Embedded GPU zero-copy panoramic image splicing method and system based on improved L-ORB algorithm

An embedded GPU zero-copy panoramic image splicing method based on an improved L-ORB algorithm comprises the following steps: step 1, determining an overlapping region of a camera array by using a calibration file, and then extracting and matching feature points of images in the overlapping region b...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHAO ZHIFENG, ZHU SHIQIANG, DU CHENGYAO, SONG XIAOFENG
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 ZHAO ZHIFENG
ZHU SHIQIANG
DU CHENGYAO
SONG XIAOFENG
description An embedded GPU zero-copy panoramic image splicing method based on an improved L-ORB algorithm comprises the following steps: step 1, determining an overlapping region of a camera array by using a calibration file, and then extracting and matching feature points of images in the overlapping region by using the ORB algorithm; 2, performing exposure compensation on the original image based on brightness consistency prior; and step 3, GPU utilization is optimized by using a stream parallel strategy. The invention also comprises an embedded GPU zero-copy panoramic image splicing system based on the improved L-ORB algorithm. According to the method, the efficiency is improved, and GPU resources can be fully utilized. 一种改进L-ORB算法的嵌入式GPU零拷贝全景图像拼接方法,包括:步骤1,使用标定文件确定相机阵列的重叠区域,然后使用ORB算法对重叠区域的图像进行特征点提取和匹配;步骤2,基于亮度一致性先验对原始图像进行曝光补偿;步骤3,使用流并行策略优化GPU利用。本发明还包括一种改进L-ORB算法的嵌入式GPU零拷贝全景图像拼接系统。本发明提升了效率,并且可以充分利用GPU资源。
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116016816A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116016816A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116016816A3</originalsourceid><addsrcrecordid>eNqNi0EKwjAQAHvxIOof1gcUDELwakvVg6iInss2WdtAkw1JEOrrzcEHeJo5zMwL1diOtCYNx9sTPhS4VOwn8Og4oDUKjMWeIPrRKON6sJQG1oBOQ5xiIgsdxryzy6UP_M5-Lq_3CnDsOZg02GUxe-EYafXjolgfmkd9KslzS9GjIkeprS9CyI2QOyH323-aLwLDPVg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Embedded GPU zero-copy panoramic image splicing method and system based on improved L-ORB algorithm</title><source>esp@cenet</source><creator>ZHAO ZHIFENG ; ZHU SHIQIANG ; DU CHENGYAO ; SONG XIAOFENG</creator><creatorcontrib>ZHAO ZHIFENG ; ZHU SHIQIANG ; DU CHENGYAO ; SONG XIAOFENG</creatorcontrib><description>An embedded GPU zero-copy panoramic image splicing method based on an improved L-ORB algorithm comprises the following steps: step 1, determining an overlapping region of a camera array by using a calibration file, and then extracting and matching feature points of images in the overlapping region by using the ORB algorithm; 2, performing exposure compensation on the original image based on brightness consistency prior; and step 3, GPU utilization is optimized by using a stream parallel strategy. The invention also comprises an embedded GPU zero-copy panoramic image splicing system based on the improved L-ORB algorithm. According to the method, the efficiency is improved, and GPU resources can be fully utilized. 一种改进L-ORB算法的嵌入式GPU零拷贝全景图像拼接方法,包括:步骤1,使用标定文件确定相机阵列的重叠区域,然后使用ORB算法对重叠区域的图像进行特征点提取和匹配;步骤2,基于亮度一致性先验对原始图像进行曝光补偿;步骤3,使用流并行策略优化GPU利用。本发明还包括一种改进L-ORB算法的嵌入式GPU零拷贝全景图像拼接系统。本发明提升了效率,并且可以充分利用GPU资源。