representing 2D surfaces.
The most recent tutorial by Paul Bayer and Hubert Mara presents a rapid method of hillshading for a geospatial dataset. The video shows the [...]
Read Full Post »
Posted in 3D, Events, Lidar Group, Teaching on Jan 17th, 2019
From 01-04 April 2019, the 3DGeo and FCGL research groups are organizing a compact course and workshop on Spatial and Temporal Analysis of Geographic Phenomena (STAP19) at the Interdisciplinary Center for Scientific Computing (IWR, Heidelberg University).
The course will teach participants state-of-the-art methods of 3D spatial data processing and analysis with a focus on spatial and [...]
Read Full Post »