Perception model training method and device and electronic equipment
The invention discloses a perception model training method and device and electronic equipment, and the method comprises the steps: obtaining actual point cloud data continuously collected by a laser radar; performing target modeling according to the actual point cloud data to obtain a target model;...
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 | CHEN JUNBO MIAO ZHENWEI GUAN JUNQUAN ZHU JUN LI XIAOMIN CHEN JIKAI MA ZEYU HAO PEIHAN QING QUAN ZHAN XIN LIU KAIXUAN LYU BAOGUI |
| description | The invention discloses a perception model training method and device and electronic equipment, and the method comprises the steps: obtaining actual point cloud data continuously collected by a laser radar; performing target modeling according to the actual point cloud data to obtain a target model; calibrating and measuring harness information of the laser radar to obtain distribution of laser harnesses; according to reflection laser points, distributed on the target model, of the laser beam, simulation point cloud data are obtained; and obtaining fusion training data according to the actual point cloud data and the simulation point cloud data, and training the perception model by using the fusion training data. According to the scheme, the generation efficiency and diversity of the training data for perceptual model training can be considered, and the training effect of the perceptual model is improved.
感知模型的训练方法、训练装置及电子设备，其中，所述训练方法包括：获取激光雷达连续采集的实际点云数据；根据所述实际点云数据进行目标建模，得到目标模型；标定测量所述激光雷达的线束信息，获得激光线束的分布；根据所述激 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115205610A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115205610A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115205610A3</originalsourceid><addsrcrecordid>eNrjZHAJSC1KTi0oyczPU8jNT0nNUSgpSszMy8xLV8hNLcnIT1FIzEtRSEkty0xOBTNTc1KTS4ry8zKTFVILSzMLclPzSngYWNMSc4pTeaE0N4Oim2uIs4duakF-fGpxQWJyal5qSbyzn6GhqZGBqZmhgaMxMWoAzXEy8g</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Perception model training method and device and electronic equipment</title><source>esp@cenet</source><creator>CHEN JUNBO ; MIAO ZHENWEI ; GUAN JUNQUAN ; ZHU JUN ; LI XIAOMIN ; CHEN JIKAI ; MA ZEYU ; HAO PEIHAN ; QING QUAN ; ZHAN XIN ; LIU KAIXUAN ; LYU BAOGUI</creator><creatorcontrib>CHEN JUNBO ; MIAO ZHENWEI ; GUAN JUNQUAN ; ZHU JUN ; LI XIAOMIN ; CHEN JIKAI ; MA ZEYU ; HAO PEIHAN ; QING QUAN ; ZHAN XIN ; LIU KAIXUAN ; LYU BAOGUI</creatorcontrib><description>The invention discloses a perception model training method and device and electronic equipment, and the method comprises the steps: obtaining actual point cloud data continuously collected by a laser radar; performing target modeling according to the actual point cloud data to obtain a target model; calibrating and measuring harness information of the laser radar to obtain distribution of laser harnesses; according to reflection laser points, distributed on the target model, of the laser beam, simulation point cloud data are obtained; and obtaining fusion training data according to the actual point cloud data and the simulation point cloud data, and training the perception model by using the fusion training data. According to the scheme, the generation efficiency and diversity of the training data for perceptual model training can be considered, and the training effect of the perceptual model is improved.
感知模型的训练方法、训练装置及电子设备，其中，所述训练方法包括：获取激光雷达连续采集的实际点云数据；根据所述实际点云数据进行目标建模，得到目标模型；标定测量所述激光雷达的线束信息，获得激光线束的分布；根据所述激</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2022</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=20221018&DB=EPODOC&CC=CN&NR=115205610A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25562,76317</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20221018&DB=EPODOC&CC=CN&NR=115205610A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CHEN JUNBO</creatorcontrib><creatorcontrib>MIAO ZHENWEI</creatorcontrib><creatorcontrib>GUAN JUNQUAN</creatorcontrib><creatorcontrib>ZHU JUN</creatorcontrib><creatorcontrib>LI XIAOMIN</creatorcontrib><creatorcontrib>CHEN JIKAI</creatorcontrib><creatorcontrib>MA ZEYU</creatorcontrib><creatorcontrib>HAO PEIHAN</creatorcontrib><creatorcontrib>QING QUAN</creatorcontrib><creatorcontrib>ZHAN XIN</creatorcontrib><creatorcontrib>LIU KAIXUAN</creatorcontrib><creatorcontrib>LYU BAOGUI</creatorcontrib><title>Perception model training method and device and electronic equipment</title><description>The invention discloses a perception model training method and device and electronic equipment, and the method comprises the steps: obtaining actual point cloud data continuously collected by a laser radar; performing target modeling according to the actual point cloud data to obtain a target model; calibrating and measuring harness information of the laser radar to obtain distribution of laser harnesses; according to reflection laser points, distributed on the target model, of the laser beam, simulation point cloud data are obtained; and obtaining fusion training data according to the actual point cloud data and the simulation point cloud data, and training the perception model by using the fusion training data. According to the scheme, the generation efficiency and diversity of the training data for perceptual model training can be considered, and the training effect of the perceptual model is improved.
