SEM algorithm and unsupervised statistical segmentation of satellite images
The work addresses Bayesian unsupervised satellite image segmentation, using contextual methods. It is shown, via a simulation study, that the spatial or spectral context contribution is sensitive to image parameters such as homogeneity, means, variances, and spatial or spectral correlations of the...
Saved in:
| Published in | IEEE transactions on geoscience and remote sensing Vol. 31; no. 3; pp. 618 - 633 |
|---|---|
| Main Authors | , |
| Format | Journal Article |
| Language | English |
| Published |
New York, NY
IEEE
01.05.1993
Institute of Electrical and Electronics Engineers |
| Subjects | |
| Online Access | Get full text |
| ISSN | 0196-2892 |
| DOI | 10.1109/36.225529 |
Cover
| Abstract | The work addresses Bayesian unsupervised satellite image segmentation, using contextual methods. It is shown, via a simulation study, that the spatial or spectral context contribution is sensitive to image parameters such as homogeneity, means, variances, and spatial or spectral correlations of the noise. From this one may choose the best context contribution according to the estimated values of the above parameters. The parameter estimation is done by SEM, a densities mixture estimator which is a stochastic variant of the EM (expectation-maximization) algorithm. Another simulation study shows good robustness of the SEM algorithm with respect to different image parameters. Thus, modification of the behavior of the contextual methods, when the SEM-based unsupervised approaches are considered, is limited, and the conclusions of the supervised simulation study stay valid. An adaptive unsupervised method using more relevant contextual features is proposed. Different SEM-based unsupervised contextual segmentation methods, applied to two real SPOT images, give consistently better results than a classical histogram-based method.< > |
|---|---|
| AbstractList | This work addresses Bayesian unsupervised satellite image segmentation. We propose, as an alternative to global methods like MAP or MPM, the use of contextual ones, which is partially justified by previous works. We show, via a simulation study, that spatial or spectral context contribution is sensitive to image parameters such as homogeneity, means, variances, and spatial or spectral correlations of the noise. From this one may choose the best context contribution according to the estimated values of the above parameters. The parameter estimation step is treated by the SEM, a densities mixture estimator which is a stochastic variant of the EM algorithm. Another simulation study shows good robustness of the SEM algorithm with respect to different image parameters. Thus modification of the behavior of the contextual methods, when the SEM-based unsupervised approaches are considered, remains limited and the conclusions of the supervised simulation study stay valid. We propose an 'adaptive unsupervised method' using more relevant contextual features. Furthermore, we apply different SEM-based unsupervised contextual segmentation methods to two real SPOT images and observe that the results obtained are consistently better than those obtained by a classical histogram based method. The work addresses Bayesian unsupervised satellite image segmentation, using contextual methods. It is shown, via a simulation study, that the spatial or spectral context contribution is sensitive to image parameters such as homogeneity, means, variances, and spatial or spectral correlations of the noise. From this one may choose the best context contribution according to the estimated values of the above parameters. The parameter estimation is done