ParisLuco3D: A High-Quality Target Dataset for Domain Generalization of LiDAR Perception
LiDAR is an essential sensor for autonomous driving by collecting precise geometric information regarding a scene. As the performance of various LiDAR perception tasks has improved, generalizations to new environments and sensors has emerged to test these optimized models in real-world conditions. U...
Gespeichert in:
| Veröffentlicht in: | IEEE robotics and automation letters 2024-06, Vol.9 (6), p.5496-5503 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 5503 |
|---|---|
| container_issue | 6 |
| container_start_page | 5496 |
| container_title | IEEE robotics and automation letters |
| container_volume | 9 |
| creator | Sanchez, Jules Soum-Fontez, Louis Deschaud, Jean-Emmanuel Goulette, Francois |
| description | LiDAR is an essential sensor for autonomous driving by collecting precise geometric information regarding a scene. As the performance of various LiDAR perception tasks has improved, generalizations to new environments and sensors has emerged to test these optimized models in real-world conditions. Unfortunately, the various annotation strategies of data providers complicate the computation of cross-domain performances. This paper provides a novel dataset, ParisLuco3D, specifically designed for cross-domain evaluation to make it easier to evaluate the performance utilizing various source datasets. Alongside the dataset, online benchmarks for LiDAR semantic segmentation, LiDAR object detection, and LiDAR tracking are provided to ensure a fair comparison across methods. |
| doi_str_mv | 10.1109/LRA.2024.3393209 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_10508037</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10508037</ieee_id><sourcerecordid>3050305205</sourcerecordid><originalsourceid>FETCH-LOGICAL-c245t-8e610841690132d70c85eeabff285a6793f22bdbae91d5b2e9474232cab308283</originalsourceid><addsrcrecordid>eNpNkMFLwzAUh4MoOHR3Dx4CnjtfkqZpvJVNN6HgHBO8hbR7nRlbM9P2MP96O7bDDo_f4_G99-Aj5IHBiDHQz_kiG3Hg8UgILTjoKzLgQqlIqCS5vuhvybBpNgDAJFdCywH5ntvgmrwrvZi80IzO3Pon-uzs1rUHurRhjS2d2NY2fVY-0InfWVfTKdYYeujPts7X1Fc0d5NsQecYStwfZ_fkprLbBofnvCNfb6_L8SzKP6bv4yyPSh7LNkoxYZDGLNHABF8pKFOJaIuq4qm0idKi4rxYFRY1W8mCo45VzAUvbSEg5am4I0-nu_vgfztsWrPxXaj7l0aAhL44yJ6CE1UG3zQBK7MPbmfDwTAwR4WmV2iOCs1ZYb_yeFpxiHiBS0hBKPEPuv9qrg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3050305205</pqid></control><display><type>article</type><title>ParisLuco3D: A High-Quality Target Dataset for Domain Generalization of LiDAR Perception</title><source>IEEE Electronic Library (IEL)</source><creator>Sanchez, Jules ; Soum-Fontez, Louis ; Deschaud, Jean-Emmanuel ; Goulette, Francois</creator><creatorcontrib>Sanchez, Jules ; Soum-Fontez, Louis ; Deschaud, Jean-Emmanuel ; Goulette, Francois</creatorcontrib><description>LiDAR is an essential sensor for autonomous driving by collecting precise geometric information regarding a scene. As the performance of various LiDAR perception tasks has improved, generalizations to new environments and sensors has emerged to test these optimized models in real-world conditions. Unfortunately, the various annotation strategies of data providers complicate the computation of cross-domain performances. This paper provides a novel dataset, ParisLuco3D, specifically designed for cross-domain evaluation to make it easier to evaluate the performance utilizing various source datasets. Alongside the dataset, online benchmarks for LiDAR semantic segmentation, LiDAR object detection, and LiDAR tracking are provided to ensure a fair comparison across methods.