Robust unsupervised small area change detection from SAR imagery using deep learning
[Display omitted] •A multiscale superpixel reconstruction method was developed to generate the Difference Image.•A two-stage center-constrained FCM algorithm was designed to deal with imbalanced data clustering.•CWNN combined with DCGAN was adopted to classify hard pixels. Small area change detectio...
Uloženo v:
| Vydáno v: | ISPRS journal of photogrammetry and remote sensing Ročník 173; s. 79 - 94 |
|---|---|
| Hlavní autoři: | , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
01.03.2021
|
| Témata: | |
| ISSN: | 0924-2716, 1872-8235 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | [Display omitted]
•A multiscale superpixel reconstruction method was developed to generate the Difference Image.•A two-stage center-constrained FCM algorithm was designed to deal with imbalanced data clustering.•CWNN combined with DCGAN was adopted to classify hard pixels.
Small area change detection using synthetic aperture radar (SAR) imagery is a highly challenging task, due to speckle noise and imbalance between classes (changed and unchanged). In this paper, a robust unsupervised approach is proposed for small area change detection using deep learning techniques. First, a multi-scale superpixel reconstruction method is developed to generate a difference image (DI), which can suppress the speckle noise effectively and enhance edges by exploiting local, spatially homogeneous information. Second, a two-stage centre-constrained fuzzy c-means clustering algorithm is proposed to divide the pixels of the DI into changed, unchanged and intermediate classes with a parallel clustering strategy. Image patches belonging to the first two classes are then constructed as pseudo-label training samples, and image patches of the intermediate class are treated as testing samples. Finally, a convolutional wavelet neural network (CWNN) is designed and trained to classify testing samples into changed or unchanged classes, coupled with a deep convolutional generative adversarial network (DCGAN) to increase the number of changed class within the pseudo-label training samples. Numerical experiments on four real SAR datasets demonstrate the validity and robustness of the proposed approach, achieving up to 99.61% accuracy for small area change detection. |
|---|---|
| AbstractList | [Display omitted]
•A multiscale superpixel reconstruction method was developed to generate the Difference Image.•A two-stage center-constrained FCM algorithm was designed to deal with imbalanced data clustering.•CWNN combined with DCGAN was adopted to classify hard pixels.
Small area change detection using synthetic aperture radar (SAR) imagery is a highly challenging task, due to speckle noise and imbalance between classes (changed and unchanged). In this paper, a robust unsupervised approach is proposed for small area change detection using deep learning techniques. First, a multi-scale superpixel reconstruction method is developed to generate a difference image (DI), which can suppress the speckle noise effectively and enhance edges by exploiting local, spatially homogeneous information. Second, a two-stage centre-constrained fuzzy c-means clustering algorithm is proposed to divide the pixels of the DI into changed, unchanged and intermediate classes with a parallel clustering strategy. Image patches belonging to the first two classes are then constructed as pseudo-label training samples, and image patches of the intermediate class are treated as testing samples. Finally, a convolutional wavelet neural network (CWNN) is designed and trained to classify testing samples into changed or unchanged classes, coupled with a deep convolutional generative adversarial network (DCGAN) to increase the number of changed class within the pseudo-label training samples. Numerical experiments on four real SAR datasets demonstrate the validity and robustness of the proposed approach, achieving up to 99.61% accuracy for small area change detection. Small area change detection using synthetic aperture radar (SAR) imagery is a highly challenging task, due to speckle noise and imbalance between classes (changed and unchanged). In this paper, a robust unsupervised approach is proposed for small area change detection using deep learning techniques. First, a multi-scale superpixel reconstruction method is developed to generate a difference image (DI), which can suppress the speckle noise effectively and enhance edges by exploiting local, spatially homogeneous information. Second, a two-stage centre-constrained fuzzy c-means clustering algorithm is proposed to divide the pixels of the DI into changed, unchanged and intermediate classes with a parallel clustering strategy. Image patches belonging to the first two classes are then constructed as pseudo-label training samples, and image patches of the intermediate class are treated as testing samples. Finally, a convolutional wavelet neural network (CWNN) is designed and trained to classify testing samples into changed or unchanged classes, coupled with a deep convolutional generative adversarial network (DCGAN) to increase the number of changed class within the pseudo-label training samples. Numerical experiments on four real SAR datasets demonstrate the validity and robustness of the proposed approach, achieving up to 99.61% accuracy for small area change detection. |
