Accelerator and acceleration device for task tracking in VSLAM system
The invention provides an accelerator and an acceleration device for task tracking in a VSLAM system, and solves the problems that an existing accelerator for task tracking in the VSLAM system is low in low-resolution image support degree and large in high-resolution image calculation load. Original...
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 | MO ZHAOCHENG LIU BOSHENG RUAN JIANHONG MEI CHENGLONG |
| description | The invention provides an accelerator and an acceleration device for task tracking in a VSLAM system, and solves the problems that an existing accelerator for task tracking in the VSLAM system is low in low-resolution image support degree and large in high-resolution image calculation load. Original image data is zoomed according to a specific ratio by utilizing a FPNfeature pyramid module, and strong semantic information and the strong spatial information of the original picture data correspond to the accuracy of the original picture data after zooming, so that the support degree of the accelerator for the low-resolution image data is improved, the storage overhead of the original picture data after zooming is reduced. In the subsequent feature point detection module and the feature point extraction module, the calculation processing amount of the picture data is reduced, and the calculation load is reduced.
本发明提出一种用于VSLAM系统中任务跟踪的加速器及加速装置，解决了现有用于VSLAM系统中任务跟踪的加速器对低分辨率图像支持度低、高分辨率图像计算负荷大的问题，本申请利用FPN特征金字塔模块按特定比例 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN113052750A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN113052750A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN113052750A3</originalsourceid><addsrcrecordid>eNrjZHB1TE5OzUktSizJL1JIzEtRSITxM_PzFFJSyzKTUxXSgHIlicXZCiVFicnZmXnpCpl5CmHBPo6-CsWVxSWpuTwMrGmJOcWpvFCam0HRzTXE2UM3tSA_PrW4IDE5NS-1JN7Zz9DQ2MDUyNzUwNGYGDUArg4yeg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Accelerator and acceleration device for task tracking in VSLAM system</title><source>esp@cenet</source><creator>MO ZHAOCHENG ; LIU BOSHENG ; RUAN JIANHONG ; MEI CHENGLONG</creator><creatorcontrib>MO ZHAOCHENG ; LIU BOSHENG ; RUAN JIANHONG ; MEI CHENGLONG</creatorcontrib><description>The invention provides an accelerator and an acceleration device for task tracking in a VSLAM system, and solves the problems that an existing accelerator for task tracking in the VSLAM system is low in low-resolution image support degree and large in high-resolution image calculation load. Original image data is zoomed according to a specific ratio by utilizing a FPNfeature pyramid module, and strong semantic information and the strong spatial information of the original picture data correspond to the accuracy of the original picture data after zooming, so that the support degree of the accelerator for the low-resolution image data is improved, the storage overhead of the original picture data after zooming is reduced. In the subsequent feature point detection module and the feature point extraction module, the calculation processing amount of the picture data is reduced, and the calculation load is reduced.
本发明提出一种用于VSLAM系统中任务跟踪的加速器及加速装置，解决了现有用于VSLAM系统中任务跟踪的加速器对低分辨率图像支持度低、高分辨率图像计算负荷大的问题，本申请利用FPN特征金字塔模块按特定比例</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2021</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=20210629&DB=EPODOC&CC=CN&NR=113052750A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210629&DB=EPODOC&CC=CN&NR=113052750A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>MO ZHAOCHENG</creatorcontrib><creatorcontrib>LIU BOSHENG</creatorcontrib><creatorcontrib>RUAN JIANHONG</creatorcontrib><creatorcontrib>MEI CHENGLONG</creatorcontrib><title>Accelerator and acceleration device for task tracking in VSLAM system</title><description>The invention provides an accelerator and an acceleration device for task tracking in a VSLAM system, and solves the problems that an existing accelerator for task tracking in the VSLAM system is low in low-resolution image support degree and large in high-resolution image calculation load. Original image data is zoomed according to a specific ratio by utilizing a FPNfeature pyramid module, and strong semantic information and the strong spatial information of the original picture data correspond to the accuracy of the original picture data after zooming, so that the support degree of the accelerator for the low-resolution image data is improved, the storage overhead of the original picture data after zooming is reduced. In the subsequent feature point detection module and the feature point extraction module, the calculation processing amount of the picture data is reduced, and the calculation load is reduced.
本发明提出一种用于VSLAM系统中任务跟踪的加速器及加速装置，解决了现有用于VSLAM系统中任务跟踪的加速器对低分辨率图像支持度低、高分辨率图像计算负荷大的问题，本申请利用FPN特征金字塔模块按特定比例</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHB1TE5OzUktSizJL1JIzEtRSITxM_PzFFJSyzKTUxXSgHIlicXZCiVFicnZmXnpCpl5CmHBPo6-CsWVxSWpuTwMrGmJOcWpvFCam0HRzTXE2UM3tSA_PrW4IDE5NS-1JN7Zz9DQ2MDUyNzUwNGYGDUArg4yeg</recordid><startdate>20210629</startdate><enddate>20210629</enddate><creator>MO ZHAOCHENG</creator><creator>LIU BOSHENG</creator><creator>RUAN JIANHONG</creator><creator>MEI CHENGLONG</creator><scope>EVB</scope></search><sort><creationdate>20210629</creationdate><title>Accelerator and acceleration device for task tracking in VSLAM system</title><author>MO ZHAOCHENG ; LIU BOSHENG ; RUAN JIANHONG ; MEI CHENGLONG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN113052750A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>MO ZHAOCHENG</creatorcontrib><creatorcontrib>LIU BOSHENG</creatorcontrib><creatorcontrib>RUAN JIANHONG</creatorcontrib><creatorcontrib>MEI CHENGLONG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>MO ZHAOCHENG</au><au>LIU BOSHENG</au><au>RUAN JIANHONG</au><au>MEI CHENGLONG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Accelerator and acceleration device for task tracking in VSLAM system</title><date>2021-06-29</date><risdate>2021</risdate><abstract>The invention provides an accelerator and an acceleration device for task tracking in a VSLAM system, and solves the problems that an existing accelerator for task tracking in the VSLAM system is low in low-resolution image support degree and large in high-resolution image calculation load. Original image data is zoomed according to a specific ratio by utilizing a FPNfeature pyramid module, and strong semantic information and the strong spatial information of the original picture data correspond to the accuracy of the original picture data after zooming, so that the support degree of the accelerator for the low-resolution image data is improved, the storage overhead of the original picture data after zooming is reduced. In the subsequent feature point detection module and the feature point extraction module, the calculation processing amount of the picture data is reduced, and the calculation load is reduced.
本发明提出一种用于VSLAM系统中任务跟踪的加速器及加速装置，解决了现有用于VSLAM系统中任务跟踪的加速器对低分辨率图像支持度低、高分辨率图像计算负荷大的问题，本申请利用FPN特征金字塔模块按特定比例</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN113052750A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Accelerator and acceleration device for task tracking in VSLAM system |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T08%3A25%3A32IST&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=MO%20ZHAOCHENG&rft.date=2021-06-29&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN113052750A%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 |