Accurate and fast large-depth-of-field three-dimensional reconstruction method based on deep learning
The invention relates to an accurate and fast large-depth-of-field three-dimensional reconstruction method based on deep learning, and belongs to the technical field of computer intelligent vision. Comprising the following steps: constructing a depth-of-field expansion convolutional neural network b...
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 | SHI JILING ZHENG DONGLIANG ZHANG MINGXING ZHANG YI GANG SHUNKUI YU HAOTIAN WANG XIAOYING |
| description | The invention relates to an accurate and fast large-depth-of-field three-dimensional reconstruction method based on deep learning, and belongs to the technical field of computer intelligent vision. Comprising the following steps: constructing a depth-of-field expansion convolutional neural network based on deep learning design, collecting an original fringe picture of a to-be-measured object through a three-dimensional measurement system, obtaining a high-precision wrapped phase, and reconstructing three-dimensional information according to the high-precision wrapped phase. According to the method provided by the invention, a high-precision wrapped phase can be obtained in a larger measurement depth of field by utilizing three fringe images with different phase shifts shot by equipment at a fixed focal length. In the process, measurement errors caused by the projector and the camera can be obviously reduced, and high-performance three-dimensional reconstruction can be realized in a large depth-of-field scene |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN113256800A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN113256800A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN113256800A3</originalsourceid><addsrcrecordid>eNqNikEKwjAUBbtxIeodvgcItBal21IUV67cl2_y0gbSJCS_97cLD-BqmGH2FXqt18wC4mDIchHynCcogySzilZZB29I5owtugWhuBjYU4aOoUhetWyBFsgcDX24wNDmBkjkwTm4MB2rnWVfcPrxUJ0f9_fwVEhxREmsESDj8Gqa9nK9dXXdt_88Xx4iPy4</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Accurate and fast large-depth-of-field three-dimensional reconstruction method based on deep learning</title><source>esp@cenet</source><creator>SHI JILING ; ZHENG DONGLIANG ; ZHANG MINGXING ; ZHANG YI ; GANG SHUNKUI ; YU HAOTIAN ; WANG XIAOYING</creator><creatorcontrib>SHI JILING ; ZHENG DONGLIANG ; ZHANG MINGXING ; ZHANG YI ; GANG SHUNKUI ; YU HAOTIAN ; WANG XIAOYING</creatorcontrib><description>The invention relates to an accurate and fast large-depth-of-field three-dimensional reconstruction method based on deep learning, and belongs to the technical field of computer intelligent vision. Comprising the following steps: constructing a depth-of-field expansion convolutional neural network based on deep learning design, collecting an original fringe picture of a to-be-measured object through a three-dimensional measurement system, obtaining a high-precision wrapped phase, and reconstructing three-dimensional information according to the high-precision wrapped phase. According to the method provided by the invention, a high-precision wrapped phase can be obtained in a larger measurement depth of field by utilizing three fringe images with different phase shifts shot by equipment at a fixed focal length. In the process, measurement errors caused by the projector and the camera can be obviously reduced, and high-performance three-dimensional reconstruction can be realized in a large depth-of-field scene</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; MEASURING ; MEASURING ANGLES ; MEASURING AREAS ; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS ; MEASURING LENGTH, THICKNESS OR SIMILAR LINEARDIMENSIONS ; PHYSICS ; TESTING</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=20210813&DB=EPODOC&CC=CN&NR=113256800A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210813&DB=EPODOC&CC=CN&NR=113256800A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SHI JILING</creatorcontrib><creatorcontrib>ZHENG DONGLIANG</creatorcontrib><creatorcontrib>ZHANG MINGXING</creatorcontrib><creatorcontrib>ZHANG YI</creatorcontrib><creatorcontrib>GANG SHUNKUI</creatorcontrib><creatorcontrib>YU HAOTIAN</creatorcontrib><creatorcontrib>WANG XIAOYING</creatorcontrib><title>Accurate and fast large-depth-of-field three-dimensional reconstruction method based on deep learning</title><description>The invention relates to an accurate and fast large-depth-of-field three-dimensional reconstruction method based on deep learning, and belongs to the technical field of computer intelligent vision. Comprising the following steps: constructing a depth-of-field expansion convolutional neural network based on deep learning design, collecting an original fringe picture of a to-be-measured object through a three-dimensional measurement system, obtaining a high-precision wrapped phase, and reconstructing three-dimensional information according to the high-precision wrapped phase. According to the method provided by the invention, a high-precision wrapped phase can be obtained in a larger measurement depth of field by utilizing three fringe images with different phase shifts shot by equipment at a fixed focal length. In the process, measurement errors caused by the projector and the camera can be obviously reduced, and high-performance three-dimensional reconstruction can be realized in a large depth-of-field scene</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>MEASURING</subject><subject>MEASURING ANGLES</subject><subject>MEASURING AREAS</subject><subject>MEASURING IRREGULARITIES OF SURFACES OR CONTOURS</subject><subject>MEASURING LENGTH, THICKNESS OR SIMILAR LINEARDIMENSIONS</subject><subject>PHYSICS</subject><subject>TESTING</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNikEKwjAUBbtxIeodvgcItBal21IUV67cl2_y0gbSJCS_97cLD-BqmGH2FXqt18wC4mDIchHynCcogySzilZZB29I5owtugWhuBjYU4aOoUhetWyBFsgcDX24wNDmBkjkwTm4MB2rnWVfcPrxUJ0f9_fwVEhxREmsESDj8Gqa9nK9dXXdt_88Xx4iPy4</recordid><startdate>20210813</startdate><enddate>20210813</enddate><creator>SHI JILING</creator><creator>ZHENG DONGLIANG</creator><creator>ZHANG MINGXING</creator><creator>ZHANG YI</creator><creator>GANG SHUNKUI</creator><creator>YU HAOTIAN</creator><creator>WANG XIAOYING</creator><scope>EVB</scope></search><sort><creationdate>20210813</creationdate><title>Accurate and fast large-depth-of-field three-dimensional reconstruction method based on deep learning</title><author>SHI JILING ; ZHENG DONGLIANG ; ZHANG MINGXING ; ZHANG YI ; GANG SHUNKUI ; YU HAOTIAN ; WANG XIAOYING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN113256800A3</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>MEASURING</topic><topic>MEASURING ANGLES</topic><topic>MEASURING AREAS</topic><topic>MEASURING IRREGULARITIES OF SURFACES OR CONTOURS</topic><topic>MEASURING LENGTH, THICKNESS OR SIMILAR LINEARDIMENSIONS</topic><topic>PHYSICS</topic><topic>TESTING</topic><toplevel>online_resources</toplevel><creatorcontrib>SHI JILING</creatorcontrib><creatorcontrib>ZHENG DONGLIANG</creatorcontrib><creatorcontrib>ZHANG MINGXING</creatorcontrib><creatorcontrib>ZHANG YI</creatorcontrib><creatorcontrib>GANG SHUNKUI</creatorcontrib><creatorcontrib>YU HAOTIAN</creatorcontrib><creatorcontrib>WANG XIAOYING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SHI JILING</au><au>ZHENG DONGLIANG</au><au>ZHANG MINGXING</au><au>ZHANG YI</au><au>GANG SHUNKUI</au><au>YU HAOTIAN</au><au>WANG XIAOYING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Accurate and fast large-depth-of-field three-dimensional reconstruction method based on deep learning</title><date>2021-08-13</date><risdate>2021</risdate><abstract>The invention relates to an accurate and fast large-depth-of-field three-dimensional reconstruction method based on deep learning, and belongs to the technical field of computer intelligent vision. Comprising the following steps: constructing a depth-of-field expansion convolutional neural network based on deep learning design, collecting an original fringe picture of a to-be-measured object through a three-dimensional measurement system, obtaining a high-precision wrapped phase, and reconstructing three-dimensional information according to the high-precision wrapped phase. According to the method provided by the invention, a high-precision wrapped phase can be obtained in a larger measurement depth of field by utilizing three fringe images with different phase shifts shot by equipment at a fixed focal length. In the process, measurement errors caused by the projector and the camera can be obviously reduced, and high-performance three-dimensional reconstruction can be realized in a large depth-of-field scene</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN113256800A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL MEASURING MEASURING ANGLES MEASURING AREAS MEASURING IRREGULARITIES OF SURFACES OR CONTOURS MEASURING LENGTH, THICKNESS OR SIMILAR LINEARDIMENSIONS PHYSICS TESTING |
| title | Accurate and fast large-depth-of-field three-dimensional reconstruction method based on deep learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T16%3A21%3A58IST&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=SHI%20JILING&rft.date=2021-08-13&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN113256800A%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 |