| Author | Zhang, Xinzheng Zhang, Ce Gu, Xiaowei Tan, Xiaoheng Su, Hang Atkinson, Peter M. |
| Author_xml | – sequence: 1 givenname: Xinzheng surname: Zhang fullname: Zhang, Xinzheng email: zhangxinzheng03@126.com organization: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China – sequence: 2 givenname: Hang surname: Su fullname: Su, Hang organization: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China – sequence: 3 givenname: Ce surname: Zhang fullname: Zhang, Ce email: c.zhang9@lancaster.ac.uk organization: Lancaster Environment Centre, Lancaster University, Lancaster LA1 4YQ, United Kingdom – sequence: 4 givenname: Xiaowei surname: Gu fullname: Gu, Xiaowei organization: Department of Computer Science, Aberystwyth University, Aberystwyth SY23 3DB, United Kingdom – sequence: 5 givenname: Xiaoheng surname: Tan fullname: Tan, Xiaoheng organization: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China – sequence: 6 givenname: Peter M. surname: Atkinson fullname: Atkinson, Peter M. organization: Lancaster Environment Centre, Lancaster University, Lancaster LA1 4YQ, United Kingdom |
| BookMark | eNqNkEtLAzEUhYMo2FZ_g1m6mZrHmMfCRSm-QBB8rEMmc6emTDNjMlPovzel4sKNwrlcLpxz4H5TdBy6AAhdUDKnhIqr9dynPqZ1njkjjM5JFimP0IQqyQrF-PUxmhDNyoJJKk7RNKU1IYReCzVBby9dNaYBjyGNPcStT1DjtLFti20Ei92HDSvANQzgBt8F3MRug18XL9hv7AriDo_Jh1U2QI9bsDHk6wydNLZNcP69Z-j97vZt-VA8Pd8_LhdPheNaDgUVUjPleEUE1bWsLedKEFoyyStKS8qbUkBjHa9lIyzVjRJSaV3VDpSGivIZujz09rH7HCENZuOTg7a1AboxGaaVKEtNlMjWm4PVxS6lCI1xfrD7j4ZofWsoMXuaZm1-aJo9TUOySJnz8le-j5lA3P0juTgkIZPYeogmOQ_BQe1jZmrqzv_Z8QWwTZf4 |
| CitedBy_id | crossref_primary_10_3390_rs15071724 crossref_primary_10_1109_TGRS_2025_3591814 crossref_primary_10_1016_j_jag_2024_103725 crossref_primary_10_1016_j_rse_2023_113821 crossref_primary_10_1016_j_ecolind_2022_108999 crossref_primary_10_3390_agronomy15040873 crossref_primary_10_3390_rs16050799 crossref_primary_10_1016_j_knosys_2025_113135 crossref_primary_10_1080_01431161_2024_2365818 crossref_primary_10_1016_j_isprsjprs_2022_01_004 crossref_primary_10_3390_rs17050840 crossref_primary_10_1016_j_isprsjprs_2022_09_006 crossref_primary_10_3390_rs14153604 crossref_primary_10_1080_01431161_2025_2505257 crossref_primary_10_1080_01431161_2023_2273245 crossref_primary_10_1016_j_jag_2023_103511 crossref_primary_10_1109_TGRS_2024_3407088 crossref_primary_10_1016_j_isprsjprs_2021_05_019 crossref_primary_10_1016_j_isprsjprs_2024_01_002 crossref_primary_10_1016_j_ecoinf_2023_102019 crossref_primary_10_1109_JSTARS_2024_3406421 crossref_primary_10_3390_rs14246362 crossref_primary_10_1117_1_JRS_18_016503 crossref_primary_10_1016_j_displa_2024_102840 crossref_primary_10_3390_rs15051194 crossref_primary_10_1109_JSTARS_2022_3199017 crossref_primary_10_1109_TGRS_2023_3294884 crossref_primary_10_23919_JSEE_2022_000087 crossref_primary_10_1109_TGRS_2022_3190977 crossref_primary_10_1016_j_rse_2023_113801 crossref_primary_10_1109_LGRS_2022_3222794 crossref_primary_10_1016_j_jag_2022_102734 crossref_primary_10_1109_TGRS_2024_3367970 crossref_primary_10_1016_j_jag_2025_104550 crossref_primary_10_3390_rs15020470 crossref_primary_10_1109_JSTARS_2022_3184355 crossref_primary_10_1109_JSTARS_2023_3333959 crossref_primary_10_1109_LGRS_2021_3110302 crossref_primary_10_1109_TGRS_2021_3110998 crossref_primary_10_1109_TGRS_2025_3598588 crossref_primary_10_1016_j_knosys_2023_110281 crossref_primary_10_1109_JSTARS_2022_3187108 crossref_primary_10_1016_j_ophoto_2023_100044 crossref_primary_10_14358_PERS_22_00108R2 crossref_primary_10_1109_JSTARS_2025_3557434 crossref_primary_10_1007_s00521_023_09377_0 crossref_primary_10_1109_TGRS_2025_3584073 crossref_primary_10_1109_ACCESS_2023_3307208 crossref_primary_10_1109_TGRS_2025_3584650 crossref_primary_10_1109_JSEN_2024_3432143 crossref_primary_10_3390_rs16030560 crossref_primary_10_1109_TGRS_2023_3344062 crossref_primary_10_1080_01431161_2025_2516691 crossref_primary_10_1016_j_neucom_2023_126611 crossref_primary_10_1109_LGRS_2024_3415819 crossref_primary_10_1117_1_JRS_18_024501 |
| Cites_doi | 10.1109/LGRS.2009.2025059 10.1109/LGRS.2011.2167211 10.3390/rs10081295 10.1109/LGRS.2016.2550666 10.1109/LGRS.2019.2895656 10.1109/TNNLS.2015.2435783 10.1016/j.rse.2013.08.050 10.1016/j.asoc.2018.07.021 10.1109/TGRS.2014.2352555 10.1016/j.isprsjprs.2020.06.020 10.1109/TGRS.2019.2901945 10.1109/LGRS.2019.2939208 10.1186/s40537-019-0197-0 10.1016/j.isprsjprs.2020.04.007 10.1109/JSTARS.2016.2547638 10.1109/LGRS.2013.2275738 10.1016/j.neucom.2018.09.013 10.1109/ACCESS.2019.2902613 10.1016/j.isprsjprs.2019.12.002 10.1016/j.asoc.2020.106510 10.1109/LGRS.2015.2484220 10.1109/TGRS.2007.893568 10.1016/j.isprsjprs.2017.05.001 10.1117/1.JRS.10.046019 10.1109/TIP.2011.2170702 10.3390/rs12121978 10.1016/j.patcog.2016.07.040 10.1109/TGRS.2009.2038274 10.1109/TPAMI.2012.120 10.1109/TGRS.2019.2913095 10.1109/LGRS.2019.2922198 10.3390/rs11091091 10.1016/j.patcog.2016.11.015 10.1109/LGRS.2018.2876616 10.1016/j.ins.2018.08.015 10.1109/TIP.2010.2040763 10.1109/LGRS.2016.2611001 |