by SEM, a densities mixture estimator which is a stochastic variant of the EM (expectation-maximization) algorithm. Another simulation study shows good robustness of the SEM algorithm with respect to different image parameters. Thus, modification of the behavior of the contextual methods, when the SEM-based unsupervised approaches are considered, is limited, and the conclusions of the supervised simulation study stay valid. An adaptive unsupervised method using more relevant contextual features is proposed. Different SEM-based unsupervised contextual segmentation methods, applied to two real SPOT images, give consistently better results than a classical histogram-based method.< > The work addresses Bayesian unsupervised satellite image segmentation, using contextual methods. It is shown, via a simulation study, that the spatial or spectral context contribution is sensitive to image parameters such as homogeneity, means, variances, and spatial or spectral correlations of the noise. From this one may choose the best context contribution according to the estimated values of the above parameters. The parameter estimation is done by SEM, a densities mixture estimator which is a stochastic variant of the EM (expectation-maximization) algorithm. Another simulation study shows good robustness of the SEM algorithm with respect to different image parameters. Thus, modification of the behavior of the contextual methods, when the SEM-based unsupervised approaches are considered, is limited, and the conclusions of the supervised simulation study stay valid. An adaptive unsupervised method using more relevant contextual features is proposed. Different SEM-based unsupervised contextual segmentation methods, applied to two real SPOT images, give consistently better results than a classical histogram-based method |
| Author | Masson, P. Pieczynski, W. |
| Author_xml | – sequence: 1 givenname: P. surname: Masson fullname: Masson, P. organization: Dept. Math. et Syst. de Commun., Ecole Nat. Superieure des Telecommun. de Bretagne, Brest, France – sequence: 2 givenname: W. surname: Pieczynski fullname: Pieczynski, W. |
| BackLink | http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=4851125$$DView record in Pascal Francis |
| BookMark | eNqFkc1Lw0AQxfdQwbZ68OopBxE8pN2PbLJ7lFI_sOJBPYftZlJX0qTubAT_exNSehChp4GZ33sM703IqG5qIOSC0RljVM9FOuNcSq5HZEyZTmOuND8lE8RPSlkiWTYmT6_L58hUm8a78LGNTF1EbY3tDvy3QygiDCY4DM6aKkLYbKHuF00dNWWEJkBVuQCR25oN4Bk5KU2FcL6fU_J-t3xbPMSrl_vHxe0qtiJVIZY2TSSoVIBIlBKglaFZAYUEoMZKVVDLeQa6lCVdq4KVKl1Lw21WlJyvQYgpuR58d775agFDvnVou1dMDU2LOddUiIyp46CSmdZUHgdTzjJFe8erPWiwi6T0prYO853vEvA_eaIkY7z3uxkw6xtED-WBYDTvu8lFmg_ddOz8D2vdkHHwxlX_Ki4HhQOAg_P--AunmZzm |
| CODEN | IGRSD2 |
| CitedBy_id | crossref_primary_10_1109_JPROC_2012_2197589 crossref_primary_10_1117_1_JRS_8_083553 crossref_primary_10_1080_01431169508954484 crossref_primary_10_1109_MAES_2010_5546306 crossref_primary_10_1080_01431161003745640 crossref_primary_10_1109_JSTARS_2014_2328597 crossref_primary_10_1109_TGRS_2010_2062526 crossref_primary_10_1109_JSEN_2009_2037794 crossref_primary_10_1109_TIP_2012_2219545 crossref_primary_10_1007_s10044_015_0519_6 crossref_primary_10_1016_j_media_2008_03_001 crossref_primary_10_1155_2012_425947 crossref_primary_10_1080_01431161_2014_967883 crossref_primary_10_1109_TGRS_2009_2016214 crossref_primary_10_1142_S0129156408005394 crossref_primary_10_4236_jgis_2024_165020 crossref_primary_10_1109_83_913593 crossref_primary_10_1109_36_239902 crossref_primary_10_1109_83_847834 crossref_primary_10_1109_TGRS_2005_859349 crossref_primary_10_1109_TGRS_2007_895416 crossref_primary_10_1109_34_589206 crossref_primary_10_1109_TGRS_2004_830644 crossref_primary_10_1109_TGRS_2016_2562018 