IMG2HEIGHT: height estimation from single remote sensing image using a deep convolutional encoder-decoder network

Height estimation from single remote sensing image is a challenging inherently ambiguous and technically ill-posed problem that we address in this study by resorting to deep learning approach. A spatial enhanced and multi-scale aggregated encoder-decoder network, SM-EDNet, is proposed, which takes a...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	International journal of remote sensing Ročník 44; číslo 18; s. 5686 - 5712
Hlavní autori:	Du, Shouhang, Xing, Jianghe, Du, Shihong, Cui, Ximin, Xiao, Xiongwu, Li, Wei, Wang, Shaoyu
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	London Taylor & Francis 17.09.2023 Taylor & Francis Ltd
Predmet:	Coders Convolution data collection deep supervision mechanism DenseASPP encoder-decoder network Encoders-Decoders Formability geometry Height height estimation Ill posed problems Remote sensing ResNet Sensitivity enhancement Single remote sensing image
ISSN:	0143-1161, 1366-5901, 1366-5901
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Height estimation from single remote sensing image is a challenging inherently ambiguous and technically ill-posed problem that we address in this study by resorting to deep learning approach. A spatial enhanced and multi-scale aggregated encoder-decoder network, SM-EDNet, is proposed, which takes a single image as input and produces an estimated height map as output. First, residual network (ResNet) is applied to extract low-level and deep features to cope with the heterogeneous characteristics of remote sensing scenes. Then, the multi-scale context information is aggregated through DenseASPP (Dense Atrous Spatial Pyramid Pooling) by extracting features from multiple dilated convolution layers. The skip connection is constructed by using the structure preserving model, DULR, to aggregate ResNet low-level features and multi-scale high-level features. The deformable convolution module is constructed to enhance the sensitivity to differences in geometric shapes of ground objects. For model training, three-layer deep supervision mechanism is designed to counteract the adverse effects of unstable gradients changes. Experimental results on three benchmark datasets, including ISPRS Vaihingen, ISPRS Potsdam, and DFC2018, show that the proposed method achieves the most outstanding performance compared with the state-of-the-art networks. The source codes are available at: https://github.com/xjh0929/2HEIGHT .
AbstractList	Height estimation from single remote sensing image is a challenging inherently ambiguous and technically ill-posed problem that we address in this study by resorting to deep learning approach. A spatial enhanced and multi-scale aggregated encoder-decoder network, SM-EDNet, is proposed, which takes a single image as input and produces an estimated height map as output. First, residual network (ResNet) is applied to extract low-level and deep features to cope with the heterogeneous characteristics of remote sensing scenes. Then, the multi-scale context information is aggregated through DenseASPP (Dense Atrous Spatial Pyramid Pooling) by extracting features from multiple dilated convolution layers. The skip connection is constructed by using the structure preserving model, DULR, to aggregate ResNet low-level features and multi-scale high-level features. The deformable convolution module is constructed to enhance the sensitivity to differences in geometric shapes of ground objects. For model training, three-layer deep supervision mechanism is designed to counteract the adverse effects of unstable gradients changes. Experimental results on three benchmark datasets, including ISPRS Vaihingen, ISPRS Potsdam, and DFC2018, show that the proposed method achieves the most outstanding performance compared with the state-of-the-art networks. The source codes are available at: https://github.com/xjh0929/2HEIGHT . Height estimation from single remote sensing image is a challenging inherently ambiguous and technically ill-posed problem that we address in this study by resorting to deep learning approach. A spatial enhanced and multi-scale aggregated encoder-decoder network, SM-EDNet, is proposed, which takes a single image as input and produces an estimated height map as output. First, residual network (ResNet) is applied to extract low-level and deep features to cope with the heterogeneous characteristics of remote sensing scenes. Then, the multi-scale context information is aggregated through DenseASPP (Dense Atrous Spatial Pyramid Pooling) by extracting features from multiple dilated convolution layers. The skip connection is constructed by using the structure preserving model, DULR, to aggregate ResNet low-level features and multi-scale high-level features. The deformable convolution module is constructed to enhance the sensitivity to differences in geometric shapes of ground objects. For model training, three-layer deep supervision mechanism is designed to counteract the adverse effects of unstable gradients changes. Experimental results on three benchmark datasets, including ISPRS Vaihingen, ISPRS Potsdam, and DFC2018, show that the proposed method achieves the most outstanding performance compared with the state-of-the-art networks. The source codes are available at: https://github.com/xjh0929/2HEIGHT.
