DLR Portal
Home|Sitemap|Contact Imprint and terms of use Privacy Cookies & Tracking |Deutsch
You are here: Home:Departments:Data Acquisition and Mobilisation:Semantische Segmentierung und Objektextraktion aus 3D-Punktwolken
Advanced Search
Institute
Departments
Data Management and Enrichment
Data Analysis and Intelligence
Data Acquisition and Mobilisation
Distributed Intelligence & Open Innovation
Applied Web- and Social Media-Data Analysis
Data Availability and Provision
HPDA
Job offers
Publications
DLR_School_Lab Jena
Print

Semantic Segmentation and Object Extraction from Point Clouds



The core of the project is the application, extension and development of modern techniques from the field of machine learning for object segmentation from unstructured 3D point clouds. An important question is to decide how fine granular with classical approaches of semantic segmentation the individual elements can be determined as fully automated as possible. Thereby, the annotation effort for the training should be kept as low as possible. Furthermore, approaches are to be investigated and developed which make it possible to integrate expert or domain knowledge into the semantic segmentation. So-called "generative adversarial networks" for unsupervised modeling are one object of investigation. The research and development work also includes the elaboration of suitable forms of representation to capture the individual objects (e.g., skeletons, graphs). Finally, the developed methods will be applied to the application scenario "tree mapping from 3D LiDAR data" and it will be investigated to what extent the methods can be transferred to "building mapping from 3D stereo data".

 

Project runtime: 2017 - 2021

Partners: FSU

Website: -

Spokeperson:  Dr. Friederike Klan

 


Current Projects
UndercoverEisAgenten
Shadow
Pixel Machine
Join_In_Lab
Data4Human
AgriSens DEMMIN 4.0
Nachtlicht-BüHNE
Hainich - Project
HyperSense
Modelling Citizen Science Data
DEMMIN Biophys
New possibilities for collecting forestry data
Related Topics
Cybernetics, Artificial Intelligence and Robotics
Communications and Radar
Copyright © 2022 German Aerospace Center (DLR). All rights reserved.