Vision-Based Indoor Scene Recognition from Time-Series Aerial Images Obtained Using a MAV Mounted Monocular Camera
This paper presents a vision-based indoor scene recognition method from aerial time-series images obtained using a micro air vehicle (MAV). The proposed method comprises two procedures: a codebook feature description procedure, and a recognition procedure using category maps. For the former procedur...
Saved in:
Published in | Drones (Basel) Vol. 3; no. 1; p. 22 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
MDPI AG
01.03.2019
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | This paper presents a vision-based indoor scene recognition method from aerial time-series images obtained using a micro air vehicle (MAV). The proposed method comprises two procedures: a codebook feature description procedure, and a recognition procedure using category maps. For the former procedure, codebooks are created automatically as visual words using self-organizing maps (SOMs) after extracting part-based local features using a part-based descriptor from time-series scene images. For the latter procedure, category maps are created using counter propagation networks (CPNs) with the extraction of category boundaries using a unified distance matrix (U-Matrix). Using category maps, topologies of image features are mapped into a low-dimensional space based on competitive and neighborhood learning. We obtained aerial time-series image datasets of five sets for two flight routes: a round flight route and a zigzag flight route. The experimentally obtained results with leave-one-out cross-validation (LOOCV) revealed respective mean recognition accuracies for the round flight datasets (RFDs) and zigzag flight datasets (ZFDs) of 71.7% and 65.5% for 10 zones. The category maps addressed the complexity of scenes because of segmented categories. Although extraction results of category boundaries using U-Matrix were partially discontinuous, we obtained comprehensive category boundaries that segment scenes into several categories. |
---|---|
AbstractList | This paper presents a vision-based indoor scene recognition method from aerial time-series images obtained using a micro air vehicle (MAV). The proposed method comprises two procedures: a codebook feature description procedure, and a recognition procedure using category maps. For the former procedure, codebooks are created automatically as visual words using self-organizing maps (SOMs) after extracting part-based local features using a part-based descriptor from time-series scene images. For the latter procedure, category maps are created using counter propagation networks (CPNs) with the extraction of category boundaries using a unified distance matrix (U-Matrix). Using category maps, topologies of image features are mapped into a low-dimensional space based on competitive and neighborhood learning. We obtained aerial time-series image datasets of five sets for two flight routes: a round flight route and a zigzag flight route. The experimentally obtained results with leave-one-out cross-validation (LOOCV) revealed respective mean recognition accuracies for the round flight datasets (RFDs) and zigzag flight datasets (ZFDs) of 71.7% and 65.5% for 10 zones. The category maps addressed the complexity of scenes because of segmented categories. Although extraction results of category boundaries using U-Matrix were partially discontinuous, we obtained comprehensive category boundaries that segment scenes into several categories. |
Author | Madokoro, Hirokazu Shimoi, Nobuhiro Sato, Kazuhito |