Author	Du, Shihong Xiao, Xiongwu Wang, Shaoyu Du, Shouhang Cui, Ximin Li, Wei Xing, Jianghe
Author_xml	– sequence: 1 givenname: Shouhang surname: Du fullname: Du, Shouhang organization: Shanghai Surveying and Mapping Institute – sequence: 2 givenname: Jianghe surname: Xing fullname: Xing, Jianghe organization: China University of Mining and Technology (Beijing) – sequence: 3 givenname: Shihong surname: Du fullname: Du, Shihong email: dshgis@hotmail.com organization: Peking University – sequence: 4 givenname: Ximin surname: Cui fullname: Cui, Ximin organization: China University of Mining and Technology (Beijing) – sequence: 5 givenname: Xiongwu orcidid: 0000-0002-3035-7727 surname: Xiao fullname: Xiao, Xiongwu organization: Mapping and Remote Sensing, Wuhan University – sequence: 6 givenname: Wei surname: Li fullname: Li, Wei organization: China University of Mining and Technology (Beijing) – sequence: 7 givenname: Shaoyu surname: Wang fullname: Wang, Shaoyu organization: China University of Mining and Technology (Beijing)
BookMark	eNqFkUFv1DAQhS1UJLaFn4BkiUsvWTxO4njhAqrK7kpFXMrZcp3xNsWxt7bTqv8eZ7dceiinGY2-N9J775Sc-OCRkI_AlsAk-8ygqQEELDnj9ZLzFkC2b8gCaiGqdsXghCxmppqhd-Q0pTvGmOjabkHutz_XfHO5XW-uv9BbHHa3mWLKw6jzEDy1MYw0DX7nkEYcQ0aa0M8HWpAd0umwa9oj7qkJ_iG4aVZqR9Gb0GOsejxM6jE_hvjnPXlrtUv44Xmekd8_Lq8vNtXVr_X24vtVZeoOciVk20nbM2O5Nh0Y7EBIw7iVom9uVlabsmoOwggUaK1pOZhiizfsBkRj6zNyfvy7j-F-Kp7UOCSDzmmPYUqqZg2rpVyxpqCfXqB3YYrFQ1JcdrCSAC0rVHukTAwpRbRqH0sI8UkBU3MR6l8Rai5CPRdRdF9f6MyQD_HmqAf3X_W3o3rwNsRRlwhdr7J-ciHaqL0ZipXXX_wFstGjNg
CitedBy_id	crossref_primary_10_1016_j_knosys_2024_111834 crossref_primary_10_1109_JSTARS_2024_3432200 crossref_primary_10_1016_j_isprsjprs_2025_07_010
Cites_doi	10.1016/j.isprsjprs.2016.07.006 10.3390/rs11192219 10.1109/ICMEW.2019.00-89 10.1609/aaai.v32i1.12301 10.1109/jstars.2013.2251457 10.1515/itms-2017-0003 10.1007/978-3-030-01234-2_49 10.1007/s12517-020-05602-5 10.1016/j.rse.2017.02.020 10.1109/jstars.2021.3073508 10.1109/CVPR.2016.90 10.1007/s11432-022-3599-y 10.1080/01431161.2022.2135410 10.1080/2150704x.2017.1335904 10.1016/j.isprsjprs.2022.08.008 10.3390/rs14092252 10.1109/lgrs.2018.2806945 10.3390/rs12172719 10.1109/IGARSS.2017.8128167 10.1109/lgrs.2020.2997295 10.1109/ICCV.2017.89 10.1016/j.cities.2020.103002 10.1016/j.rse.2013.05.019 10.1016/j.compenvurbsys.2018.09.004 10.1016/j.compag.2019.104903 10.1109/lgrs.2019.2947783 10.1016/j.rse.2021.112590 10.1109/lgrs.2021.3090470 10.3390/rs10121926 10.1109/JURSE.2019.8809037 10.1109/CVPR.2017.660 10.1007/978-3-319-24574-4_28 10.1080/22797254.2019.1622836 10.1016/j.patcog.2022.108549 10.1109/JURSE.2017.7924549 10.3390/s21072272 10.1109/CVPR.2018.00388 10.1016/j.rse.2020.111705 10.1016/j.isprsjprs.2019.01.013 10.1109/tgrs.2022.3176670
