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

Object Detection Based on Deep Learning and Context Information

Pekezou Fouopi, Paulin and Srinivas, Gurucharan and Knake-Langhorst, Sascha and Köster, Frank (2016) Object Detection Based on Deep Learning and Context Information. In: Machine Learning reports. New Challenges in Neural Computation and Machine Learning, 12.09.2016, Hannover, Deutschland.

[img] PDF
113kB

Abstract

In order to avoid collision with other traffic participants automated driving vehicles need to understand the scene around the ego-vehicle. Object detection as part of scene understanding remains a challenging task due to the highly variable object appearances. Object appearances can vary according to position, occlusion, illumination, etc. In this work we propose a combination of convolutional neural networks and context information to improve object detection. Context information and deep learning architectures, which are relevant for object detection, are chosen. Different approaches for integrating context information into the convolutional neural networt are discussed. The combined classifier is trained and evaluated on real scene data.

Item URL in elib:https://elib.dlr.de/112764/
Document Type:Conference or Workshop Item (Speech, Poster)
Title:Object Detection Based on Deep Learning and Context Information
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Pekezou Fouopi, PaulinPaulin.PekezouFouopi (at) dlr.deUNSPECIFIED
Srinivas, GurucharanGurucharan.Srinivas (at) dlr.deUNSPECIFIED
Knake-Langhorst, Saschasascha.knake-langhorst (at) dlr.dehttps://orcid.org/0000-0001-7399-0939
Köster, FrankFrank.Koester (at) dlr.deUNSPECIFIED
Date:2016
Journal or Publication Title:Machine Learning reports
Refereed publication:Yes
Open Access:No
In DOAJ:No
In SCOPUS:No
In ISI Web of Science:No
Editors:
EditorsEmail
Villmann, ThomasUniversity of Applied Sciences Mittweida
Schleif, Frank-MichaelUniversität of Bielefeld
Status:Published
Keywords:Object Detection, Deep Learning, Convolutional Neural Networks, Context Information, Semantic Models, Bayesian Models
Event Title:New Challenges in Neural Computation and Machine Learning
Event Location:Hannover, Deutschland
Event Type:Workshop
Event Dates:12.09.2016
Organizer:GI-Fachgruppe Neuronale Netze, German Neural Networks Society in connection to GCPR 2016
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Terrestrial Vehicles
DLR - Research area:Transport
DLR - Program:V BF - Bodengebundene Fahrzeuge
DLR - Research theme (Project):V - Fahrzeugintelligenz
Location: Braunschweig
Institutes and Institutions:Institute of Transportation Systems
Deposited By: Pekezou Fouopi, Paulin
Deposited On:19 Jun 2017 10:51
Last Modified:09 Feb 2018 07:50

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.