</description><language>chi ; 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>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&amp;date=20230425&amp;DB=EPODOC&amp;CC=CN&amp;NR=116016816A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230425&amp;DB=EPODOC&amp;CC=CN&amp;NR=116016816A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHAO ZHIFENG</creatorcontrib><creatorcontrib>ZHU SHIQIANG</creatorcontrib><creatorcontrib>DU CHENGYAO</creatorcontrib><creatorcontrib>SONG XIAOFENG</creatorcontrib><title>Embedded GPU zero-copy panoramic image splicing method and system based on improved L-ORB algorithm</title><description>An embedded GPU zero-copy panoramic image splicing method based on an improved L-ORB algorithm comprises the following steps: step 1, determining an overlapping region of a camera array by using a calibration file, and then extracting and matching feature points of images in the overlapping region by using the ORB algorithm; 2, performing exposure compensation on the original image based on brightness consistency prior; and step 3, GPU utilization is optimized by using a stream parallel strategy. The invention also comprises an embedded GPU zero-copy panoramic image splicing system based on the improved L-ORB algorithm. According to the method, the efficiency is improved, and GPU resources can be fully utilized. 一种改进L-ORB算法的嵌入式GPU零拷贝全景图像拼接方法,包括:步骤1,使用标定文件确定相机阵列的重叠区域,然后使用ORB算法对重叠区域的图像进行特征点提取和匹配;步骤2,基于亮度一致性先验对原始图像进行曝光补偿;步骤3,使用流并行策略优化GPU利用。本发明还包括一种改进L-ORB算法的嵌入式GPU零拷贝全景图像拼接系统。本发明提升了效率,并且可以充分利用GPU资源。</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNi0EKwjAQAHvxIOof1gcUDELwakvVg6iInss2WdtAkw1JEOrrzcEHeJo5zMwL1diOtCYNx9sTPhS4VOwn8Og4oDUKjMWeIPrRKON6sJQG1oBOQ5xiIgsdxryzy6UP_M5-Lq_3CnDsOZg02GUxe-EYafXjolgfmkd9KslzS9GjIkeprS9CyI2QOyH323-aLwLDPVg</recordid><startdate>20230425</startdate><enddate>20230425</enddate><creator>ZHAO ZHIFENG</creator><creator>ZHU SHIQIANG</creator><creator>DU CHENGYAO</creator><creator>SONG XIAOFENG</creator><scope>EVB</scope></search><sort><creationdate>20230425</creationdate><title>Embedded GPU zero-copy panoramic image splicing method and system based on improved L-ORB algorithm</title><author>ZHAO ZHIFENG ; ZHU SHIQIANG ; DU CHENGYAO ; SONG XIAOFENG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116016816A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</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>ZHAO ZHIFENG</creatorcontrib><creatorcontrib>ZHU SHIQIANG</creatorcontrib><creatorcontrib>DU CHENGYAO</creatorcontrib><creatorcontrib>SONG XIAOFENG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHAO ZHIFENG</au><au>ZHU SHIQIANG</au><au>DU CHENGYAO</au><au>SONG XIAOFENG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Embedded GPU zero-copy panoramic image splicing method and system based on improved L-ORB algorithm</title><date>2023-04-25</date><risdate>2023</risdate><abstract>An embedded GPU zero-copy panoramic image splicing method based on an improved L-ORB algorithm comprises the following steps: step 1, determining an overlapping region of a camera array by using a calibration file, and then extracting and matching feature points of images in the overlapping region by using the ORB algorithm; 2, performing exposure compensation on the original image based on brightness consistency prior; and step 3, GPU utilization is optimized by using a stream parallel strategy. The invention also comprises an embedded GPU zero-copy panoramic image splicing system based on the improved L-ORB algorithm. According to the method, the efficiency is improved, and GPU resources can be fully utilized. 一种改进L-ORB算法的嵌入式GPU零拷贝全景图像拼接方法,包括:步骤1,使用标定文件确定相机阵列的重叠区域,然后使用ORB算法对重叠区域的图像进行特征点提取和匹配;步骤2,基于亮度一致性先验对原始图像进行曝光补偿;步骤3,使用流并行策略优化GPU利用。本发明还包括一种改进L-ORB算法的嵌入式GPU零拷贝全景图像拼接系统。本发明提升了效率,并且可以充分利用GPU资源。</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN116016816A
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 Embedded GPU zero-copy panoramic image splicing method and system based on improved L-ORB algorithm
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T22%3A15%3A54IST&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=ZHAO%20ZHIFENG&rft.date=2023-04-25&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116016816A%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