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

A Review of Neural Network based Semantic Segmentation for Scene Understanding in Context of the self driving Car

Niemeijer, Joshua and Pekezou Fouopi, Paulin and Knake-Langhorst, Sascha and Barth, Erhardt (2017) A Review of Neural Network based Semantic Segmentation for Scene Understanding in Context of the self driving Car. In: Student Conference on Medical Engineering Science. Infinite Science Publishing. BioMedTec Studierendentagung, 07.-09. März 2017, Lübeck.

[img] PDF
2MB

Abstract

This paper tackles the challenge of scene understanding in context of automated driving. To react properly to the conditions given by the surrounding scene, the car has to understand it’s environment. Further the real time capability of a method solving this task is essential. For scene understanding the car has to detect and classify surrounding objects. For this purpose one can employ a semantic segmentation to assign a class label to every pixel. In this paper we evaluate the the state of the art methods for the semantic segmentation and perform tests on the FCN-8 architecture. Due to Hardware limitations, we train the FCN-8 on a downscaled version of the Cityscapes Dataset, containing urban traffic scenes. The evaluation of the results shows, the necessity to train the FCN-8 on the original size City Scapes Dataset. We conclude that we need to purchase a better hardware.

Item URL in elib:https://elib.dlr.de/110862/
Document Type:Conference or Workshop Item (Speech, Poster)
Title:A Review of Neural Network based Semantic Segmentation for Scene Understanding in Context of the self driving Car
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Niemeijer, JoshuaJoshua.Niemeijer (at) student.uni-luebeck.deUNSPECIFIED
Pekezou Fouopi, Paulinpaulin.pekezoufouopi (at) dlr.dehttps://orcid.org/0000-0003-3583-8279
Knake-Langhorst, Saschasascha.knake-langhorst (at) dlr.dehttps://orcid.org/0000-0001-7399-0939
Barth, Erhardtbarth (at) inb.uni-luebeck.deUNSPECIFIED
Date:2017
Journal or Publication Title:Student Conference on Medical Engineering Science
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Publisher:Infinite Science Publishing
Status:Published
Keywords:Deep Learning, Semantic Segmentation, Object Detection
Event Title:BioMedTec Studierendentagung
Event Location:Lübeck
Event Type:national Conference
Event Dates:07.-09. März 2017
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Transport System
DLR - Research area:Transport
DLR - Program:V VS - Verkehrssystem
DLR - Research theme (Project):V - Verkehrsentwicklung und Umwelt II (old)
Location: Braunschweig
Institutes and Institutions:Institute of Transportation Systems
Deposited By: Pekezou Fouopi, Paulin
Deposited On:26 Jun 2017 12:55
Last Modified:31 Jul 2019 20:08

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.