VIEWPOINT-ADAPTIVE PERCEPTION FOR AUTONOMOUS MACHINES AND APPLICATIONS USING SIMULATED SENSOR DATA
Systems and methods are disclosed relating to viewpoint adapted perception for autonomous machines and applications. A 3D perception network may be adapted to handle unavailable target rig data by training the one or more layers of the 3D perception network as part of a training network using simula...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Patent |
| 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 | SEO, Ahyun Choe, Tae Eun Park, Minwoo Joo, Jung Seock |
| description | Systems and methods are disclosed relating to viewpoint adapted perception for autonomous machines and applications. A 3D perception network may be adapted to handle unavailable target rig data by training the one or more layers of the 3D perception network as part of a training network using simulated source and target rig data. A consistency loss that compares (e.g., top-down) transformed feature maps extracted from simulated source and target rig data may be used to minimize differences across training channels. As such, one or more of the paths through the training network(s) may be designated as the 3D perception network, and target rig data may be applied to the 3D perception network to perform one or more perception tasks. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2024320923A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2024320923A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2024320923A13</originalsourceid><addsrcrecordid>eNqNi7EKwjAQQLs4iPoPB86Fmro4HsnVHrRJ6CV1LFXiJFqo_48V_ACn94b31tm1Z7p4xzbkaNAH7gk8dZoWdRYq1wHG4KxrXRRoUddsSQCtAfS-YY3fTiAK2zMIt7HBQAaErCyvwYDbbHUfH3Pa_bjJ9hUFXedpeg1pnsZbeqb3EEUV6liq4qRKPJT_VR8TcDVx</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>VIEWPOINT-ADAPTIVE PERCEPTION FOR AUTONOMOUS MACHINES AND APPLICATIONS USING SIMULATED SENSOR DATA</title><source>esp@cenet</source><creator>SEO, Ahyun ; Choe, Tae Eun ; Park, Minwoo ; Joo, Jung Seock</creator><creatorcontrib>SEO, Ahyun ; Choe, Tae Eun ; Park, Minwoo ; Joo, Jung Seock</creatorcontrib><description>Systems and methods are disclosed relating to viewpoint adapted perception for autonomous machines and applications. A 3D perception network may be adapted to handle unavailable target rig data by training the one or more layers of the 3D perception network as part of a training network using simulated source and target rig data. A consistency loss that compares (e.g., top-down) transformed feature maps extracted from simulated source and target rig data may be used to minimize differences across training channels. As such, one or more of the paths through the training network(s) may be designated as the 3D perception network, and target rig data may be applied to the 3D perception network to perform one or more perception tasks.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC COMMUNICATION TECHNIQUE ; ELECTRICITY ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS ; PICTORIAL COMMUNICATION, e.g. TELEVISION</subject><creationdate>2024</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240926&DB=EPODOC&CC=US&NR=2024320923A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76294</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240926&DB=EPODOC&CC=US&NR=2024320923A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SEO, Ahyun</creatorcontrib><creatorcontrib>Choe, Tae Eun</creatorcontrib><creatorcontrib>Park, Minwoo</creatorcontrib><creatorcontrib>Joo, Jung Seock</creatorcontrib><title>VIEWPOINT-ADAPTIVE PERCEPTION FOR AUTONOMOUS MACHINES AND APPLICATIONS USING SIMULATED SENSOR DATA</title><description>Systems and methods are disclosed relating to viewpoint adapted perception for autonomous machines and applications. A 3D perception network may be adapted to handle unavailable target rig data by training the one or more layers of the 3D perception network as part of a training network using simulated source and target rig data. A consistency loss that compares (e.g., top-down) transformed feature maps extracted from simulated source and target rig data may be used to minimize differences across training channels. As such, one or more of the paths through the training network(s) may be designated as the 3D perception network, and target rig data may be applied to the 3D perception network to perform one or more perception tasks.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC COMMUNICATION TECHNIQUE</subject><subject>ELECTRICITY</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><subject>PICTORIAL COMMUNICATION, e.g. TELEVISION</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNi7EKwjAQQLs4iPoPB86Fmro4HsnVHrRJ6CV1LFXiJFqo_48V_ACn94b31tm1Z7p4xzbkaNAH7gk8dZoWdRYq1wHG4KxrXRRoUddsSQCtAfS-YY3fTiAK2zMIt7HBQAaErCyvwYDbbHUfH3Pa_bjJ9hUFXedpeg1pnsZbeqb3EEUV6liq4qRKPJT_VR8TcDVx</recordid><startdate>20240926</startdate><enddate>20240926</enddate><creator>SEO, Ahyun</creator><creator>Choe, Tae Eun</creator><creator>Park, Minwoo</creator><creator>Joo, Jung Seock</creator><scope>EVB</scope></search><sort><creationdate>20240926</creationdate><title>VIEWPOINT-ADAPTIVE PERCEPTION FOR AUTONOMOUS MACHINES AND APPLICATIONS USING SIMULATED SENSOR DATA</title><author>SEO, Ahyun ; Choe, Tae Eun ; Park, Minwoo ; Joo, Jung Seock</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2024320923A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC COMMUNICATION TECHNIQUE</topic><topic>ELECTRICITY</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><topic>PICTORIAL COMMUNICATION, e.g. TELEVISION</topic><toplevel>online_resources</toplevel><creatorcontrib>SEO, Ahyun</creatorcontrib><creatorcontrib>Choe, Tae Eun</creatorcontrib><creatorcontrib>Park, Minwoo</creatorcontrib><creatorcontrib>Joo, Jung Seock</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SEO, Ahyun</au><au>Choe, Tae Eun</au><au>Park, Minwoo</au><au>Joo, Jung Seock</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>VIEWPOINT-ADAPTIVE PERCEPTION FOR AUTONOMOUS MACHINES AND APPLICATIONS USING SIMULATED SENSOR DATA</title><date>2024-09-26</date><risdate>2024</risdate><abstract>Systems and methods are disclosed relating to viewpoint adapted perception for autonomous machines and applications. A 3D perception network may be adapted to handle unavailable target rig data by training the one or more layers of the 3D perception network as part of a training network using simulated source and target rig data. A consistency loss that compares (e.g., top-down) transformed feature maps extracted from simulated source and target rig data may be used to minimize differences across training channels. As such, one or more of the paths through the training network(s) may be designated as the 3D perception network, and target rig data may be applied to the 3D perception network to perform one or more perception tasks.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2024320923A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING ELECTRIC COMMUNICATION TECHNIQUE ELECTRICITY IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS PICTORIAL COMMUNICATION, e.g. TELEVISION |
| title | VIEWPOINT-ADAPTIVE PERCEPTION FOR AUTONOMOUS MACHINES AND APPLICATIONS USING SIMULATED SENSOR DATA |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T04%3A00%3A52IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=SEO,%20Ahyun&rft.date=2024-09-26&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2024320923A1%3C/epo_EVB%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 |