| ContentType | Journal Article |
| Copyright | 2021 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS) |
| Copyright_xml | – notice: 2021 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS) |
| DBID | AAYXX CITATION 7S9 L.6 |
| DOI | 10.1016/j.isprsjprs.2021.01.004 |
| DatabaseName | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitle | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | AGRICOLA |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Geography Engineering |
| EISSN | 1872-8235 |
| EndPage | 94 |
| ExternalDocumentID | 10_1016_j_isprsjprs_2021_01_004 S0924271621000046 |
| GroupedDBID | --K --M .~1 0R~ 1B1 1RT 1~. 1~5 29J 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AACTN AAEDT AAEDW AAIAV AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABJNI ABMAC ABQEM ABQYD ABXDB ABYKQ ACDAQ ACGFS ACLVX ACNNM ACRLP ACSBN ACZNC ADBBV ADEZE ADJOM ADMUD AEBSH AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG ATOGT AVWKF AXJTR AZFZN BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA GBOLZ HMA HVGLF HZ~ H~9 IHE IMUCA J1W KOM LY3 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SDF SDG SEP SES SEW SPC SPCBC SSE SSV SSZ T5K T9H WUQ ZMT ~02 ~G- 9DU AAHBH AATTM AAXKI AAYWO AAYXX ABDPE ABUFD ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD 7S9 L.6 |
| ID | FETCH-LOGICAL-c397t-167928c3b0619d7da3386014273b11413f46efac3d7f6a19f867899bdce89eb13 |
| ISICitedReferencesCount | 58 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000640986100006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0924-2716 |
| IngestDate | Sun Sep 28 06:19:25 EDT 2025 Sat Nov 29 07:14:12 EST 2025 Tue Nov 18 21:19:34 EST 2025 Fri Feb 23 02:44:54 EST 2024 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Fuzzy c-means algorithm Change detection Synthetic aperture radar Difference image |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c397t-167928c3b0619d7da3386014273b11413f46efac3d7f6a19f867899bdce89eb13 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| OpenAccessLink | https://www.sciencedirect.com/science/article/pii/S0924271621000046 |
| PQID | 2986449086 |
| PQPubID | 24069 |
| PageCount | 16 |
| ParticipantIDs | proquest_miscellaneous_2986449086 crossref_citationtrail_10_1016_j_isprsjprs_2021_01_004 crossref_primary_10_1016_j_isprsjprs_2021_01_004 elsevier_sciencedirect_doi_10_1016_j_isprsjprs_2021_01_004 |
| PublicationCentury | 2000 |
| PublicationDate | March 2021 2021-03-00 20210301 |
| PublicationDateYYYYMMDD | 2021-03-01 |
| PublicationDate_xml | – month: 03 year: 2021 text: March 2021 |
| PublicationDecade | 2020 |
| PublicationTitle | ISPRS journal of photogrammetry and remote sensing |
| PublicationYear | 2021 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Cao, Du, Zhao, Hu, Mo, Chen, Cai, Peng, Zhang (b0015) 2020; 167 Zhuang, Tan, Deng, Yao (b0215) 2020; 17 Pantze, Santoro, Fransson (b0160) 2014; 155 arXiv preprint arXiv:1511.06434. Zheng, Zhang, Hou, Liu (b0205) 2014; 11 Gong, Zhao, Liu, Miao, Jiao (b0080) 2016; 27 Kim, Lee (b0115) 2020; 12 Gao, Wang, Gao, Dong, Wang (b0055) 2019; 16 Gong, Yang, Zhang (b0075) 2017; 129 Gong, Cao, Wu (b0070) 2012; 9 Frid-Adar, Diamant, Klang, Amitai, Goldberger, Greenspan (b0040) 2018; 321 Inglada, Mercier (b0100) 2007; 45 Tian, Gong (b0185) 2018; 467 Kalaiselvi, Gomathi (b0110) 2020; 95 Saha, Bovolo, Bruzzone (b0170) 2020 Geng, Ma, Zhou, Wang (b0060) 2019; 57 Huang, Cai, Chen, Liu (b0095) 2011; 13 Deledalle, Denis, Tupin, Reigber, Jager (b0030) 2015; 53 Brunner, Lemoine, Bruzzone (b0010) 2010; 48 Shorten, Khoshgoftaar (b0175) 2019; 6 Li, Peng, Chen, Jiao, Zhou, Shang (b0155) 2019; 57 Radford, A., Metz, L., Chintala, S., 2015. Unsupervised representation learning with deep convolutional generative adversarial networks. Zheng, Jiao, Liu, Zhang, Hou, Wang (b0200) 2017; 61 Achanta, Shaji, Smith, Lucchi, Fua, Süsstrunk (b0005) 2012; 34 Krinidis, Chatzis (b0120) 2010; 19 Li, Li, Zhang, Wu, Song, An (b0150) 2019; 16 Jia, Li, Zhang, Wu, Zhu (b0105) 2016; 13 Duan, Liu, Jiao, Zhao, Zhang (b0035) 2017; 64 He, Bai, Garcia, Li (b0090) 2008 Cozzolino, Verdoliva, Scarpa, Poggi (b0025) 2020; 17 Gao, Dong, Li, Xu (b0045) 2016; 13 Gao, Dong, Li, Xu, Xie (b0050) 2016; 10 Celik (b0020) 2009; 6 Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair, Courville, Bengio (b0065) 2014 Li, Gong, Wang, Miao (b0130) 2018; 71 Sun, Zhang, Chen, Liu, Song (b0180) 2020; 17 Gong, Zhou, Ma (b0085) 2012; 21 . Wang, Jiao, Yang (b0195) 2016; 9 Lei, Liu, Shi, Lei, Wang (b0125) 2019; 7 Li, Yang, Yang, Du, Emery (b0140) 2020; 160 