A New Multi-Channel Deep Convolutional Neural Network for Semantic Segmentation of Remote Sensing Image
The semantic segmentation of remote sensing (RS) image is a hot research field. With the development of deep learning, the semantic segmentation based on a full convolution neural network greatly improves the segmentation accuracy. The amount of information on the RS image is very large, but the sam...
Saved in:
Published in | IEEE access Vol. 8; p. 1 |
---|---|
Main Authors | , , , , |
Format | Journal Article |
Language | English |
Published |
Piscataway
IEEE
01.01.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The semantic segmentation of remote sensing (RS) image is a hot research field. With the development of deep learning, the semantic segmentation based on a full convolution neural network greatly improves the segmentation accuracy. The amount of information on the RS image is very large, but the sample size is extremely uneven. Therefore, even the common network can segment RS images to a certain extent, but the segmentation accuracy can still be greatly improved. The common neural network deepens the network to improve the classification accuracy, but it has a lot of loss to the target spatial features and scale features, and the existing common feature fusion methods can only solve some problems. A segmentation network is built to solve the above problems very well. The network employs the InceptionV-4 network as the backbone and improves it. We modify the network structure and introduce the changed Atrous Spatial Pyramid Pooling module to extract the multi-scale features of the target from different training stages. Without losing the depth of the network, using Inception blocks to strengthen the width of the network can obtain more abstract features. At the same time, the backbone network is used for semantic fusion of the context, it can retain more spatial features, then an effective decoder network is designed. Finally, evaluate our model on the ISPRS 2D Semantic Labeling Contest Potsdam and Inria Aerial Image Labeling Dataset. The results show that the network has very superior performance, reaching 89.62% IOU score and 94.49% F1 score on the Potsdam dataset, and the IOU score on the Inria dataset has been greatly improved. |
---|---|
AbstractList | The semantic segmentation of remote sensing (RS) image is a hot research field. With the development of deep learning, the semantic segmentation based on a full convolution neural network greatly improves the segmentation accuracy. The amount of information on the RS image is very large, but the sample size is extremely uneven. Therefore, even the common network can segment RS images to a certain extent, but the segmentation accuracy can still be greatly improved. The common neural network deepens the network to improve the classification accuracy, but it has a lot of loss to the target spatial features and scale features, and the existing common feature fusion methods can only solve some problems. A segmentation network is built to solve the above problems very well. The network employs the InceptionV-4 network as the backbone and improves it. We modify the network structure and introduce the changed Atrous Spatial Pyramid Pooling module to extract the multi-scale features of the target from different training stages. Without losing