</description><identifier>ISSN: 2377-3766</identifier><identifier>EISSN: 2377-3766</identifier><identifier>DOI: 10.1109/LRA.2024.3393209</identifier><identifier>CODEN: IRALC6</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Annotations ; Data sets for robotic vision ; Datasets ; intelligent transportation systems ; Laser radar ; Lidar ; Object detection ; Object recognition ; Perception ; Performance evaluation ; Point cloud compression ; Robot sensing systems ; segmentation and categorization ; Semantic segmentation ; Task analysis</subject><ispartof>IEEE robotics and automation letters, 2024-06, Vol.9 (6), p.5496-5503</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c245t-8e610841690132d70c85eeabff285a6793f22bdbae91d5b2e9474232cab308283</cites><orcidid>0009-0003-9789-1558 ; 0000-0002-6696-9354 ; 0000-0003-1527-2650 ; 0000-0002-8104-0930</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10508037$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>315,781,785,797,27929,27930,54763</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10508037$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Sanchez, Jules</creatorcontrib><creatorcontrib>Soum-Fontez, Louis</creatorcontrib><creatorcontrib>Deschaud, Jean-Emmanuel</creatorcontrib><creatorcontrib>Goulette, Francois</creatorcontrib><title>ParisLuco3D: A High-Quality Target Dataset for Domain Generalization of LiDAR Perception</title><title>IEEE robotics and automation letters</title><addtitle>LRA</addtitle><description>LiDAR is an essential sensor for autonomous driving by collecting precise geometric information regarding a scene. As the performance of various LiDAR perception tasks has improved, generalizations to new environments and sensors has emerged to test these optimized models in real-world conditions. Unfortunately, the various annotation strategies of data providers complicate the computation of cross-domain performances. This paper provides a novel dataset, ParisLuco3D, specifically designed for cross-domain evaluation to make it easier to evaluate the performance utilizing various source datasets. Alongside the dataset, online benchmarks for LiDAR semantic segmentation, LiDAR object detection, and LiDAR tracking are provided to ensure a fair comparison across methods.</description><subject>Annotations</subject><subject>Data sets for robotic vision</subject><subject>Datasets</subject><subject>intelligent transportation systems</subject><subject>Laser radar</subject><subject>Lidar</subject><subject>Object detection</subject><subject>Object recognition</subject><subject>Perception</subject><subject>Performance evaluation</subject><subject>Point cloud compression</subject><subject>Robot sensing systems</subject><subject>segmentation and categorization</subject><subject>Semantic segmentation</subject><subject>Task analysis</subject><issn>2377-3766</issn><issn>2377-3766</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkMFLwzAUh4MoOHR3Dx4CnjtfkqZpvJVNN6HgHBO8hbR7nRlbM9P2MP96O7bDDo_f4_G99-Aj5IHBiDHQz_kiG3Hg8UgILTjoKzLgQqlIqCS5vuhvybBpNgDAJFdCywH5ntvgmrwrvZi80IzO3Pon-uzs1rUHurRhjS2d2NY2fVY-0InfWVfTKdYYeujPts7X1Fc0d5NsQecYStwfZ_fkprLbBofnvCNfb6_L8SzKP6bv4yyPSh7LNkoxYZDGLNHABF8pKFOJaIuq4qm0idKi4rxYFRY1W8mCo45VzAUvbSEg5am4I0-nu_vgfztsWrPxXaj7l0aAhL44yJ6CE1UG3zQBK7MPbmfDwTAwR4WmV2iOCs1ZYb_yeFpxiHiBS0hBKPEPuv9qrg</recordid><startdate>20240601</startdate><enddate>20240601</enddate><creator>Sanchez, Jules</creator><creator>Soum-Fontez, Louis</creator><creator>Deschaud, Jean-Emmanuel</creator><creator>Goulette, Francois</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0009-0003-9789-1558</orcidid><orcidid>https://orcid.org/0000-0002-6696-9354</orcidid><orcidid>https://orcid.org/0000-0003-1527-2650</orcidid><orcidid>https://orcid.org/0000-0002-8104-0930</orcidid></search><sort><creationdate>20240601</creationdate><title>ParisLuco3D: A High-Quality Target Dataset for Domain Generalization of LiDAR Perception</title><author>Sanchez, Jules ; Soum-Fontez, Louis ; Deschaud, Jean-Emmanuel ; Goulette, Francois</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c245t-8e610841690132d70c85eeabff285a6793f22bdbae91d5b2e9474232cab308283</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Annotations</topic><topic>Data