Li, Wang, Zhang, Zhang, Wu (b0145) 2019; 11 Wang, Yang, Yang, Jia, Fang (b0190) 2020; 164 Li, Celik, Longbotham, Emery (b0135) 2015; 12 Zhuang, Fan, Deng, Yao (b0210) 2018; 10 Li (10.1016/j.isprsjprs.2021.01.004_b0135) 2015; 12 He (10.1016/j.isprsjprs.2021.01.004_b0090) 2008 Kalaiselvi (10.1016/j.isprsjprs.2021.01.004_b0110) 2020; 95 Gong (10.1016/j.isprsjprs.2021.01.004_b0070) 2012; 9 Li (10.1016/j.isprsjprs.2021.01.004_b0130) 2018; 71 Sun (10.1016/j.isprsjprs.2021.01.004_b0180) 2020; 17 Wang (10.1016/j.isprsjprs.2021.01.004_b0195) 2016; 9 Zhuang (10.1016/j.isprsjprs.2021.01.004_b0215) 2020; 17 Frid-Adar (10.1016/j.isprsjprs.2021.01.004_b0040) 2018; 321 Tian (10.1016/j.isprsjprs.2021.01.004_b0185) 2018; 467 Wang (10.1016/j.isprsjprs.2021.01.004_b0190) 2020; 164 Zheng (10.1016/j.isprsjprs.2021.01.004_b0200) 2017; 61 Cozzolino (10.1016/j.isprsjprs.2021.01.004_b0025) 2020; 17 Lei (10.1016/j.isprsjprs.2021.01.004_b0125) 2019; 7 Huang (10.1016/j.isprsjprs.2021.01.004_b0095) 2011; 13 Gong (10.1016/j.isprsjprs.2021.01.004_b0080) 2016; 27 Gong (10.1016/j.isprsjprs.2021.01.004_b0085) 2012; 21 Inglada (10.1016/j.isprsjprs.2021.01.004_b0100) 2007; 45 Krinidis (10.1016/j.isprsjprs.2021.01.004_b0120) 2010; 19 Duan (10.1016/j.isprsjprs.2021.01.004_b0035) 2017; 64 Brunner (10.1016/j.isprsjprs.2021.01.004_b0010) 2010; 48 Deledalle (10.1016/j.isprsjprs.2021.01.004_b0030) 2015; 53 Geng (10.1016/j.isprsjprs.2021.01.004_b0060) 2019; 57 Achanta (10.1016/j.isprsjprs.2021.01.004_b0005) 2012; 34 Saha (10.1016/j.isprsjprs.2021.01.004_b0170) 2020 Gao (10.1016/j.isprsjprs.2021.01.004_b0055) 2019; 16 Kim (10.1016/j.isprsjprs.2021.01.004_b0115) 2020; 12 Li (10.1016/j.isprsjprs.2021.01.004_b0150) 2019; 16 Li (10.1016/j.isprsjprs.2021.01.004_b0155) 2019; 57 Goodfellow (10.1016/j.isprsjprs.2021.01.004_b0065) 2014 Zhuang (10.1016/j.isprsjprs.2021.01.004_b0210) 2018; 10 Gao (10.1016/j.isprsjprs.2021.01.004_b0045) 2016; 13 Gong (10.1016/j.isprsjprs.2021.01.004_b0075) 2017; 129 Celik (10.1016/j.isprsjprs.2021.01.004_b0020) 2009; 6 10.1016/j.isprsjprs.2021.01.004_b0165 Zheng (10.1016/j.isprsjprs.2021.01.004_b0205) 2014; 11 Gao (10.1016/j.isprsjprs.2021.01.004_b0050) 2016; 10 Li (10.1016/j.isprsjprs.2021.01.004_b0140) 2020; 160 Pantze (10.1016/j.isprsjprs.2021.01.004_b0160) 2014; 155 Shorten (10.1016/j.isprsjprs.2021.01.004_b0175) 2019; 6 Li (10.1016/j.isprsjprs.2021.01.004_b0145) 2019; 11 Jia (10.1016/j.isprsjprs.2021.01.004_b0105) 2016; 13 Cao (10.1016/j.isprsjprs.2021.01.004_b0015) 2020; 167 |
| References_xml | – volume: 45 start-page: 1432 year: 2007 end-page: 1445 ident: b0100 article-title: A new statistical similarity measure for change detection in multitemporal SAR images and its extension to multiscale change analysis publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 160 start-page: 167 year: 2020 end-page: 179 ident: b0140 article-title: Deep nonsmooth nonnegative matrix factorization network factorization network with semi-supervised learning for SAR image change detection publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 11 start-page: 1091 year: 2019 ident: b0145 article-title: Urban building change detection in SAR images using combined differential image and residual U-Net network publication-title: Remote Sens. – volume: 71 start-page: 698 year: 2018 end-page: 714 ident: b0130 article-title: Self-paced stacked denoising autoencoders based on differential evolution for change detection publication-title: Appl. Soft Comput. – volume: 16 start-page: 1240 year: 2019 end-page: 1244 ident: b0055 article-title: Sea ice change detection in SAR images based on convolutional-wavelet neural networks publication-title: IEEE Geosci. Remote Sens. Lett. – reference: Radford, A., Metz, L., Chintala, S., 2015. Unsupervised representation learning with deep convolutional generative adversarial networks. – year: 2020 ident: b0170 article-title: Building change detection in VHR SAR images via unsupervised deep tanscoding publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 34 start-page: 2274 year: 2012 end-page: 2282 ident: b0005 article-title: SLIC superpixels compared to state-of-the-art superpixel methods publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 1322 year: 2008 end-page: 1328 ident: b0090 article-title: ADASYN: Adaptive synthetic sampling approach for imbalanced learning publication-title: Proc. Int’l Joint Conf. Neural Netw. – volume: 6 year: 2019 ident: b0175 article-title: A survey on image data augmentation for deep learning publication-title: J. Big Data – volume: 64 start-page: 255 year: 2017 end-page: 267 ident: b0035 article-title: SAR Image segmentation based on convolutional-wavelet neural network and markov random field publication-title: Pattern Recognit. – volume: 129 start-page: 212 year: 2017 end-page: 225 ident: b0075 article-title: Feature learning and change feature classification based on deep learning for ternary change detection in SAR images publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 