the depth of the network, using Inception blocks to strengthen the width of the network can obtain more abstract features. At the same time, the backbone network is used for semantic fusion of the context, it can retain more spatial features, then an effective decoder network is designed. Finally, evaluate our model on the ISPRS 2D Semantic Labeling Contest Potsdam and Inria Aerial Image Labeling Dataset. The results show that the network has very superior performance, reaching 89.62% IOU score and 94.49% F1 score on the Potsdam dataset, and the IOU score on the Inria dataset has been greatly improved. |
Author | Fan, Haisheng Zou, Yongjie Zhang, Yongjun Liu, Wenjie Cui, Zhongwei |
Author_xml | – sequence: 1 givenname: Wenjie surname: Liu fullname: Liu, Wenjie organization: Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China. (e-mail: Udellliu@163.com) – sequence: 2 givenname: Yongjun surname: Zhang fullname: Zhang, Yongjun organization: Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China – sequence: 3 givenname: Haisheng surname: Fan fullname: Fan, Haisheng organization: ZHUHAI ORBITA AEROSPACE SCIENCE&TECHNOLOGY Co, LTD. Oribita Tech Park, 1 BaiSha Road, TangJia DongAn, ZhuHai 519000, China – sequence: 4 givenname: Yongjie surname: Zou fullname: Zou, Yongjie organization: Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China – sequence: 5 givenname: Zhongwei surname: Cui fullname: Cui, Zhongwei organization: Big Data Science and Intelligent Engineering Research Institute, Guizhou Education University, Guiyang 550018, China |
BookMark | eNpNUcFunDAQRVEqNU3zBbkg9cxmjI2NjyuaNislrdTN3RpgTNiCvTXQqH9fb4ii-DKj5_fejP0-JefOO0qSawYbxkDfbKvqdr_f5JDDhgNoreRZcpEzqTNecHn-rv-YXE3TAeIpI1Soi6Tbpj_oOX1YhrnPqid0job0K9Exrbz764dl7r3DIZKW8FLmZx9-p9aHdE8jurlvYtON5GY8UVNv0180-pki7KbedeluxI4-Jx8sDhNdvdbL5PHb7WN1l93__L6rtvdZI6CcMyQrGNQIElqrBAhZK1kqtMqihFxyRQKZhJLnWFiJhLKwrEbBgXHZ8stkt9q2Hg_mGPoRwz_jsTcvgA-dwRB3HshAo-ta6xKk0qJtSix5QblWraBaKoLo9WX1Ogb_Z6FpNge_hPgZk8lFIWRcVMjI4iurCX6aAtm3qQzMKR-z5mNO-ZjXfKLqelX1RPSm0Cy-I97-BzJrjNA |
CODEN | IAECCG |
CitedBy_id | crossref_primary_10_52547_jgit_10_2_89 crossref_primary_10_1007_s11042_023_17247_z crossref_primary_10_1007_s12524_022_01496_w crossref_primary_10_1371_journal_pone_0290624 crossref_primary_10_3390_ijgi11030165 crossref_primary_10_3390_ijgi10040245 |
Cites_doi | 10.3390/rs11161922 10.1109/TFUZZ.2015.2406889 10.1016/0273-1177(81)90384-7 10.3390/rs61110733 10.1109/CVPRW.2014.131 10.1007/s002670010258 10.1016/j.isprsjprs.2017.11.011 10.1109/TSMC.1973.4309314 10.1109/ICPHYS.2019.8780187 10.1117/1.JRS.8.083584 10.3390/rs11070830 10.1080/2150704X.2015.1101179 10.1016/j.isprsjprs.2020.01.023 10.1109/ICCV.2015.179 10.1126/science.1127647 10.3390/rs9060522 10.3390/rs9040368 10.1016/j.isprsjprs.2019.11.006 10.1109/ICCV.2017.322 10.1109/JSTARS.2019.2925416 10.3390/rs10010052 10.1364/AO.44.004327 10.1016/j.isprsjprs.2020.01.013 10.1109/IGARSS.2017.8127684 10.1016/S0034-4257(96)00067-3 10.1109/TPAMI.2016.2572683 10.3390/rs11161897 10.1016/j.ijleo.2015.06.024 10.1109/TPAMI.2017.2699184 10.3390/rs11010020 |
ContentType | Journal Article |
Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020 |
Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020 |
DBID | 97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA |
DOI | 10.1109/ACCESS.2020.3009976 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Xplore CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals |
DatabaseTitle | CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional |
DatabaseTitleList | Materials Research Database |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Xplore url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering |
EISSN | 2169-3536 |
EndPage | 1 |
ExternalDocumentID | oai_doaj_org_article_0c9bb99806794dc8a835e297d4eb67e0 10_1109_ACCESS_2020_3009976 9143076 |
Genre | orig-research |
GrantInformation_xml | – fundername: 2017 Zhuhai introduces innovation and entrepreneurship team grantid: ZH01110405170027PWC – fundername: Key Disciplines of Guizhou ProvinceComputer Science and Technology grantid: ZDXK[2018]007 – fundername: Key Supported Disciplines of Guizhou ProvinceComputer Application Technology grantid: No. QianXueWeiHeZi ZDXK [2016]20 – fundername: Research Foundation for Advanced Talents of Guizhou University grantid: (2016) No. 49 – fundername: National Natural Science Foundation of China grantid: 61462013; 61661010 funderid: 10.13039/501100001809 |
GroupedDBID | 0R~ 5VS 6IK 97E AAJGR ABVLG ACGFS ADBBV ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS ESBDL GROUPED_DOAJ IFIPE IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RIG RNS 4.4 AAYXX CITATION EJD 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D |
ID | FETCH-LOGICAL-c408t-aef410ba060df74046b7687af7fa602637e4a160832a5f6aea65f1ba430136d3 |
IEDL.DBID | RIE |
ISSN | 2169-3536 |
IngestDate | Thu Sep 05 15:41:00 EDT 2024 Fri Sep 13 04:25:07 EDT 2024 Fri Aug 23 01:12:53 EDT 2024 Wed Jun 26 19:28:33 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c408t-aef410ba060df74046b7687af7fa602637e4a160832a5f6aea65f1ba430136d3 |
ORCID | 0000-0003-3209-4024 0000-0002-7534-1219 |
OpenAccessLink | https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/document/9143076 |
PQID | 2454641046 |
PQPubID | 4845423 |
PageCount | 1 |
ParticipantIDs | ieee_primary_9143076 doaj_primary_oai_doaj_org_article_0c9bb99806794dc8a835e297d4eb67e0 crossref_primary_10_1109_ACCESS_2020_3009976 proquest_journals_2454641046 |
PublicationCentury | 2000 |
PublicationDate | 2020-01-01 |
PublicationDateYYYYMMDD | 2020-01-01 |
PublicationDate_xml | – month: 01 year: 2020 text: 2020-01-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Piscataway |
PublicationPlace_xml | – name: Piscataway |
PublicationTitle | IEEE access |
PublicationTitleAbbrev | Access |
PublicationYear | 2020 |
Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
References | ref35 ref13 ref34 ref37 ref36 ref14 ref30 ref33 ref10 ref2 ref1 ref39 ref17 ref38 ref18 yu (ref23) 2015 michaelis (ref26) 2018 szegedy (ref16) 2014 huaiying (ref11) 2011; 15 ref25 ref42 ref41 (ref32) 2020 simonyan (ref15) 2014 ronneberger (ref20) 2015 lafferty (ref24) 2001; 3 ref28 ref27 ref29 ref8 ref7 szegedy (ref19) 2016; 3 ref9 ref4 chen (ref22) 2017 ref3 ref6 ref5 hinton (ref12) 2006; 313 badrinarayanan (ref21) 2015 ref40 ioffe (ref31) 2015 |