感知模型的训练方法、训练装置及电子设备，其中，所述训练方法包括：获取激光雷达连续采集的实际点云数据；根据所述实际点云数据进行目标建模，得到目标模型；标定测量所述激光雷达的线束信息，获得激光线束的分布；根据所述激</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHAJSC1KTi0oyczPU8jNT0nNUSgpSszMy8xLV8hNLcnIT1FIzEtRSEkty0xOBTNTc1KTS4ry8zKTFVILSzMLclPzSngYWNMSc4pTeaE0N4Oim2uIs4duakF-fGpxQWJyal5qSbyzn6GhqZGBqZmhgaMxMWoAzXEy8g</recordid><startdate>20221018</startdate><enddate>20221018</enddate><creator>CHEN JUNBO</creator><creator>MIAO ZHENWEI</creator><creator>GUAN JUNQUAN</creator><creator>ZHU JUN</creator><creator>LI XIAOMIN</creator><creator>CHEN JIKAI</creator><creator>MA ZEYU</creator><creator>HAO PEIHAN</creator><creator>QING QUAN</creator><creator>ZHAN XIN</creator><creator>LIU KAIXUAN</creator><creator>LYU BAOGUI</creator><scope>EVB</scope></search><sort><creationdate>20221018</creationdate><title>Perception model training method and device and electronic equipment</title><author>CHEN JUNBO ; MIAO ZHENWEI ; GUAN JUNQUAN ; ZHU JUN ; LI XIAOMIN ; CHEN JIKAI ; MA ZEYU ; HAO PEIHAN ; QING QUAN ; ZHAN XIN ; LIU KAIXUAN ; LYU BAOGUI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115205610A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>CHEN JUNBO</creatorcontrib><creatorcontrib>MIAO ZHENWEI</creatorcontrib><creatorcontrib>GUAN JUNQUAN</creatorcontrib><creatorcontrib>ZHU JUN</creatorcontrib><creatorcontrib>LI XIAOMIN</creatorcontrib><creatorcontrib>CHEN JIKAI</creatorcontrib><creatorcontrib>MA ZEYU</creatorcontrib><creatorcontrib>HAO PEIHAN</creatorcontrib><creatorcontrib>QING QUAN</creatorcontrib><creatorcontrib>ZHAN XIN</creatorcontrib><creatorcontrib>LIU KAIXUAN</creatorcontrib><creatorcontrib>LYU BAOGUI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CHEN JUNBO</au><au>MIAO ZHENWEI</au><au>GUAN JUNQUAN</au><au>ZHU JUN</au><au>LI XIAOMIN</au><au>CHEN JIKAI</au><au>MA ZEYU</au><au>HAO PEIHAN</au><au>QING QUAN</au><au>ZHAN XIN</au><au>LIU KAIXUAN</au><au>LYU BAOGUI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Perception model training method and device and electronic equipment</title><date>2022-10-18</date><risdate>2022</risdate><abstract>The invention discloses a perception model training method and device and electronic equipment, and the method comprises the steps: obtaining actual point cloud data continuously collected by a laser radar; performing target modeling according to the actual point cloud data to obtain a target model; calibrating and measuring harness information of the laser radar to obtain distribution of laser harnesses; according to reflection laser points, distributed on the target model, of the laser beam, simulation point cloud data are obtained; and obtaining fusion training data according to the actual point cloud data and the simulation point cloud data, and training the perception model by using the fusion training data. According to the scheme, the generation efficiency and diversity of the training data for perceptual model training can be considered, and the training effect of the perceptual model is improved.
感知模型的训练方法、训练装置及电子设备，其中，所述训练方法包括：获取激光雷达连续采集的实际点云数据；根据所述实际点云数据进行目标建模，得到目标模型；标定测量所述激光雷达的线束信息，获得激光线束的分布；根据所述激</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN115205610A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING PHYSICS |
| title | Perception model training method and device and electronic equipment |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T09%3A07%3A36IST&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=CHEN%20JUNBO&rft.date=2022-10-18&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115205610A%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 |