Author_xml | – sequence: 1 givenname: Hirokazu orcidid: 0000-0001-5485-2928 surname: Madokoro fullname: Madokoro, Hirokazu – sequence: 2 givenname: Kazuhito surname: Sato fullname: Sato, Kazuhito – sequence: 3 givenname: Nobuhiro surname: Shimoi fullname: Shimoi, Nobuhiro |
BookMark | eNpVkM1PAjEQxRuDiYgcvfcfWO3X7pYjEj9IICSCxNtmdndKStjWtMvB_94ixuhh8ua9N_kd5poMnHdIyC1nd1JO2H0bko-SccaEuCBDkTOVKVW8D_7sV2Qc456dTlReTPiQhK2N1rvsASK2dO5a7wNdN-iQvmLjd872qaYm-I5ubIfZGoPFSKdJ4EDnHeySW9U9WJcAb9G6HQW6nG7p0h9dn7Kld745HiDQGXQY4IZcGjhEHP_oiGyeHjezl2yxep7PpousUUz3mVBCYyshN5KbXKfJGWqjSiMMB80nqJQoUy8bNMC10qYtOdTAjUKt5IjMz9jWw776CLaD8Fl5sNV34MOugtDb5oCVaDUHMckLLIXipq4ltg3LayhKqVAViZWdWU3wMQY0vzzOqtP7q3_vl1-OB3sw |
CitedBy_id | crossref_primary_10_1038_s41598_023_50064_w crossref_primary_10_3390_s21144881 crossref_primary_10_3390_drones5040123 crossref_primary_10_3390_robotics9020040 |
Cites_doi | 10.1109/CVPR.2009.5206537 10.1016/j.paerosci.2017.04.003 10.7210/jrsj.31.918 10.1364/AO.26.004979 10.1109/ICASSP.2013.6639343 10.1587/transinf.E94.D.127 10.1109/ICCAS.2016.7832306 10.5194/isprsarchives-XL-3-305-2014 10.1214/09-SS054 10.1109/ICCV.2003.1238354 10.1098/rspb.1979.0006 10.1109/IROS.2007.4398986 10.1109/TPAMI.2007.40 10.1016/S0079-6123(06)55002-2 10.1007/BFb0119405 10.1109/TPAMI.2017.2723009 10.1109/TSMC.1979.4310076 10.1109/TPAMI.2007.1049 10.1109/CVPR.2005.16 10.1002/arp.399 10.1109/IROS.2009.5354164 10.5244/C.27.13 10.14429/dsj.68.10504 10.1109/TPAMI.2010.224 10.1126/science.1127647 10.1109/ICCV.1999.790410 10.1109/CVPR.2005.177 10.1007/978-3-319-29363-9_14 10.1109/SII.2017.8279296 10.1109/ROMAN.2014.6926331 10.1016/j.geomorph.2015.05.011 10.1109/ROBOT.1996.506507 |
ContentType | Journal Article |
DBID | AAYXX CITATION DOA |
DOI | 10.3390/drones3010022 |
DatabaseName | CrossRef Directory of Open Access Journals |
DatabaseTitle | CrossRef |
DatabaseTitleList | CrossRef |
Database_xml | – sequence: 1 dbid: DOA name: Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
DeliveryMethod | fulltext_linktorsrc |
EISSN | 2504-446X |
ExternalDocumentID | oai_doaj_org_article_2d81a2956e7241fbb3edc05ba6734e46 10_3390_drones3010022 |
GroupedDBID | AADQD AAFWJ AAYXX ADBBV AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS BCNDV CITATION GROUPED_DOAJ IAO MODMG M~E OK1 |
ID | FETCH-LOGICAL-c408t-2428ed3a5f31f581f550e8f47f2f1a819e44273a53cefa1848fd71aba1f4e843 |
IEDL.DBID | DOA |
ISSN | 2504-446X |
IngestDate | Thu Jul 04 21:03:31 EDT 2024 Fri Aug 23 02:48:50 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 1 |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c408t-2428ed3a5f31f581f550e8f47f2f1a819e44273a53cefa1848fd71aba1f4e843 |
ORCID | 0000-0001-5485-2928 |
OpenAccessLink | https://doaj.org/article/2d81a2956e7241fbb3edc05ba6734e46 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_2d81a2956e7241fbb3edc05ba6734e46 crossref_primary_10_3390_drones3010022 |
PublicationCentury | 2000 |
PublicationDate | 2019-03-01 |
PublicationDateYYYYMMDD | 2019-03-01 |
PublicationDate_xml | – month: 03 year: 2019 text: 2019-03-01 day: 01 |
PublicationDecade | 2010 |
PublicationTitle | Drones (Basel) |
PublicationYear | 2019 |
Publisher | MDPI AG |
Publisher_xml | – name: MDPI AG |
References | ref13 ref35 ref12 ref34 ref15 ref37 ref14 ref36 ref30 ref11 ref33 Dissanayake (ref2) 2000 ref10 Vapnik (ref28) 1963; 24 ref32 ref1 ref17 ref16 ref38 ref19 ref18 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref27 Kohonen (ref31) 1995 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 |