sets for robotic vision</topic><topic>Datasets</topic><topic>intelligent transportation systems</topic><topic>Laser radar</topic><topic>Lidar</topic><topic>Object detection</topic><topic>Object recognition</topic><topic>Perception</topic><topic>Performance evaluation</topic><topic>Point cloud compression</topic><topic>Robot sensing systems</topic><topic>segmentation and categorization</topic><topic>Semantic segmentation</topic><topic>Task analysis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Sanchez, Jules</creatorcontrib><creatorcontrib>Soum-Fontez, Louis</creatorcontrib><creatorcontrib>Deschaud, Jean-Emmanuel</creatorcontrib><creatorcontrib>Goulette, Francois</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE robotics and automation letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Sanchez, Jules</au><au>Soum-Fontez, Louis</au><au>Deschaud, Jean-Emmanuel</au><au>Goulette, Francois</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>ParisLuco3D: A High-Quality Target Dataset for Domain Generalization of LiDAR Perception</atitle><jtitle>IEEE robotics and automation letters</jtitle><stitle>LRA</stitle><date>2024-06-01</date><risdate>2024</risdate><volume>9</volume><issue>6</issue><spage>5496</spage><epage>5503</epage><pages>5496-5503</pages><issn>2377-3766</issn><eissn>2377-3766</eissn><coden>IRALC6</coden><abstract>LiDAR is an essential sensor for autonomous driving by collecting precise geometric information regarding a scene. As the performance of various LiDAR perception tasks has improved, generalizations to new environments and sensors has emerged to test these optimized models in real-world conditions. Unfortunately, the various annotation strategies of data providers complicate the computation of cross-domain performances. This paper provides a novel dataset, ParisLuco3D, specifically designed for cross-domain evaluation to make it easier to evaluate the performance utilizing various source datasets. Alongside the dataset, online benchmarks for LiDAR semantic segmentation, LiDAR object detection, and LiDAR tracking are provided to ensure a fair comparison across methods.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/LRA.2024.3393209</doi><tpages>8</tpages><orcidid>https://orcid.org/0009-0003-9789-1558</orcidid><orcidid>https://orcid.org/0000-0002-6696-9354</orcidid><orcidid>https://orcid.org/0000-0003-1527-2650</orcidid><orcidid>https://orcid.org/0000-0002-8104-0930</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2377-3766 |
| ispartof | IEEE robotics and automation letters, 2024-06, Vol.9 (6), p.5496-5503 |
| issn | 2377-3766 2377-3766 |
| language | eng |
| recordid | cdi_ieee_primary_10508037 |
| source | IEEE Electronic Library (IEL) |
| subjects | Annotations Data sets for robotic vision Datasets intelligent transportation systems Laser radar Lidar Object detection Object recognition Perception Performance evaluation Point cloud compression Robot sensing systems segmentation and categorization Semantic segmentation Task analysis |
| title | ParisLuco3D: A High-Quality Target Dataset for Domain Generalization of LiDAR Perception |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-15T02%3A00%3A00IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=ParisLuco3D:%20A%20High-Quality%20Target%20Dataset%20for%20Domain%20Generalization%20of%20LiDAR%20Perception&rft.jtitle=IEEE%20robotics%20and%20automation%20letters&rft.au=Sanchez,%20Jules&rft.date=2024-06-01&rft.volume=9&rft.issue=6&rft.spage=5496&rft.epage=5503&rft.pages=5496-5503&rft.issn=2377-3766&rft.eissn=2377-3766&rft.coden=IRALC6&rft_id=info:doi/10.1109/LRA.2024.3393209&rft_dat=%3Cproquest_RIE%3E3050305205%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3050305205&rft_id=info:pmid/&rft_ieee_id=10508037&rfr_iscdi=true |