On Offline Evaluation of 3D Object Detection for Autonomous Driving

On Offline Evaluation of 3D Object Detection for Autonomous Driving

Prior work in 3D object detection evaluates models using offline metrics like average precision since closed-loop online evaluation on the downstream driving task is costly. However, it is unclear how indicative offline results are of driving performance. In this work, we perform the first empirical...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-08
Hauptverfasser: Schreier, Tim, Renz, Katrin, Geiger, Andreas, Kashyap Chitta
Format: Artikel
Sprache:eng
Schlagworte:
Closed loops
Object recognition
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Schreier, Tim
Renz, Katrin
Geiger, Andreas
Kashyap Chitta
description Prior work in 3D object detection evaluates models using offline metrics like average precision since closed-loop online evaluation on the downstream driving task is costly. However, it is unclear how indicative offline results are of driving performance. In this work, we perform the first empirical evaluation measuring how predictive different detection metrics are of driving performance when detectors are integrated into a full self-driving stack. We conduct extensive experiments on urban driving in the CARLA simulator using 16 object detection models. We find that the nuScenes Detection Score has a higher correlation to driving performance than the widely used average precision metric. In addition, our results call for caution on the exclusive reliance on the emerging class of `planner-centric' metrics.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2857163850</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2857163850</sourcerecordid><originalsourceid>FETCH-proquest_journals_28571638503</originalsourceid><addsrcrecordid>eNqNiksKwjAUAIMgWLR3eOC6kCamzVaairtu3JdaEkmpeZpPz28FD-BqYGY2JGOcl4U8MbYjeQgTpZRVNROCZ6TpHHTGzNZpaJdhTkO06AANcAXdfdJjBKXjiq826OGcIjp8YgqgvF2sexzI1gxz0PmPe3K8tLfmWrw8vpMOsZ8webemnklRlxWXgvL_rg-IIjlw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2857163850</pqid></control><display><type>article</type><title>On Offline Evaluation of 3D Object Detection for Autonomous Driving</title><source>Free E- Journals</source><creator>Schreier, Tim ; Renz, Katrin ; Geiger, Andreas ; Kashyap Chitta</creator><creatorcontrib>Schreier, Tim ; Renz, Katrin ; Geiger, Andreas ; Kashyap Chitta</creatorcontrib><description>Prior work in 3D object detection evaluates models using offline metrics like average precision since closed-loop online evaluation on the downstream driving task is costly. However, it is unclear how indicative offline results are of driving performance. In this work, we perform the first empirical evaluation measuring how predictive different detection metrics are of driving performance when detectors are integrated into a full self-driving stack. We conduct extensive experiments on urban driving in the CARLA simulator using 16 object detection models. We find that the nuScenes Detection Score has a higher correlation to driving performance than the widely used average precision metric. In addition, our results call for caution on the exclusive reliance on the emerging class of `planner-centric' metrics.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Closed loops ; Object recognition</subject><ispartof>arXiv.org, 2023-08</ispartof><rights>2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>780,784</link.rule.ids></links><search><creatorcontrib>Schreier, Tim</creatorcontrib><creatorcontrib>Renz, Katrin</creatorcontrib><creatorcontrib>Geiger, Andreas</creatorcontrib><creatorcontrib>Kashyap Chitta</creatorcontrib><title>On Offline Evaluation of 3D Object Detection for Autonomous Driving</title><title>arXiv.org</title><description>Prior work in 3D object detection evaluates models using offline metrics like average precision since closed-loop online evaluation on the downstream driving task is costly. However, it is unclear how indicative offline results are of driving performance. In this work, we perform the first empirical evaluation measuring how predictive different detection metrics are of driving performance when detectors are integrated into a full self-driving stack. We conduct extensive experiments on urban driving in the CARLA simulator using 16 object detection models. We find that the nuScenes Detection Score has a higher correlation to driving performance than the widely used average precision metric. In addition, our results call for caution on the exclusive reliance on the emerging class of `planner-centric' metrics.</description><subject>Closed loops</subject><subject>Object recognition</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNiksKwjAUAIMgWLR3eOC6kCamzVaairtu3JdaEkmpeZpPz28FD-BqYGY2JGOcl4U8MbYjeQgTpZRVNROCZ6TpHHTGzNZpaJdhTkO06AANcAXdfdJjBKXjiq826OGcIjp8YgqgvF2sexzI1gxz0PmPe3K8tLfmWrw8vpMOsZ8webemnklRlxWXgvL_rg-IIjlw</recordid><startdate>20230824</startdate><enddate>20230824</enddate><creator>Schreier, Tim</creator><creator>Renz, Katrin</creator><creator>Geiger, Andreas</creator><creator>Kashyap Chitta</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PTHSS</scope></search><sort><creationdate>20230824</creationdate><title>On Offline Evaluation of 3D Object Detection for Autonomous Driving</title><author>Schreier, Tim ; Renz, Katrin ; Geiger, Andreas ; Kashyap Chitta</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28571638503</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Closed loops</topic><topic>Object recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Schreier, Tim</creatorcontrib><creatorcontrib>Renz, Katrin</creatorcontrib><creatorcontrib>Geiger, Andreas</creatorcontrib><creatorcontrib>Kashyap Chitta</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Schreier, Tim</au><au>Renz, Katrin</au><au>Geiger, Andreas</au><au>Kashyap Chitta</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>On Offline Evaluation of 3D Object Detection for Autonomous Driving</atitle><jtitle>arXiv.org</jtitle><date>2023-08-24</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Prior work in 3D object detection evaluates models using offline metrics like average precision since closed-loop online evaluation on the downstream driving task is costly. However, it is unclear how indicative offline results are of driving performance. In this work, we perform the first empirical evaluation measuring how predictive different detection metrics are of driving performance when detectors are integrated into a full self-driving stack. We conduct extensive experiments on urban driving in the CARLA simulator using 16 object detection models. We find that the nuScenes Detection Score has a higher correlation to driving performance than the widely used average precision metric. In addition, our results call for caution on the exclusive reliance on the emerging class of `planner-centric' metrics.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-08
issn 2331-8422
language eng
recordid cdi_proquest_journals_2857163850
source Free E- Journals
subjects Closed loops
Object recognition
title On Offline Evaluation of 3D Object Detection for Autonomous Driving
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-18T20%3A04%3A14IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=On%20Offline%20Evaluation%20of%203D%20Object%20Detection%20for%20Autonomous%20Driving&rft.jtitle=arXiv.org&rft.au=Schreier,%20Tim&rft.date=2023-08-24&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2857163850%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2857163850&rft_id=info:pmid/&rfr_iscdi=true