References_xml | – ident: ref38 doi: 10.3390/rs11161922 – ident: ref13 doi: 10.1109/TFUZZ.2015.2406889 – volume: 3 start-page: 282 year: 2001 ident: ref24 article-title: Pereira FCN Conditional random fields: Probabilistic models for segmenting and labeling swquence data publication-title: Prec ICML contributor: fullname: lafferty – ident: ref8 doi: 10.1016/0273-1177(81)90384-7 – ident: ref5 doi: 10.3390/rs61110733 – ident: ref14 doi: 10.1109/CVPRW.2014.131 – ident: ref1 doi: 10.1007/s002670010258 – ident: ref39 doi: 10.1016/j.isprsjprs.2017.11.011 – year: 2017 ident: ref22 article-title: Rethinking atrous convolution for semantic image segmentation publication-title: arXiv 1706 05587 contributor: fullname: chen – ident: ref7 doi: 10.1109/TSMC.1973.4309314 – ident: ref42 doi: 10.1109/ICPHYS.2019.8780187 – ident: ref10 doi: 10.1117/1.JRS.8.083584 – ident: ref29 doi: 10.3390/rs11070830 – year: 2018 ident: ref26 article-title: One-shot instance segmentation publication-title: arXiv 1811 11507 contributor: fullname: michaelis – ident: ref2 doi: 10.1080/2150704X.2015.1101179 – ident: ref40 doi: 10.1016/j.isprsjprs.2020.01.023 – ident: ref25 doi: 10.1109/ICCV.2015.179 – volume: 313 start-page: 504 year: 2006 ident: ref12 article-title: Reducing the dimensionality of data with neural networks publication-title: Science doi: 10.1126/science.1127647 contributor: fullname: hinton – year: 2014 ident: ref16 article-title: Going deeper with convolutions publication-title: arXiv 1409 4842 contributor: fullname: szegedy – volume: 3 start-page: 105 year: 2016 ident: ref19 article-title: Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning publication-title: Comput Sci contributor: fullname: szegedy – ident: ref37 doi: 10.3390/rs9060522 – volume: 15 start-page: 778 year: 2011 ident: ref11 article-title: A shadow detection of remote sensing images based on statistical texture features publication-title: J Remote Sens contributor: fullname: huaiying – year: 2015 ident: ref31 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift publication-title: arXiv 1502 03167 contributor: fullname: ioffe – ident: ref34 doi: 10.3390/rs9040368 – ident: ref28 doi: 10.1016/j.isprsjprs.2019.11.006 – ident: ref18 doi: 10.1109/ICCV.2017.322 – ident: ref41 doi: 10.1109/JSTARS.2019.2925416 – ident: ref36 doi: 10.3390/rs10010052 – ident: ref3 doi: 10.1364/AO.44.004327 – ident: ref27 doi: 10.1016/j.isprsjprs.2020.01.013 – year: 2014 ident: ref15 article-title: Very deep convolutional networks for large-scale image recognition publication-title: arXiv 1409 1556 contributor: fullname: simonyan – ident: ref33 doi: 10.1109/IGARSS.2017.8127684 – year: 2015 ident: ref21 article-title: SegNet: A deep convolutional encoder-decoder architecture for image segmentation publication-title: arXiv 1511 00561 contributor: fullname: badrinarayanan – year: 2020 ident: ref32 publication-title: 2D Semantic Labeling Contest – ident: ref9 doi: 10.1016/S0034-4257(96)00067-3 – ident: ref17 doi: 10.1109/TPAMI.2016.2572683 – year: 2015 ident: ref23 article-title: Multi-scale context aggregation by dilated convolutions publication-title: arXiv 1511 07122 contributor: fullname: yu – ident: ref30 doi: 10.3390/rs11161897 – ident: ref4 doi: 10.1016/j.ijleo.2015.06.024 – year: 2015 ident: ref20 article-title: U-net: Convolutional networks for biomedical image segmentation publication-title: arXiv 1505 04597 contributor: fullname: ronneberger – ident: ref6 doi: 10.1109/TPAMI.2017.2699184 – ident: ref35 doi: 10.3390/rs11010020 |
SSID | ssj0000816957 |
Score | 2.2589755 |
Snippet | The semantic segmentation of remote sensing (RS) image is a hot research field. With the development of deep learning, the semantic segmentation based on a... |