ContentType	Journal Article
Copyright	2023 Informa UK Limited, trading as Taylor & Francis Group 2023 2023 Informa UK Limited, trading as Taylor & Francis Group
Copyright_xml	– notice: 2023 Informa UK Limited, trading as Taylor & Francis Group 2023 – notice: 2023 Informa UK Limited, trading as Taylor & Francis Group
DBID	AAYXX CITATION 7TG 7TN 8FD F1W FR3 H8D H96 KL. KR7 L.G L7M 7S9 L.6
DOI	10.1080/01431161.2023.2251185
DatabaseName	CrossRef Meteorological & Geoastrophysical Abstracts Oceanic Abstracts Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Meteorological & Geoastrophysical Abstracts - Academic Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace AGRICOLA AGRICOLA - Academic
DatabaseTitle	CrossRef Aerospace Database Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Meteorological & Geoastrophysical Abstracts Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Oceanic Abstracts Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Meteorological & Geoastrophysical Abstracts - Academic AGRICOLA AGRICOLA - Academic
DatabaseTitleList	Aerospace Database AGRICOLA
DeliveryMethod	fulltext_linktorsrc
Discipline	Geography
EISSN	1366-5901
EndPage	5712
ExternalDocumentID	10_1080_01431161_2023_2251185 2251185
Genre	Research Article
GroupedDBID	-~X .7F .DC .QJ 0BK 0R~ 29J 30N 4.4 5GY 5VS AAENE AAGDL AAHBH AAHIA AAJMT AALDU AAMIU AAPUL AAQRR ABCCY ABFIM ABHAV ABJNI ABLIJ ABLJU ABPAQ ABPEM ABRLO ABUFD ABXUL ABXYU ACGEJ ACGFS ACIWK ACTIO ADCVX ADGTB ADXPE AEISY AENEX AEOZL AEPSL AEXLP AEYOC AFKVX AFRVT AGDLA AGMYJ AHDZW AIJEM AIYEW AJWEG AKBVH AKOOK ALMA_UNASSIGNED_HOLDINGS ALQZU AQRUH AQTUD AVBZW AWYRJ BLEHA CCCUG CE4 CS3 DGEBU DKSSO DU5 EBS E~A E~B F5P H13 HF~ IPNFZ J.P KYCEM LJTGL M4Z P2P RIG RNANH ROSJB RTWRZ S-T SNACF TASJS TBQAZ TDBHL TEN TFL TFT TFW TN5 TNC TQWBC TTHFI TUROJ TWF UPT UT5 UU3 ZGOLN ~02 ~S~ AAYXX CITATION 7TG 7TN 8FD F1W FR3 H8D H96 KL. KR7 L.G L7M 7S9 L.6
ID	FETCH-LOGICAL-c371t-68578fd0cf2ac71ce7168c02f86d4b9fac2f8a216c6e6effc521c000240b164f3
IEDL.DBID	TFW
ISICitedReferencesCount	5
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001093048100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0143-1161 1366-5901
IngestDate	Fri Sep 05 17:33:22 EDT 2025 Wed Aug 13 07:34:36 EDT 2025 Tue Nov 18 21:36:20 EST 2025 Sat Nov 29 06:13:49 EST 2025 Mon Oct 20 23:45:14 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	18
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c371t-68578fd0cf2ac71ce7168c02f86d4b9fac2f8a216c6e6effc521c000240b164f3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-3035-7727