27 start-page: 125 year: 2016 end-page: 138 ident: b0080 article-title: Change detection in synthetic aperture radar images based on deep neural networks publication-title: IEEE Trans. Neural Netw. Learning Syst. – volume: 17 start-page: 1097 year: 2020 end-page: 1101 ident: b0180 article-title: Frost filtering algorithm of SAR images with adaptive windowing and adaptive tuning factor publication-title: IEEE Geosci. Remote Sens. Lett. – volume: 53 start-page: 2021 year: 2015 end-page: 2038 ident: b0030 article-title: NL-SAR: A unified nonlocal framework for resolution-preserving (Pol)(In)SAR denoising publication-title: IEEE Trans. Geosci. Remote Sensing – volume: 48 start-page: 2403 year: 2010 end-page: 2420 ident: b0010 article-title: Earthquake damage assessment of buildings using VHR optical and SAR imagery publication-title: IEEE Trans. Geosci. Remote Sensing – volume: 57 start-page: 5751 year: 2019 end-page: 5763 ident: b0155 article-title: A deep learning method for change detection in synthetic aperture radar images publication-title: IEEE Trans. Geosci. Remote Sens. – reference: arXiv preprint arXiv:1511.06434. – volume: 10 start-page: 046019 year: 2016 ident: b0050 article-title: Change detection from synthetic aperture radar images based on neighborhood-based ratio and extreme learning machine publication-title: J. Appl. Remote Sens – volume: 9 start-page: 307 year: 2012 end-page: 311 ident: b0070 article-title: A neighborhood-based ratio approach for change detection in SAR images publication-title: IEEE Geosci. Remote Sensing Lett. – volume: 19 start-page: 1328 year: 2010 end-page: 1337 ident: b0120 article-title: A robust fuzzy local information c-means clustering algorithm publication-title: IEEE Trans. Image Process. – volume: 17 start-page: 1097 year: 2020 end-page: 1101 ident: b0025 article-title: Nonlocal CNN SAR image despeckling publication-title: Remote Sens. – volume: 12 start-page: 2458 year: 2015 end-page: 2462 ident: b0135 article-title: Gabor feature based unsupervised change detection of multitemporal SAR images based on two-level clustering publication-title: IEEE Geosci. Remote Sens. Lett. – volume: 16 start-page: 402 year: 2019 end-page: 406 ident: b0150 article-title: SAR image change detection using PCANet guided by saliency detecion publication-title: IEEE Geosci. Remote Sens. Lett. – volume: 21 start-page: 2141 year: 2012 end-page: 2151 ident: b0085 article-title: Change detection in synthetic aperture radar images based on image fusion and fuzzy clustering publication-title: IEEE Trans. Image Process. – volume: 13 start-page: 856 year: 2016 end-page: 860 ident: b0105 article-title: SAR image change detection based on multiple kernel k-means clustering with local-neighborhood information publication-title: IEEE Geosci. Remote Sens. Lett. – volume: 167 start-page: 54 year: 2020 end-page: 70 ident: b0015 article-title: Multi-level monitoring of three-dimensional building changes for megacities: Trajectory, morphology, and landscape publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 12 start-page: 1978 year: 2020 ident: b0115 article-title: Rapid change detection of flood affected area after collapse of the Laos Xe-Plain Xe-Namnoy dam using Sentinel GRD data publication-title: Remote Sens. – volume: 7 start-page: 36600 year: 2019 end-page: 36616 ident: b0125 article-title: Multiscale superpixel segmentation with deep features for change detection publication-title: IEEE Access. – volume: 11 start-page: 691 year: 2014 end-page: 695 ident: b0205 article-title: Using combined difference image and k-means clustering for SAR image change detection publication-title: IEEE Geosci. Remote Sens. Lett. – volume: 155 start-page: 120 year: 2014 end-page: 128 ident: b0160 article-title: Change detection of boreal forest using bi-temporal ALOS PALSAR backscatter data publication-title: Remote Sens. Environ. – volume: 10 start-page: 1295 year: 2018 ident: b0210 article-title: A spatial-temporal adaptive neighborhood-based ratio approach for change detection in SAR images publication-title: Remote Sens. – volume: 95 year: 2020 ident: b0110 article-title: α-cut induced fuzzy deep neural network for change detection of SAR images publication-title: Appl. Soft Comput. – volume: 13 start-page: 863 year: 2011 end-page: 872 ident: b0095 article-title: Change detection method based on fractal model and wavelet transform for multitemporal SAR images publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 17 start-page: 416 year: 2020 end-page: 420 ident: b0215 article-title: Adaptive generalized likelihood ratio test for change detection in SAR image publication-title: IEEE Geosci. Remote Sens. Lett. – start-page: 2672 year: 2014 end-page: 2680 ident: b0065 article-title: Generative adversarial nets publication-title: Proc. NIPS. – volume: 61 start-page: 309 year: 2017 end-page: 326 ident: b0200 article-title: Unsupervised saliency-guided SAR image change detection publication-title: Pattern Recognit. – volume: 164 start-page: 61 year: 2020 end-page: 72 ident: b0190 article-title: Unsupervised change detection between SAR images based on hypergraphs publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 9 start-page: 3452 year: 2016 end-page: 3466 ident: b0195 article-title: SAR Images Change detection based on spatial coding and nonlocal similarity pooling publication-title: IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. – volume: 321 start-page: 321 year: 2018 end-page: 331 ident: b0040 article-title: GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification publication-title: Neurocomputing – volume: 467 start-page: 415 year: 2018 end-page: 430 ident: b0185 article-title: A novel edge-weight based fuzzy clustering method for change detection in SAR images publication-title: Inf. Sci. – volume: 13 start-page: 1792 year: 2016 end-page: 1796 ident: b0045 article-title: Automatic change detection in synthetic aperture radar images based on PCANet publication-title: IEEE Geosci. Remote Sens. Lett. – reference: . – volume: 57 start-page: 7365 year: 2019 end-page: 7377 ident: b0060 article-title: Saliency-guided deep neural networks for SAR image change detection publication-title: IEEE Trans. Geosci. Remote Sensing – volume: 6 start-page: 772 year: 2009 end-page: 776 ident: b0020 article-title: Unsupervised change detection in satellite images using principal component analysis and k-means clustering publication-title: IEEE Geosci. Remote Sens. Lett. – volume: 6 start-page: 772 issue: 4 year: 2009 ident: 10.1016/j.isprsjprs.2021.01.004_b0020 article-title: Unsupervised change detection in satellite images using principal component analysis and k-means clustering publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2009.2025059 – volume: 9 start-page: 307 issue: 2 year: 2012 ident: 10.1016/j.isprsjprs.2021.01.004_b0070 article-title: A neighborhood-based ratio approach for change detection in SAR images publication-title: IEEE Geosci. Remote Sensing Lett. doi: 10.1109/LGRS.2011.2167211 – volume: 10 start-page: 1295 issue: 8 year: 2018 ident: 10.1016/j.isprsjprs.2021.01.004_b0210 article-title: A spatial-temporal adaptive neighborhood-based ratio approach for change detection in SAR images publication-title: Remote Sens. doi: 10.3390/rs10081295 – volume: 13 start-page: 856 issue: 6 year: 2016 ident: 10.1016/j.isprsjprs.2021.01.004_b0105 article-title: SAR image change detection based on multiple kernel k-means clustering with local-neighborhood information publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2016.2550666 – volume: 16 start-page: 1240 issue: 8 year: 2019 ident: 10.1016/j.isprsjprs.2021.01.004_b0055 article-title: Sea ice change detection in SAR images based on convolutional-wavelet neural networks publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2019.2895656 – volume: 27 start-page: 125 issue: 1 year: 2016 ident: 10.1016/j.isprsjprs.2021.01.004_b0080 article-title: Change detection in synthetic aperture radar images based on deep neural networks publication-title: IEEE Trans. Neural Netw. Learning Syst. doi: 10.1109/TNNLS.2015.2435783 – ident: 10.1016/j.isprsjprs.2021.01.004_b0165 – year: 2020 ident: 10.1016/j.isprsjprs.2021.01.004_b0170 article-title: Building change detection in VHR SAR images via unsupervised deep tanscoding publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 155 start-page: 120 year: 2014 ident: 10.1016/j.isprsjprs.2021.01.004_b0160 article-title: Change detection of boreal forest using bi-temporal ALOS PALSAR backscatter data publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2013.08.050 – volume: 71 start-page: 698 year: 2018 ident: 10.1016/j.isprsjprs.2021.01.004_b0130 article-title: Self-paced stacked denoising autoencoders based on differential evolution for change detection publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2018.07.021 – volume: 53 start-page: 2021 issue: 4 year: 2015 ident: 10.1016/j.isprsjprs.2021.01.004_b0030 article-title: NL-SAR: A unified nonlocal framework for resolution-preserving (Pol)(In)SAR denoising publication-title: IEEE Trans. Geosci. Remote Sensing doi: 10.1109/TGRS.2014.2352555 – volume: 167 start-page: 54 year: 2020 ident: 10.1016/j.isprsjprs.2021.01.004_b0015 article-title: Multi-level monitoring of three-dimensional building changes for megacities: Trajectory, morphology, and landscape publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2020.06.020 – volume: 57 start-page: 5751 issue: 8 year: 2019 ident: 10.1016/j.isprsjprs.2021.01.004_b0155 article-title: A deep learning method for change detection in synthetic aperture radar images publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2019.2901945 – start-page: 1322 year: 2008 ident: 10.1016/j.isprsjprs.2021.01.004_b0090 article-title: ADASYN: Adaptive synthetic sampling approach for imbalanced learning publication-title: Proc. Int’l Joint Conf. Neural Netw. – volume: 17 start-page: 1097 issue: 6 year: 