References_xml | – ident: ref13 doi: 10.1109/CVPR.2009.5206537 – ident: ref3 doi: 10.1016/j.paerosci.2017.04.003 – ident: ref21 doi: 10.7210/jrsj.31.918 – ident: ref32 doi: 10.1364/AO.26.004979 – ident: ref18 doi: 10.1109/ICASSP.2013.6639343 – ident: ref16 doi: 10.1587/transinf.E94.D.127 – ident: ref26 doi: 10.1109/ICCAS.2016.7832306 – ident: ref5 doi: 10.5194/isprsarchives-XL-3-305-2014 – ident: ref36 doi: 10.1214/09-SS054 – ident: ref14 doi: 10.1109/ICCV.2003.1238354 – ident: ref4 doi: 10.1098/rspb.1979.0006 – ident: ref23 doi: 10.1109/IROS.2007.4398986 – ident: ref12 doi: 10.1109/TPAMI.2007.40 – ident: ref19 doi: 10.1016/S0079-6123(06)55002-2 – start-page: 265 year: 2000 ident: ref2 article-title: An Experimental and Theoretical Investigation into Simultaneous Localisation and Map Building (SLAM) doi: 10.1007/BFb0119405 contributor: fullname: Dissanayake – ident: ref10 doi: 10.1109/TPAMI.2017.2723009 – ident: ref38 doi: 10.1109/TSMC.1979.4310076 – ident: ref7 doi: 10.1109/TPAMI.2007.1049 – ident: ref22 doi: 10.1109/CVPR.2005.16 – ident: ref11 – ident: ref34 – ident: ref30 – ident: ref37 doi: 10.1002/arp.399 – ident: ref8 doi: 10.1109/IROS.2009.5354164 – ident: ref29 doi: 10.5244/C.27.13 – ident: ref27 doi: 10.14429/dsj.68.10504 – ident: ref9 doi: 10.1109/TPAMI.2010.224 – ident: ref17 doi: 10.1126/science.1127647 – ident: ref20 doi: 10.1109/ICCV.1999.790410 – ident: ref24 doi: 10.1109/CVPR.2005.177 – ident: ref1 doi: 10.1007/978-3-319-29363-9_14 – ident: ref25 doi: 10.1109/SII.2017.8279296 – volume: 24 start-page: 774 year: 1963 ident: ref28 article-title: Pattern Recognition Using Generalized Portrait Method publication-title: Autom. Remote Control contributor: fullname: Vapnik – ident: ref33 doi: 10.1109/ROMAN.2014.6926331 – year: 1995 ident: ref31 contributor: fullname: Kohonen – ident: ref6 doi: 10.1016/j.geomorph.2015.05.011 – ident: ref15 doi: 10.1109/ROBOT.1996.506507 – ident: ref35 |
SSID | ssj0002245691 |
Score | 2.152498 |
Snippet | This paper presents a vision-based indoor scene recognition method from aerial time-series images obtained using a micro air vehicle (MAV). The proposed method... |
SourceID | doaj crossref |
SourceType | Open Website Aggregation Database |
StartPage | 22 |
SubjectTerms | category maps counter propagation networks leave-one-out cross-validation micro air vehicles self-organizing maps unified distance matrix |
Title | Vision-Based Indoor Scene Recognition from Time-Series Aerial Images Obtained Using a MAV Mounted Monocular Camera |
URI | https://doaj.org/article/2d81a2956e7241fbb3edc05ba6734e46 |
Volume | 3 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELZQJxYEAkR5yQNis2rHduKMbUXVIhUkKFW3yM8BiQSl5f9zdlpUJhaGLE50ir67-O6cu-8QugtW8SAKS6Q3gQiWOWKMpsSUojC5ygpqYr_z_CmfvonHlVztjfqKNWEdPXAH3CBziukMonhfgLMJxnDvLJVG5wUXXnRk20zuJVPvidQFAoOSdaSaHPL6gWsj9z2Yc7z5ywntcfUnpzI5RkfbaBAPu7c4QQe-PkXtMvV7kxE4GIdntWuaFr9a2JTwy67cp6lxbAzBsYODxBMuv8bDZEx49gFbxBo_m5j0g4BUFIA1ng-XeB4nQ8AafMlNKkDFYx1Ppc7QYvKwGE_JdjQCsYKqTfyRq7zjWgbOglRwSeoVgB6ywDR4eS8EBCZacuuDhixOBVcwbTQLwivBz1GvBjwuEOaBlUGZXBdcityDWBpUbjOpqPOlyProfgdV9dkRYFSQOERMq1-Y9tEoAvnzUOStTgugzWqrzeovbV7-h5ArdAhhTdlVil2j3qb98jcQOmzMbbKSb_Ktwx4 |
link.rule.ids | 315,786,790,870,2115,27957,27958 |
linkProvider | Directory of Open Access Journals |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Vision-Based+Indoor+Scene+Recognition+from+Time-Series+Aerial+Images+Obtained+Using+a+MAV+Mounted+Monocular+Camera&rft.jtitle=Drones+%28Basel%29&rft.au=Hirokazu+Madokoro&rft.au=Kazuhito+Sato&rft.au=Nobuhiro+Shimoi&rft.date=2019-03-01&rft.pub=MDPI+AG&rft.eissn=2504-446X&rft.volume=3&rft.issue=1&rft.spage=22&rft_id=info:doi/10.3390%2Fdrones3010022&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_2d81a2956e7241fbb3edc05ba6734e46 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2504-446X&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2504-446X&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2504-446X&client=summon |