System and method for self-supervised depth and ego-motion overfitting
Systems and methods to improve machine learning by explicitly over-fitting environmental data obtained by an imaging system, such as a monocular camera are disclosed. The system includes training self-supervised depth and pose networks in monocular visual data collected from a certain area over mult...
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 | Pillai, Sudeep Guizilini, Vitor Ambrus, Rares A Gaidon, Adrien David |
| description | Systems and methods to improve machine learning by explicitly over-fitting environmental data obtained by an imaging system, such as a monocular camera are disclosed. The system includes training self-supervised depth and pose networks in monocular visual data collected from a certain area over multiple passes. Pose and depth networks may be trained by extracting data from multiple images of a single environment or trajectory, allowing the system to overfit the image data. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US11915487B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US11915487B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US11915487B23</originalsourceid><addsrcrecordid>eNqNyj0KAjEQBtA0FqLeYTxAiviD2iou9qv1EsyX3cAmE5JxwdsL4gGsXvPmqmnfVRDJJkcRMrAjz4UqRq_rK6NMocKRQ5bhm9CzjiyBE_GE4oNISP1SzbwdK1Y_F2rdXO-Xm0bmDjXbJxKke7TGnMx-dzycN9t_zgdEaDQB</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>System and method for self-supervised depth and ego-motion overfitting</title><source>esp@cenet</source><creator>Pillai, Sudeep ; Guizilini, Vitor ; Ambrus, Rares A ; Gaidon, Adrien David</creator><creatorcontrib>Pillai, Sudeep ; Guizilini, Vitor ; Ambrus, Rares A ; Gaidon, Adrien David</creatorcontrib><description>Systems and methods to improve machine learning by explicitly over-fitting environmental data obtained by an imaging system, such as a monocular camera are disclosed. The system includes training self-supervised depth and pose networks in monocular visual data collected from a certain area over multiple passes. Pose and depth networks may be trained by extracting data from multiple images of a single environment or trajectory, allowing the system to overfit the image data.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</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=20240227&DB=EPODOC&CC=US&NR=11915487B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76294</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240227&DB=EPODOC&CC=US&NR=11915487B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Pillai, Sudeep</creatorcontrib><creatorcontrib>Guizilini, Vitor</creatorcontrib><creatorcontrib>Ambrus, Rares A</creatorcontrib><creatorcontrib>Gaidon, Adrien David</creatorcontrib><title>System and method for self-supervised depth and ego-motion overfitting</title><description>Systems and methods to improve machine learning by explicitly over-fitting environmental data obtained by an imaging system, such as a monocular camera are disclosed. The system includes training self-supervised depth and pose networks in monocular visual data collected from a certain area over multiple passes. Pose and depth networks may be trained by extracting data from multiple images of a single environment or trajectory, allowing the system to overfit the image data.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyj0KAjEQBtA0FqLeYTxAiviD2iou9qv1EsyX3cAmE5JxwdsL4gGsXvPmqmnfVRDJJkcRMrAjz4UqRq_rK6NMocKRQ5bhm9CzjiyBE_GE4oNISP1SzbwdK1Y_F2rdXO-Xm0bmDjXbJxKke7TGnMx-dzycN9t_zgdEaDQB</recordid><startdate>20240227</startdate><enddate>20240227</enddate><creator>Pillai, Sudeep</creator><creator>Guizilini, Vitor</creator><creator>Ambrus, Rares A</creator><creator>Gaidon, Adrien David</creator><scope>EVB</scope></search><sort><creationdate>20240227</creationdate><title>System and method for self-supervised depth and ego-motion overfitting</title><author>Pillai, Sudeep ; Guizilini, Vitor ; Ambrus, Rares A ; Gaidon, Adrien David</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US11915487B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Pillai, Sudeep</creatorcontrib><creatorcontrib>Guizilini, Vitor</creatorcontrib><creatorcontrib>Ambrus, Rares A</creatorcontrib><creatorcontrib>Gaidon, Adrien David</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Pillai, Sudeep</au><au>Guizilini, Vitor</au><au>Ambrus, Rares A</au><au>Gaidon, Adrien David</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>System and method for self-supervised depth and ego-motion overfitting</title><date>2024-02-27</date><risdate>2024</risdate><abstract>Systems and methods to improve machine learning by explicitly over-fitting environmental data obtained by an imaging system, such as a monocular camera are disclosed. The system includes training self-supervised depth and pose networks in monocular visual data collected from a certain area over multiple passes. Pose and depth networks may be trained by extracting data from multiple images of a single environment or trajectory, allowing the system to overfit the image data.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US11915487B2 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | System and method for self-supervised depth and ego-motion overfitting |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T12%3A57%3A57IST&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=Pillai,%20Sudeep&rft.date=2024-02-27&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS11915487B2%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 |