Intelligent vehicle 3D target detection method suitable for uneven road scene
The invention discloses an intelligent vehicle 3D target detection method suitable for an uneven road scene, and the method comprises the steps: obtaining front-view image data and vehicle acceleration information at the same time through a vehicle-mounted camera sensor and a vehicle-mounted MEMS se...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; 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 | JIANG HENGTAO ZHAO WANZHONG WANG CHUNYAN WANG YUANLONG CHEN GUANYING |
| description | The invention discloses an intelligent vehicle 3D target detection method suitable for an uneven road scene, and the method comprises the steps: obtaining front-view image data and vehicle acceleration information at the same time through a vehicle-mounted camera sensor and a vehicle-mounted MEMS sensor, carrying out the feature extraction of the obtained front-view image data, and obtaining an image feature map F; meanwhile, the real-time roll angle and the pitch angle of the vehicle are calculated through obtained vehicle acceleration information, then a rotation matrix A is calculated based on the roll angle and the pitch angle, a transformation matrix M is obtained through combination of the rotation matrix and internal and external parameter matrixes of the camera, pixel coordinate transformation is conducted on the image feature map F through the transformation matrix M, and the image feature map F is obtained. And performing projection from the 2D features to the 3D features based on the feature map F |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116665166A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116665166A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116665166A3</originalsourceid><addsrcrecordid>eNqNyrEOgjAUheEuDkZ9h8sDOBBidwMSHXRyJ7UcoEm9Je2F57cmPoDL-YfzbdX9xgLv3QgWWjE560FVQ2LiCKEeAisuML0hU-gpLU7MK5shRFoYK5hiMPmwYOzVZjA-4fDrThXt5Vlfj5hDhzSbL5KufpSl1vqU51z9Yz7BpzYC</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Intelligent vehicle 3D target detection method suitable for uneven road scene</title><source>esp@cenet</source><creator>JIANG HENGTAO ; ZHAO WANZHONG ; WANG CHUNYAN ; WANG YUANLONG ; CHEN GUANYING</creator><creatorcontrib>JIANG HENGTAO ; ZHAO WANZHONG ; WANG CHUNYAN ; WANG YUANLONG ; CHEN GUANYING</creatorcontrib><description>The invention discloses an intelligent vehicle 3D target detection method suitable for an uneven road scene, and the method comprises the steps: obtaining front-view image data and vehicle acceleration information at the same time through a vehicle-mounted camera sensor and a vehicle-mounted MEMS sensor, carrying out the feature extraction of the obtained front-view image data, and obtaining an image feature map F; meanwhile, the real-time roll angle and the pitch angle of the vehicle are calculated through obtained vehicle acceleration information, then a rotation matrix A is calculated based on the roll angle and the pitch angle, a transformation matrix M is obtained through combination of the rotation matrix and internal and external parameter matrixes of the camera, pixel coordinate transformation is conducted on the image feature map F through the transformation matrix M, and the image feature map F is obtained. And performing projection from the 2D features to the 3D features based on the feature map F</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2023</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=20230829&DB=EPODOC&CC=CN&NR=116665166A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230829&DB=EPODOC&CC=CN&NR=116665166A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>JIANG HENGTAO</creatorcontrib><creatorcontrib>ZHAO WANZHONG</creatorcontrib><creatorcontrib>WANG CHUNYAN</creatorcontrib><creatorcontrib>WANG YUANLONG</creatorcontrib><creatorcontrib>CHEN GUANYING</creatorcontrib><title>Intelligent vehicle 3D target detection method suitable for uneven road scene</title><description>The invention discloses an intelligent vehicle 3D target detection method suitable for an uneven road scene, and the method comprises the steps: obtaining front-view image data and vehicle acceleration information at the same time through a vehicle-mounted camera sensor and a vehicle-mounted MEMS sensor, carrying out the feature extraction of the obtained front-view image data, and obtaining an image feature map F; meanwhile, the real-time roll angle and the pitch angle of the vehicle are calculated through obtained vehicle acceleration information, then a rotation matrix A is calculated based on the roll angle and the pitch angle, a transformation matrix M is obtained through combination of the rotation matrix and internal and external parameter matrixes of the camera, pixel coordinate transformation is conducted on the image feature map F through the transformation matrix M, and the image feature map F is obtained. And performing projection from the 2D features to the 3D features based on the feature map F</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyrEOgjAUheEuDkZ9h8sDOBBidwMSHXRyJ7UcoEm9Je2F57cmPoDL-YfzbdX9xgLv3QgWWjE560FVQ2LiCKEeAisuML0hU-gpLU7MK5shRFoYK5hiMPmwYOzVZjA-4fDrThXt5Vlfj5hDhzSbL5KufpSl1vqU51z9Yz7BpzYC</recordid><startdate>20230829</startdate><enddate>20230829</enddate><creator>JIANG HENGTAO</creator><creator>ZHAO WANZHONG</creator><creator>WANG CHUNYAN</creator><creator>WANG YUANLONG</creator><creator>CHEN GUANYING</creator><scope>EVB</scope></search><sort><creationdate>20230829</creationdate><title>Intelligent vehicle 3D target detection method suitable for uneven road scene</title><author>JIANG HENGTAO ; ZHAO WANZHONG ; WANG CHUNYAN ; WANG YUANLONG ; CHEN GUANYING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116665166A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>JIANG HENGTAO</creatorcontrib><creatorcontrib>ZHAO WANZHONG</creatorcontrib><creatorcontrib>WANG CHUNYAN</creatorcontrib><creatorcontrib>WANG YUANLONG</creatorcontrib><creatorcontrib>CHEN GUANYING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>JIANG HENGTAO</au><au>ZHAO WANZHONG</au><au>WANG CHUNYAN</au><au>WANG YUANLONG</au><au>CHEN GUANYING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Intelligent vehicle 3D target detection method suitable for uneven road scene</title><date>2023-08-29</date><risdate>2023</risdate><abstract>The invention discloses an intelligent vehicle 3D target detection method suitable for an uneven road scene, and the method comprises the steps: obtaining front-view image data and vehicle acceleration information at the same time through a vehicle-mounted camera sensor and a vehicle-mounted MEMS sensor, carrying out the feature extraction of the obtained front-view image data, and obtaining an image feature map F; meanwhile, the real-time roll angle and the pitch angle of the vehicle are calculated through obtained vehicle acceleration information, then a rotation matrix A is calculated based on the roll angle and the pitch angle, a transformation matrix M is obtained through combination of the rotation matrix and internal and external parameter matrixes of the camera, pixel coordinate transformation is conducted on the image feature map F through the transformation matrix M, and the image feature map F is obtained. And performing projection from the 2D features to the 3D features based on the feature map F</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN116665166A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING PHYSICS |
| title | Intelligent vehicle 3D target detection method suitable for uneven road scene |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-11T21%3A40%3A29IST&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=JIANG%20HENGTAO&rft.date=2023-08-29&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116665166A%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 |