2020 ident: 10.1016/j.isprsjprs.2021.01.004_b0180 article-title: Frost filtering algorithm of SAR images with adaptive windowing and adaptive tuning factor publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2019.2939208 – volume: 6 issue: 1 year: 2019 ident: 10.1016/j.isprsjprs.2021.01.004_b0175 article-title: A survey on image data augmentation for deep learning publication-title: J. Big Data doi: 10.1186/s40537-019-0197-0 – volume: 164 start-page: 61 year: 2020 ident: 10.1016/j.isprsjprs.2021.01.004_b0190 article-title: Unsupervised change detection between SAR images based on hypergraphs publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2020.04.007 – volume: 9 start-page: 3452 issue: 8 year: 2016 ident: 10.1016/j.isprsjprs.2021.01.004_b0195 article-title: SAR Images Change detection based on spatial coding and nonlocal similarity pooling publication-title: IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. doi: 10.1109/JSTARS.2016.2547638 – volume: 11 start-page: 691 issue: 3 year: 2014 ident: 10.1016/j.isprsjprs.2021.01.004_b0205 article-title: Using combined difference image and k-means clustering for SAR image change detection publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2013.2275738 – volume: 321 start-page: 321 year: 2018 ident: 10.1016/j.isprsjprs.2021.01.004_b0040 article-title: GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.09.013 – volume: 7 start-page: 36600 year: 2019 ident: 10.1016/j.isprsjprs.2021.01.004_b0125 article-title: Multiscale superpixel segmentation with deep features for change detection publication-title: IEEE Access. doi: 10.1109/ACCESS.2019.2902613 – volume: 17 start-page: 1097 issue: 6 year: 2020 ident: 10.1016/j.isprsjprs.2021.01.004_b0025 article-title: Nonlocal CNN SAR image despeckling publication-title: Remote Sens. – volume: 160 start-page: 167 year: 2020 ident: 10.1016/j.isprsjprs.2021.01.004_b0140 article-title: Deep nonsmooth nonnegative matrix factorization network factorization network with semi-supervised learning for SAR image change detection publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2019.12.002 – volume: 95 year: 2020 ident: 10.1016/j.isprsjprs.2021.01.004_b0110 article-title: α-cut induced fuzzy deep neural network for change detection of SAR images publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2020.106510 – volume: 12 start-page: 2458 issue: 12 year: 2015 ident: 10.1016/j.isprsjprs.2021.01.004_b0135 article-title: Gabor feature based unsupervised change detection of multitemporal SAR images based on two-level clustering publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2015.2484220 – volume: 45 start-page: 1432 issue: 5 year: 2007 ident: 10.1016/j.isprsjprs.2021.01.004_b0100 article-title: A new statistical similarity measure for change detection in multitemporal SAR images and its extension to multiscale change analysis publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2007.893568 – volume: 129 start-page: 212 year: 2017 ident: 10.1016/j.isprsjprs.2021.01.004_b0075 article-title: Feature learning and change feature classification based on deep learning for ternary change detection in SAR images publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2017.05.001 – volume: 10 start-page: 046019 issue: 4 year: 2016 ident: 10.1016/j.isprsjprs.2021.01.004_b0050 article-title: Change detection from synthetic aperture radar images based on neighborhood-based ratio and extreme learning machine publication-title: J. Appl. Remote Sens doi: 10.1117/1.JRS.10.046019 – volume: 21 start-page: 2141 issue: 4 year: 2012 ident: 10.1016/j.isprsjprs.2021.01.004_b0085 article-title: Change detection in synthetic aperture radar images based on image fusion and fuzzy clustering publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2011.2170702 – volume: 12 start-page: 1978 issue: 12 year: 2020 ident: 10.1016/j.isprsjprs.2021.01.004_b0115 article-title: Rapid change detection of flood affected area after collapse of the Laos Xe-Plain Xe-Namnoy dam using Sentinel GRD data publication-title: Remote Sens. doi: 10.3390/rs12121978 – volume: 61 start-page: 309 year: 2017 ident: 10.1016/j.isprsjprs.2021.01.004_b0200 article-title: Unsupervised saliency-guided SAR image change detection publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2016.07.040 – volume: 48 start-page: 2403 issue: 5 year: 2010 ident: 10.1016/j.isprsjprs.2021.01.004_b0010 article-title: Earthquake damage assessment of buildings using VHR optical and SAR imagery publication-title: IEEE Trans. Geosci. Remote Sensing doi: 10.1109/TGRS.2009.2038274 – volume: 34 start-page: 2274 issue: 11 year: 2012 ident: 10.1016/j.isprsjprs.2021.01.004_b0005 article-title: SLIC superpixels compared to state-of-the-art superpixel methods publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2012.120 – volume: 57 start-page: 7365 issue: 10 year: 2019 ident: 10.1016/j.isprsjprs.2021.01.004_b0060 article-title: Saliency-guided deep neural networks for SAR