elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

A Sensor-AI approach to improve visual odometry in dynamic environments

Irmisch, Patrick (2021) A Sensor-AI approach to improve visual odometry in dynamic environments. 2nd Sensor AI Workshop, 24. Nov. 2021, Berlin, Deutschland. (Unpublished)

[img] PDF - Only accessible within DLR
2MB

Abstract

A key component of the interdisciplinary research field Sensor-AI is the close interaction and combination of physical models, data based models and classical approaches in one sensor system, primary for applications that are defined by strict energy requirements. This concept finds practical use cases in many domains. I propose a Sensor-AI based approach that targets to improve visual odometry specifically in uncommon high dynamic environments. It combines classical feature-based visual odometry, which relies on physical models and analytical error propagation, with a data-based model in form of a deep neural network for semantic segmentation. The former is used to automatically generate semantic labels to train the neural network offline, simultaneously for multiple environments, and use its inference output to generate a mask for feature selection online. The proposed method is evaluated on datasets that contain the two dynamic environment elements steam and water, recorded at a volcanic fumarole field, a coast line and a river.

Item URL in elib:https://elib.dlr.de/148452/
Document Type:Conference or Workshop Item (Speech)
Title:A Sensor-AI approach to improve visual odometry in dynamic environments
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Irmisch, PatrickPatrick.Irmisch (at) dlr.deUNSPECIFIED
Date:November 2021
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Status:Unpublished
Keywords:Artificial Intelligence, Deep Learning, Visual Odometry, Dynamic Environments, Sensor AI
Event Title:2nd Sensor AI Workshop
Event Location:Berlin, Deutschland
Event Type:Workshop
Event Dates:24. Nov. 2021
Organizer:DLR
HGF - Research field:other
HGF - Program:other
HGF - Program Themes:other
DLR - Research area:Digitalisation
DLR - Program:D IAS - Innovative Autonomous Systems
DLR - Research theme (Project):D - SKIAS
Location: Berlin-Adlershof
Institutes and Institutions:Institute of Optical Sensor Systems
Institute of Optical Sensor Systems > Real-Time Data Processing
Deposited By: Irmisch, Patrick
Deposited On:25 Jan 2022 08:19
Last Modified:25 Jan 2022 08:19

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.