PQID	2871981150
PQPubID	2045515
PageCount	27
ParticipantIDs	proquest_miscellaneous_3040388904 crossref_citationtrail_10_1080_01431161_2023_2251185 informaworld_taylorfrancis_310_1080_01431161_2023_2251185 crossref_primary_10_1080_01431161_2023_2251185 proquest_journals_2871981150
PublicationCentury	2000
PublicationDate	2023-09-17
PublicationDateYYYYMMDD	2023-09-17
PublicationDate_xml	– month: 09 year: 2023 text: 2023-09-17 day: 17
PublicationDecade	2020
PublicationPlace	London
PublicationPlace_xml	– name: London
PublicationTitle	International journal of remote sensing
PublicationYear	2023
Publisher	Taylor & Francis Taylor & Francis Ltd
Publisher_xml	– name: Taylor & Francis – name: Taylor & Francis Ltd
References	e_1_3_3_30_1 Mou L. (e_1_3_3_23_1) 2018 e_1_3_3_18_1 e_1_3_3_17_1 e_1_3_3_39_1 e_1_3_3_19_1 Chen L. C. (e_1_3_3_9_1) 2017 e_1_3_3_14_1 e_1_3_3_37_1 e_1_3_3_13_1 e_1_3_3_38_1 e_1_3_3_16_1 e_1_3_3_35_1 e_1_3_3_15_1 e_1_3_3_36_1 e_1_3_3_10_1 e_1_3_3_33_1 e_1_3_3_34_1 e_1_3_3_12_1 e_1_3_3_31_1 e_1_3_3_11_1 e_1_3_3_32_1 e_1_3_3_40_1 e_1_3_3_41_1 e_1_3_3_7_1 e_1_3_3_6_1 e_1_3_3_8_1 e_1_3_3_29_1 e_1_3_3_28_1 e_1_3_3_25_1 e_1_3_3_24_1 e_1_3_3_27_1 e_1_3_3_26_1 e_1_3_3_3_1 e_1_3_3_21_1 e_1_3_3_2_1 e_1_3_3_20_1 e_1_3_3_5_1 e_1_3_3_42_1 e_1_3_3_4_1 e_1_3_3_22_1 e_1_3_3_43_1
References_xml	– year: 2017 ident: e_1_3_3_9_1 article-title: Rethinking Atrous Convolution for Semantic Image Segmentation publication-title: arXiv: 1706.05587 – ident: e_1_3_3_16_1 doi: 10.1016/j.isprsjprs.2016.07.006 – ident: e_1_3_3_2_1 doi: 10.3390/rs11192219 – ident: e_1_3_3_41_1 doi: 10.1109/ICMEW.2019.00-89 – ident: e_1_3_3_25_1 doi: 10.1609/aaai.v32i1.12301 – ident: e_1_3_3_33_1 doi: 10.1109/jstars.2013.2251457 – ident: e_1_3_3_27_1 doi: 10.1515/itms-2017-0003 – ident: e_1_3_3_10_1 doi: 10.1007/978-3-030-01234-2_49 – ident: e_1_3_3_29_1 doi: 10.1007/s12517-020-05602-5 – ident: e_1_3_3_4_1 doi: 10.1016/j.rse.2017.02.020 – ident: e_1_3_3_12_1 doi: 10.1109/jstars.2021.3073508 – ident: e_1_3_3_15_1 doi: 10.1109/CVPR.2016.90 – ident: e_1_3_3_17_1 doi: 10.1007/s11432-022-3599-y – ident: e_1_3_3_42_1 doi: 10.1080/01431161.2022.2135410 – ident: e_1_3_3_18_1 doi: 10.1080/2150704x.2017.1335904 – ident: e_1_3_3_20_1 doi: 10.1016/j.isprsjprs.2022.08.008 – ident: e_1_3_3_38_1 doi: 10.3390/rs14092252 – ident: e_1_3_3_14_1 doi: 10.1109/lgrs.2018.2806945 – ident: e_1_3_3_19_1 doi: 10.3390/rs12172719 – year: 2018 ident: e_1_3_3_23_1 article-title: IM2HEIGHT: Height Estimation from Single Monocular Imagery via Fully Residual Convolutional-Deconvolutional Network publication-title: arXiv:1802.10249 – ident: e_1_3_3_31_1 doi: 10.1109/IGARSS.2017.8128167 – ident: e_1_3_3_26_1 doi: 10.1109/lgrs.2020.2997295 – ident: e_1_3_3_11_1 doi: 10.1109/ICCV.2017.89 – ident: e_1_3_3_30_1 doi: 10.1016/j.cities.2020.103002 – ident: e_1_3_3_35_1 doi: 10.1016/j.rse.2013.05.019 – ident: e_1_3_3_6_1 doi: 10.1016/j.compenvurbsys.2018.09.004 – ident: e_1_3_3_24_1 doi: 10.1016/j.compag.2019.104903 – ident: e_1_3_3_8_1 doi: 10.1109/lgrs.2019.2947783 – ident: e_1_3_3_7_1 doi: 10.1016/j.rse.2021.112590 – ident: e_1_3_3_37_1 doi: 10.1109/lgrs.2021.3090470 – ident: e_1_3_3_5_1 doi: 10.3390/rs10121926 – ident: e_1_3_3_32_1 doi: 10.1109/JURSE.2019.8809037 – ident: e_1_3_3_43_1 doi: 10.1109/CVPR.2017.660 – ident: e_1_3_3_28_1 doi: 10.1007/978-3-319-24574-4_28 – ident: e_1_3_3_36_1 doi: 10.1080/22797254.2019.1622836 – ident: e_1_3_3_39_1 doi: 10.1016/j.patcog.2022.108549 – ident: e_1_3_3_34_1 doi: 10.1109/JURSE.2017.7924549 – ident: e_1_3_3_13_1 doi: 10.3390/s21072272 – ident: e_1_3_3_40_1 doi: 10.1109/CVPR.2018.00388 – ident: e_1_3_3_21_1 doi: 10.1016/j.rse.2020.111705 – ident: e_1_3_3_3_1 doi: 10.1016/j.isprsjprs.2019.01.013 – ident: e_1_3_3_22_1 doi: 10.1109/tgrs.2022.3176670
SSID	ssj0006757
Score	2.4431274
Snippet	Height estimation from single remote sensing image is a challenging inherently ambiguous and technically ill-posed problem that we address in this study by...
SourceID	proquest crossref informaworld
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	5686
SubjectTerms	Coders Convolution data collection deep supervision mechanism DenseASPP encoder-decoder network Encoders-Decoders Formability geometry Height height estimation Ill posed problems Remote sensing ResNet Sensitivity enhancement Single remote sensing image
Title	IMG2HEIGHT: height estimation from single remote sensing image using a deep convolutional encoder-decoder network
URI	https://www.tandfonline.com/doi/abs/10.1080/01431161.2023.2251185 https://www.proquest.com/docview/2871981150 https://www.proquest.com/docview/3040388904
Volume	44
WOSCitedRecordID	wos001093048100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAWR databaseName: Taylor & Francis Online Journals customDbUrl: eissn: 1366-5901 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0006757 issn: 0143-1161 databaseCode: TFW dateStart: 19800101 isFulltext: true titleUrlDefault: https://www.tandfonline.com providerName: Taylor & Francis