SourceID | doaj proquest crossref ieee |
SourceType | Open Website Aggregation Database Publisher |
StartPage | 1 |
SubjectTerms | Accuracy Artificial neural networks Computer networks Convolution Datasets Feature extraction feature fusion Image classification Image segmentation Labelling Machine learning neural network Neural networks Remote sensing Semantic segmentation Semantics Two dimensional models |
SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA7iSQ_iE9cXOXi0mHaTtDmuq6KCHnyAt5CkExHcrujq73cmjbLgwYunllDS5pt0Ml8e3zB2aGKITTmsC6lpmdH5smgAiWtQdXSiCUEnOYbrG33xIK8e1eNcqi_aE9bLA_fAHYtgvEdOQBMesg2Nw5ABKlO3EryuoWfrpZojU8kHN6U2qs4yQ6Uwx6PxGFuEhLBCnkpxEamMzA1FSbE_p1j55ZfTYHO-ylZylMhH_detsQXo1tnynHbgBnsacXRQPB2gLeiMQAcv_BTglY-n3WfuUFgHqW-kS9ruzTFG5XcwQTyfA948TfLZo45PI78FNBxgcUczCPxygs5mk92fn92PL4qcNaEIUjSzwkGUpfBOaNHGWiL_9UgpahcRfMo3NaxBulJj6FU5FbUDp1UsvZNDkm9rh1tssZt2sM14MCGSwJ5QLUgfnTehMqpBr-BJEycM2NE3fva118awiVMIY3u4LcFtM9wDdkIY_zxKwtapAM1ts7ntX-YesA2y0E8lBuM9QXXvfVvM5p_w3VZSSS1pEXvnP169y5aoOf38yx5bnL19wD5GJDN_kDrfF8Ma2rw priority: 102 providerName: Directory of Open Access Journals |
Title | A New Multi-Channel Deep Convolutional Neural Network for Semantic Segmentation of Remote Sensing Image |
URI | https://ieeexplore.ieee.org/document/9143076 https://www.proquest.com/docview/2454641046/abstract/ https://doaj.org/article/0c9bb99806794dc8a835e297d4eb67e0 |
Volume | 8 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1NT9wwEB0BJ3roB7TqthT5wJEsTtZx4uN2WwRIcGipxM2ynTGqymYR7PbQX98Zx7tCbQ89xYoSy_bzx7yx5xngyMQQ23LSFErzNqPzZdEiEddQN9HJNgSd5Bgur_TZN3VxU99swfEmFgYR0-EzHHMy7eV3i7BiV9mJocWdePc2bLeyGmK1Nv4UvkDC1E0WFiqlOZnOZlQHooAVMVO2hFhX5MnikzT686Uqf83EaXk5fQGX64INp0p-jFdLPw6__tBs_N-Sv4Tn2c4U06FjvIIt7Pfg2RP1wX24nQqa4kQKwS04yqDHO_EJ8V7MFv3P3CUpD9bvSI90YFyQlSu-4pwQ-R4ocTvP0Uu9WETxBQl6pNc9-yDE-Zymq9dwffr5enZW5HsXiqBkuywcRlVK76SWXWwUMWhPpKRxkeDjG6smDSpXajLeKldH7dDpOpbeURXLie4mb2CnX_T4FkQwIbJEn6w7VD46b0Jl6paawrOqThjB8RoPez-oa9jESqSxA3yW4bMZvhF8ZMw2n7I0dnpBbW3zSLMyGO-JRLKHTHWhdWRjYmWaTqHXDcoR7DM-m0wyNCM4WPcAm4fxo61UrbTibfB3__7rPexyAQefzAHsLB9W-IGslKU_TOz-MHXS3-2O5TQ |
link.rule.ids | 315,786,790,802,870,2115,27957,27958,55109 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LbxMxEB6VcgAOvAoiUMAHjt3Um3i962MIVCk0PUCQerNs77iqIJsKEg78ema8TlQBB05reXct258fM2PPNwBvTAyxKcd1oTQfMzpfFg2S4hqqOjrZhKATHcP8XM--qA8X1cUeHO18YRAxXT7DISfTWX67Chs2lR0b2txJ774Ft2mfl6b31tpZVDiEhKnqTC1E748n0ym1gpTAEemmLAsxs8iN7Sex9OewKn-txWmDOXkA823V-nslX4ebtR-GX3-wNv5v3R_C_Sxpikk_NB7BHnaP4d4N_sEDuJwIWuREcsIt2M-gw2_iHeK1mK66n3lQUhnM4JEe6cq4IDlXfMYlYXIVKHG5zP5LnVhF8QkJfKTsjq0Q4nRJC9YTWJy8X0xnRY68UAQlm3XhMKpSeie1bGOtSIf2pJbULhKAHLNqXKNypSbxbeSqqB06XcXSO2piOdbt-Cnsd6sOn4EIJkQm6ZNVi8pH500YmaqhrvDMqxMGcLTFw173_Bo26SXS2B4-y_DZDN8A3jJmu0-ZHDtlUF_bPNesDMZ7UiPZRqba0DiSMnFk6lah1zXKARwwPrtCMjQDONyOAJsn8g87UpXSig_Cn__7r9dwZ7aYn9mz0_OPL-AuV7a30BzC_vr7Bl-SzLL2r9JQ_Q3Cz-eV |
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=A+New+Multi-Channel+Deep+Convolutional+Neural+Network+for+Semantic+Segmentation+of+Remote+Sensing+Image&rft.jtitle=IEEE+access&rft.au=Liu%2C+Wenjie&rft.au=Zhang%2C+Yongjun&rft.au=Fan%2C+Haisheng&rft.au=Zou%2C+Yongjie&rft.date=2020-01-01&rft.pub=IEEE&rft.eissn=2169-3536&rft.spage=1&rft.epage=1&rft_id=info:doi/10.1109%2FACCESS.2020.3009976&rft.externalDocID=9143076 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon |