A grid-point detection method based on U-net for a structured light system

Accurate detection of the feature points of the projected pattern plays an extremely important role in one-shot 3D reconstruction systems, especially for the ones using a grid pattern. To solve this problem, this paper proposes a grid-point detection method based on U-net. A specific dataset is desi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pham, Dieuthuy, Ha, Minhtuan, Xiao, Changyan
Format: Artikel
Sprache: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 Pham, Dieuthuy
Ha, Minhtuan
Xiao, Changyan
description Accurate detection of the feature points of the projected pattern plays an extremely important role in one-shot 3D reconstruction systems, especially for the ones using a grid pattern. To solve this problem, this paper proposes a grid-point detection method based on U-net. A specific dataset is designed that includes the images captured with the two-shot imaging method and the ones acquired with the one-shot imaging method. Among them, the images in the first group after labeled as the ground truth images and the images captured at the same pose with the one-shot method are cut into small patches with the size of 64x64 pixels then feed to the training set. The remaining of the images in the second group is the test set. The experimental results show that our method can achieve a better detecting performance with higher accuracy in comparison with the previous methods.
doi_str_mv 10.48550/arxiv.2012.08641
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2012_08641</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2012_08641</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-9456f71ccaff600ae7c6e064e86878adb34b2a088399414bec33a011ec22a22b3</originalsourceid><addsrcrecordid>eNotz8tqwzAUBFBtuihpP6Cr6gfk6mVZXobQJ4Fs0rW5kq4SQWwHSSnN3zdNuxqGgYFDyIPgjbZty58gf6evRnIhG26NFrfkY0l3OQV2nNNUacCKvqZ5oiPW_Ryog4KBXvonm7DSOGcKtNR88vWUL8sh7faVlnOpON6RmwiHgvf_uSDbl-ft6o2tN6_vq-WagekE63VrYie8hxgN54CdN8iNRmtsZyE4pZ0Ebq3qey20Q68UcCHQSwlSOrUgj3-3V8xwzGmEfB5-UcMVpX4A_ApG7g</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A grid-point detection method based on U-net for a structured light system</title><source>arXiv.org</source><creator>Pham, Dieuthuy ; Ha, Minhtuan ; Xiao, Changyan</creator><creatorcontrib>Pham, Dieuthuy ; Ha, Minhtuan ; Xiao, Changyan</creatorcontrib><description>Accurate detection of the feature points of the projected pattern plays an extremely important role in one-shot 3D reconstruction systems, especially for the ones using a grid pattern. To solve this problem, this paper proposes a grid-point detection method based on U-net. A specific dataset is designed that includes the images captured with the two-shot imaging method and the ones acquired with the one-shot imaging method. Among them, the images in the first group after labeled as the ground truth images and the images captured at the same pose with the one-shot method are cut into small patches with the size of 64x64 pixels then feed to the training set. The remaining of the images in the second group is the test set. The experimental results show that our method can achieve a better detecting performance with higher accuracy in comparison with the previous methods.</description><identifier>DOI: 10.48550/arxiv.2012.08641</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning</subject><creationdate>2020-12</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,782,887</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2012.08641$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2012.08641$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Pham, Dieuthuy</creatorcontrib><creatorcontrib>Ha, Minhtuan</creatorcontrib><creatorcontrib>Xiao, Changyan</creatorcontrib><title>A grid-point detection method based on U-net for a structured light system</title><description>Accurate detection of the feature points of the projected pattern plays an extremely important role in one-shot 3D reconstruction systems, especially for the ones using a grid pattern. To solve this problem, this paper proposes a grid-point detection method based on U-net. A specific dataset is designed that includes the images captured with the two-shot imaging method and the ones acquired with the one-shot imaging method. Among them, the images in the first group after labeled as the ground truth images and the images captured at the same pose with the one-shot method are cut into small patches with the size of 64x64 pixels then feed to the training set. The remaining of the images in the second group is the test set. The experimental results show that our method can achieve a better detecting performance with higher accuracy in comparison with the previous methods.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz8tqwzAUBFBtuihpP6Cr6gfk6mVZXobQJ4Fs0rW5kq4SQWwHSSnN3zdNuxqGgYFDyIPgjbZty58gf6evRnIhG26NFrfkY0l3OQV2nNNUacCKvqZ5oiPW_Ryog4KBXvonm7DSOGcKtNR88vWUL8sh7faVlnOpON6RmwiHgvf_uSDbl-ft6o2tN6_vq-WagekE63VrYie8hxgN54CdN8iNRmtsZyE4pZ0Ebq3qey20Q68UcCHQSwlSOrUgj3-3V8xwzGmEfB5-UcMVpX4A_ApG7g</recordid><startdate>20201205</startdate><enddate>20201205</enddate><creator>Pham, Dieuthuy</creator><creator>Ha, Minhtuan</creator><creator>Xiao, Changyan</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20201205</creationdate><title>A grid-point detection method based on U-net for a structured light system</title><author>Pham, Dieuthuy ; Ha, Minhtuan ; Xiao, Changyan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-9456f71ccaff600ae7c6e064e86878adb34b2a088399414bec33a011ec22a22b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Pham, Dieuthuy</creatorcontrib><creatorcontrib>Ha, Minhtuan</creatorcontrib><creatorcontrib>Xiao, Changyan</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Pham, Dieuthuy</au><au>Ha, Minhtuan</au><au>Xiao, Changyan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A grid-point detection method based on U-net for a structured light system</atitle><date>2020-12-05</date><risdate>2020</risdate><abstract>Accurate detection of the feature points of the projected pattern plays an extremely important role in one-shot 3D reconstruction systems, especially for the ones using a grid pattern. To solve this problem, this paper proposes a grid-point detection method based on U-net. A specific dataset is designed that includes the images captured with the two-shot imaging method and the ones acquired with the one-shot imaging method. Among them, the images in the first group after labeled as the ground truth images and the images captured at the same pose with the one-shot method are cut into small patches with the size of 64x64 pixels then feed to the training set. The remaining of the images in the second group is the test set. The experimental results show that our method can achieve a better detecting performance with higher accuracy in comparison with the previous methods.</abstract><doi>10.48550/arxiv.2012.08641</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2012.08641
ispartof
issn
language eng
recordid cdi_arxiv_primary_2012_08641
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
title A grid-point detection method based on U-net for a structured light system
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-03T12%3A14%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20grid-point%20detection%20method%20based%20on%20U-net%20for%20a%20structured%20light%20system&rft.au=Pham,%20Dieuthuy&rft.date=2020-12-05&rft_id=info:doi/10.48550/arxiv.2012.08641&rft_dat=%3Carxiv_GOX%3E2012_08641%3C/arxiv_GOX%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