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3dS8MwEA8igr74LU6nRPC1s-26NvFNZF-gw4epeytpetmE0c11E_zvzaXpcIjsQZ-afiQpSe5yd7n7HSHXKXAGLvcdhef_AbDEEaEvHY42p1CzQ2XiK14eol6PDQb8yXoT5tatEnVoVQBFGF6NxC2SvPSIu0FIOk9LKjVM_V3zjZCMYeb4WK_ofut1yYu1OFwETCMQp65SxvD81srK7rSCXfqDV5sNqLX3D7--T3at9EnviuVyQDYgOyTbNhH66POIvHcf236n2W13-rd0ZMymFHE4igBHisEoFK0LY6Az0LMMNEcP-GxI9SdDoAtTFjQFmFL0aLcrW3eKiJkpzJwUzJVmhQP6MXluNfv3HcdmZXBkPfLmTsg0kavUlcoXMvIkaI2LSddXLEyDhCshdVH4XihDCEEpqQUE6RostUTrZqp-QjazSQanhOKpJ3CeKEijQHgehwhkI1IN1JR9EVZIUM5GLC1kOWbOGMdeiWxqxzPG8YzteFZIbVltWmB2rKvAv091PDfGElVkNonra-pWy3URW_LPY1RDOUNhu0Kulq814eJpjMhgstDNavZZZ4y7wdkfuj8nO3iLHixeVCWb89kCLsiW_Ji_5bNLQwxfrO8DcQ
linkProvider	Taylor & Francis
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT8MwDLZgIMGFN2IwIEhcO9quaxNuCDE2MXYasFvUpc6GNBXYA4l_T5y20xBCHODUSK2TKnEc27E_A5wnKDi6wnc03f8HyPtOHPrKEeRzCo041Da_4rEddTq81xOLuTAUVkk2tM6AIqysps1NzugiJO6CMOk8o6pUqfZ31bdacn0ZVmx1OsPT3cbTXBobhThLmSYoTkNTZPH81M2X8-kLeuk3aW2PoMbmf_z8FmzkCii7yjhmG5Yw3YG1vBb68GMX3lr3t37zpnXb7F6yofWcMoLiyHIcGeWjMHIwjJCN0Sw0sgkFwacDZj4ZIJvZdswSxFdGQe05c5tBCTQzwbGToH2yNItB34OHxk33uunkhRkcVYu8qRNys8914irtxyryFBqjiyvX1zxMgr7QsTLN2PdCFWKIWiujIyjXwqn1jXmma_tQSl9SPABGF58oRF9jEgWx5wmMUNUjXSdj2Y_DMgTFckiVo5ZT8YyR9Apw03w-Jc2nzOezDNU52WsG2_EbgVhcazm1_hKdFTeRtV9oKwVjyFwCTCRZooKTvl2Gs_lrs3fpQiZO8WVmujUStMa5cIPDPwx_CmvN7n1btluduyNYp1cU0OJFFShNxzM8hlX1Pn2ejE_szvgELWsHnw
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT8MwDLZ4CbjwRoxnkLh2tF3XJtwQMDYBE4fxuEVd6gASKmMPJP49cZpOIIQ4wKmRWidVEju2Y38GOMhQcPRF6Gm6_4-Qd700DpUnyOcUG3GobX7F7WXSbvP7e3HtogkHLqySbGhdAEVYWU3M3ct0GRF3SJB0gdFUqlT6uxpaJbk-CdPGtqhTVFencTcWxkYfLjKmCYnT0JRJPD918-V4-gJe-k1Y2xOosfgP_74EC079ZMfFflmGCcxXYM5VQn98X4XX1tV52DxrnTc7R-zR-k0ZAXEUGY6MslEYuReekfXRLDOyAYXA5w_MfPKAbGTbKcsQe4xC2t3WNoMSZGaGfS9D-2R5EYG-BjeNs85J03NlGTxVS4KhF3PD5TrzlQ5TlQQKjcnFlR9qHmdRV-hUmWYaBrGKMUatldEQlG_B1LrGONO1dZjKX3LcAEbXnihEV2OWRGkQCExQ1RNdJ1M5TOMKROVqSOUwy6l0xrMMSmhTN5-S5lO6-axAdUzWK0A7fiMQn5daDq23RBelTWTtF9rtcl9Ix_8DSXao4KRtV2B__NpwLl3HpDm-jEy3Rn7WOBd-tPmH4fdg9vq0IS9b7YstmKc3FM0SJNswNeyPcAdm1NvwadDftXzxAdYKBkM
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=IMG2HEIGHT%3A+height+estimation+from+single+remote+sensing+image+using+a+deep+convolutional+encoder-decoder+network&rft.jtitle=International+journal+of+remote+sensing&rft.au=Du%2C+Shouhang&rft.au=Xing%2C+Jianghe&rft.au=Du%2C+Shihong&rft.au=Cui%2C+Ximin&rft.date=2023-09-17&rft.issn=0143-1161&rft.eissn=1366-5901&rft.volume=44&rft.issue=18&rft.spage=5686&rft.epage=5712&rft_id=info:doi/10.1080%2F01431161.2023.2251185&rft.externalDBID=n%2Fa&rft.externalDocID=10_1080_01431161_2023_2251185
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0143-1161&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0143-1161&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0143-1161&client=summon