DeepReflecs: Deep Learning for Automotive Object Classification with Radar Reflections

This paper presents an novel object type classification method for automotive applications which uses deep learning with radar reflections. The method provides object class information such as pedestrian, cyclist, car, or non-obstacle. The method is both powerful and efficient, by using a light-weig...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ulrich, Michael, Gläser, Claudius, Timm, Fabian
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Ulrich, Michael
Gläser, Claudius
Timm, Fabian
description This paper presents an novel object type classification method for automotive applications which uses deep learning with radar reflections. The method provides object class information such as pedestrian, cyclist, car, or non-obstacle. The method is both powerful and efficient, by using a light-weight deep learning approach on reflection level radar data. It fills the gap between low-performant methods of handcrafted features and high-performant methods with convolutional neural networks. The proposed network exploits the specific characteristics of radar reflection data: It handles unordered lists of arbitrary length as input and it combines both extraction of local and global features. In experiments with real data the proposed network outperforms existing methods of handcrafted or learned features. An ablation study analyzes the impact of the proposed global context layer.
doi_str_mv 10.48550/arxiv.2010.09273
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2010_09273</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2010_09273</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-b9ae3cd66222f48342142c3dcf47003719f091e53a5351fe5c79d265bf99cd5a3</originalsourceid><addsrcrecordid>eNotj8tOwzAUBb1hgQofwAr_QIqfcc2uCk8pUqWqYhvd2NetUZpUjinw95C2q6Mzi5GGkDvO5mqhNXuA9BOPc8H-AbPCyGvy8YR4WGPo0I2PdDq0Rkh97Lc0DIkuv_KwH3I8Il21n-gyrToYxxiigxyHnn7HvKNr8JDoWTPR8YZcBehGvL3sjGxenjfVW1GvXt-rZV1AaWTRWkDpfFkKIYJaSCW4Ek56F5RhTBpuA7MctQQtNQ-onbFelLoN1jqvQc7I_Vl7CmsOKe4h_TZTYHMKlH8ZhktX</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>DeepReflecs: Deep Learning for Automotive Object Classification with Radar Reflections</title><source>arXiv.org</source><creator>Ulrich, Michael ; Gläser, Claudius ; Timm, Fabian</creator><creatorcontrib>Ulrich, Michael ; Gläser, Claudius ; Timm, Fabian</creatorcontrib><description>This paper presents an novel object type classification method for automotive applications which uses deep learning with radar reflections. The method provides object class information such as pedestrian, cyclist, car, or non-obstacle. The method is both powerful and efficient, by using a light-weight deep learning approach on reflection level radar data. It fills the gap between low-performant methods of handcrafted features and high-performant methods with convolutional neural networks. The proposed network exploits the specific characteristics of radar reflection data: It handles unordered lists of arbitrary length as input and it combines both extraction of local and global features. In experiments with real data the proposed network outperforms existing methods of handcrafted or learned features. An ablation study analyzes the impact of the proposed global context layer.</description><identifier>DOI: 10.48550/arxiv.2010.09273</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning ; Computer Science - Robotics</subject><creationdate>2020-10</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2010.09273$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2010.09273$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Ulrich, Michael</creatorcontrib><creatorcontrib>Gläser, Claudius</creatorcontrib><creatorcontrib>Timm, Fabian</creatorcontrib><title>DeepReflecs: Deep Learning for Automotive Object Classification with Radar Reflections</title><description>This paper presents an novel object type classification method for automotive applications which uses deep learning with radar reflections. The method provides object class information such as pedestrian, cyclist, car, or non-obstacle. The method is both powerful and efficient, by using a light-weight deep learning approach on reflection level radar data. It fills the gap between low-performant methods of handcrafted features and high-performant methods with convolutional neural networks. The proposed network exploits the specific characteristics of radar reflection data: It handles unordered lists of arbitrary length as input and it combines both extraction of local and global features. In experiments with real data the proposed network outperforms existing methods of handcrafted or learned features. An ablation study analyzes the impact of the proposed global context layer.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><subject>Computer Science - Robotics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tOwzAUBb1hgQofwAr_QIqfcc2uCk8pUqWqYhvd2NetUZpUjinw95C2q6Mzi5GGkDvO5mqhNXuA9BOPc8H-AbPCyGvy8YR4WGPo0I2PdDq0Rkh97Lc0DIkuv_KwH3I8Il21n-gyrToYxxiigxyHnn7HvKNr8JDoWTPR8YZcBehGvL3sjGxenjfVW1GvXt-rZV1AaWTRWkDpfFkKIYJaSCW4Ek56F5RhTBpuA7MctQQtNQ-onbFelLoN1jqvQc7I_Vl7CmsOKe4h_TZTYHMKlH8ZhktX</recordid><startdate>20201019</startdate><enddate>20201019</enddate><creator>Ulrich, Michael</creator><creator>Gläser, Claudius</creator><creator>Timm, Fabian</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20201019</creationdate><title>DeepReflecs: Deep Learning for Automotive Object Classification with Radar Reflections</title><author>Ulrich, Michael ; Gläser, Claudius ; Timm, Fabian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-b9ae3cd66222f48342142c3dcf47003719f091e53a5351fe5c79d265bf99cd5a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><topic>Computer Science - Robotics</topic><toplevel>online_resources</toplevel><creatorcontrib>Ulrich, Michael</creatorcontrib><creatorcontrib>Gläser, Claudius</creatorcontrib><creatorcontrib>Timm, Fabian</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ulrich, Michael</au><au>Gläser, Claudius</au><au>Timm, Fabian</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>DeepReflecs: Deep Learning for Automotive Object Classification with Radar Reflections</atitle><date>2020-10-19</date><risdate>2020</risdate><abstract>This paper presents an novel object type classification method for automotive applications which uses deep learning with radar reflections. The method provides object class information such as pedestrian, cyclist, car, or non-obstacle. The method is both powerful and efficient, by using a light-weight deep learning approach on reflection level radar data. It fills the gap between low-performant methods of handcrafted features and high-performant methods with convolutional neural networks. The proposed network exploits the specific characteristics of radar reflection data: It handles unordered lists of arbitrary length as input and it combines both extraction of local and global features. In experiments with real data the proposed network outperforms existing methods of handcrafted or learned features. An ablation study analyzes the impact of the proposed global context layer.</abstract><doi>10.48550/arxiv.2010.09273</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2010.09273
ispartof
issn
language eng
recordid cdi_arxiv_primary_2010_09273
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
Computer Science - Robotics
title DeepReflecs: Deep Learning for Automotive Object Classification with Radar Reflections
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T12%3A07%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=DeepReflecs:%20Deep%20Learning%20for%20Automotive%20Object%20Classification%20with%20Radar%20Reflections&rft.au=Ulrich,%20Michael&rft.date=2020-10-19&rft_id=info:doi/10.48550/arxiv.2010.09273&rft_dat=%3Carxiv_GOX%3E2010_09273%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true