image change detection publication-title: IEEE Trans. Geosci. Remote Sensing doi: 10.1109/TGRS.2019.2913095 – volume: 17 start-page: 416 issue: 3 year: 2020 ident: 10.1016/j.isprsjprs.2021.01.004_b0215 article-title: Adaptive generalized likelihood ratio test for change detection in SAR image publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2019.2922198 – volume: 11 start-page: 1091 issue: 9 year: 2019 ident: 10.1016/j.isprsjprs.2021.01.004_b0145 article-title: Urban building change detection in SAR images using combined differential image and residual U-Net network publication-title: Remote Sens. doi: 10.3390/rs11091091 – volume: 64 start-page: 255 year: 2017 ident: 10.1016/j.isprsjprs.2021.01.004_b0035 article-title: SAR Image segmentation based on convolutional-wavelet neural network and markov random field publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2016.11.015 – volume: 16 start-page: 402 issue: 3 year: 2019 ident: 10.1016/j.isprsjprs.2021.01.004_b0150 article-title: SAR image change detection using PCANet guided by saliency detecion publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2018.2876616 – volume: 13 start-page: 863 issue: 6 year: 2011 ident: 10.1016/j.isprsjprs.2021.01.004_b0095 article-title: Change detection method based on fractal model and wavelet transform for multitemporal SAR images publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 467 start-page: 415 year: 2018 ident: 10.1016/j.isprsjprs.2021.01.004_b0185 article-title: A novel edge-weight based fuzzy clustering method for change detection in SAR images publication-title: Inf. Sci. doi: 10.1016/j.ins.2018.08.015 – volume: 19 start-page: 1328 issue: 5 year: 2010 ident: 10.1016/j.isprsjprs.2021.01.004_b0120 article-title: A robust fuzzy local information c-means clustering algorithm publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2010.2040763 – volume: 13 start-page: 1792 issue: 12 year: 2016 ident: 10.1016/j.isprsjprs.2021.01.004_b0045 article-title: Automatic change detection in synthetic aperture radar images based on PCANet publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2016.2611001 – start-page: 2672 year: 2014 ident: 10.1016/j.isprsjprs.2021.01.004_b0065 article-title: Generative adversarial nets publication-title: Proc. NIPS. |
| SSID | ssj0001568 |
| Score | 2.5521803 |
| Snippet | [Display omitted]
•A multiscale superpixel reconstruction method was developed to generate the Difference Image.•A two-stage center-constrained FCM algorithm... Small area change detection using synthetic aperture radar (SAR) imagery is a highly challenging task, due to speckle noise and imbalance between classes... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 79 |
| SubjectTerms | algorithms Change detection data collection Deep learning Difference image Fuzzy c-means algorithm photogrammetry Synthetic aperture radar wavelet |
| Title | Robust unsupervised small area change detection from SAR imagery using deep learning |
| URI | https://dx.doi.org/10.1016/j.isprsjprs.2021.01.004 https://www.proquest.com/docview/2986449086 |
| Volume | 173 |
| WOSCitedRecordID | wos000640986100006&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: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1872-8235 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001568 issn: 0924-2716 databaseCode: AIEXJ dateStart: 19950201 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLbKhgR7QDBAbFxkJN6ioDROE4e3ahpjCE1TU1DfIid2tlZrEuUyBr-En8vxJVnYhgZCSG0UpXFi-Xw9_nx8Lgi9oQIUQMoTO6NUwALF823mJ7DmCSbhhMNZoJzHv3wKjo7oYhEej0Y_uliY87Mgz-nFRVj-V1HDNRC2DJ39C3H3D4ULcA5ChyOIHY5_JPhZkbR1Y7V53ZZSEdRAKeu13IFmQBBNpK_FRSN0lXAVYBJNZ9ZyLfNZfLNaZT7gQpRdTYmTIYU9jI5n0TDjRHlaNMrJay2aSqdzqgQgQFi19I43rYfG6cUy_34qLn-IWjUDshtu3euBd9Dqpqz4KpZDY4U78NbSFrRrUTTaFOl6NoDCpMTWipgGoKldncqk19QBGehaXYTGzNq6UvK1-UCbJlbwnrKqV_B9K3ulErXqqsdXkm1Hsi-yK67a9_D8O2jTBdiCvtycHu4vPvaz_FiHWfZ9_8V38MbX_Y75XOEAitjMH6IHZkWCpxpJj9BI5Ntoa5CnchvdOxAms_ljNNf4wkN8YYUvLPGFNb5wjy8s8YUBX9jgCyt8YYkv3OHrCfr8fn--98E2pTnsFAhsY8vNO5emJAE6GPKAM0IoLO1h6EgCK-wxyTxfZCwlPMh8Ng4zCqQoDBOeChqCdiBP0UZe5OIZwkCIPB9YtcfJxGPCYQFJQ4-QhLPEEZNkB_ndsMWpyVsvy6ecxZ2D4iruxzuW4x078HG8HeT0DUuduuX2Ju86ucSGgWpmGQOgbm_8upNkDDpabryxXBQt3CRrIMgddn_3X17wHN2__E-9QBtN1YqX6G563izr6pUB6E8et74w |
| linkProvider | Elsevier |
| 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=Robust+unsupervised+small+area+change+detection+from+SAR+imagery+using+deep+learning&rft.jtitle=ISPRS+journal+of+photogrammetry+and+remote+sensing&rft.au=Zhang%2C+Xinzheng&rft.au=Su%2C+Hang&rft.au=Zhang%2C+Ce&rft.au=Gu%2C+Xiaowei&rft.date=2021-03-01&rft.pub=Elsevier+B.V&rft.issn=0924-2716&rft.eissn=1872-8235&rft.volume=173&rft.spage=79&rft.epage=94&rft_id=info:doi/10.1016%2Fj.isprsjprs.2021.01.004&rft.externalDocID=S0924271621000046 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0924-2716&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0924-2716&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0924-2716&client=summon |