crossref_primary_10_1364_AO_43_006596 crossref_primary_10_1088_0031_9155_56_18_001 crossref_primary_10_1109_TIP_2006_873446 crossref_primary_10_1109_5_784235 crossref_primary_10_1007_s00138_012_0441_5 crossref_primary_10_1016_j_jksuci_2023_101715 crossref_primary_10_1016_j_rse_2005_01_011 crossref_primary_10_1016_j_neucom_2012_11_016 crossref_primary_10_1016_S0167_8655_02_00193_9 crossref_primary_10_1007_s10851_019_00885_0 crossref_primary_10_1117_1_OE_55_7_073101 crossref_primary_10_1109_TIP_2010_2076298 crossref_primary_10_1109_83_557353 crossref_primary_10_1109_TGRS_2020_2986239 crossref_primary_10_1109_83_624951 crossref_primary_10_1137_16M1057346 crossref_primary_10_1109_JSTARS_2013_2272697 crossref_primary_10_1016_j_patrec_2008_01_007 crossref_primary_10_1080_02757250109532431 crossref_primary_10_1109_TGRS_2007_907973 crossref_primary_10_1016_j_physa_2010_10_015 crossref_primary_10_1016_S0031_3203_99_00135_1 crossref_primary_10_1016_S0262_8856_03_00136_7 crossref_primary_10_1109_TGRS_2004_841481 crossref_primary_10_1016_j_jvcir_2007_05_001 crossref_primary_10_1109_JSTARS_2012_2186284 crossref_primary_10_1117_1_3077179 crossref_primary_10_1109_JSTARS_2015_2416255 crossref_primary_10_1109_TIP_2019_2933747 crossref_primary_10_1109_42_544504 crossref_primary_10_1109_TMI_2006_872142 crossref_primary_10_1016_j_artmed_2015_04_002 crossref_primary_10_1109_TGRS_2002_803716 crossref_primary_10_1117_1_3386069 crossref_primary_10_1007_BF02344714 crossref_primary_10_1117_1_JRS_13_036502 crossref_primary_10_1007_s11554_008_0105_x crossref_primary_10_1007_s00521_011_0538_1 crossref_primary_10_1364_AO_47_000F27 crossref_primary_10_3390_math11040986 crossref_primary_10_1007_s11227_018_2288_7 crossref_primary_10_1006_gmip_1997_0431 crossref_primary_10_1016_j_sigpro_2007_04_010 crossref_primary_10_1109_79_974730 crossref_primary_10_1155_2010_372370 crossref_primary_10_1109_TIP_2005_851710 crossref_primary_10_1155_2012_162106 crossref_primary_10_1016_j_patrec_2006_03_005 crossref_primary_10_1109_36_942557 crossref_primary_10_1016_S0167_8655_98_00076_2 crossref_primary_10_1016_j_imavis_2006_03_005 |
| Cites_doi | 10.1109/IGARSS.1992.578461 10.1109/34.85674 10.1109/TGRS.1986.289563 10.1109/29.7551 10.1109/34.6774 10.1080/02664768900000022 10.1016/0031-3203(89)90011-3 10.1080/02664768900000021 10.1117/12.463182 10.2307/2289127 10.1007/BF00341287 10.1109/TGRS.1987.289751 10.1109/TC.1976.1674719 10.1109/IGARSS.1992.578356 10.1080/02664768900000014 10.1109/IGARSS.1991.580308 10.1109/TGRS.1982.350410 10.1016/0031-3203(81)90005-4 10.1109/IGARSS.1992.578462 10.1109/TPAMI.1984.4767596 10.1109/IGARSS.1991.575472 |
| ContentType | Journal Article |
| Copyright | 1993 INIST-CNRS |
| Copyright_xml | – notice: 1993 INIST-CNRS |
| DBID | AAYXX CITATION IQODW 8FD H8D L7M FR3 KR7 |
| DOI | 10.1109/36.225529 |
| DatabaseName | CrossRef Pascal-Francis Technology Research Database Aerospace Database Advanced Technologies Database with Aerospace Engineering Research Database Civil Engineering Abstracts |
| DatabaseTitle | CrossRef Technology Research Database Aerospace Database Advanced Technologies Database with Aerospace Civil Engineering Abstracts Engineering Research Database |
| DatabaseTitleList | Technology Research Database Technology Research Database Technology Research Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Physics |
| EndPage | 633 |
| ExternalDocumentID | 4851125 10_1109_36_225529 225529 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AETIX AFRAH AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IBMZZ ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 Y6R AAYXX CITATION IQODW RIG 8FD H8D L7M FR3 KR7 |
| ID | FETCH-LOGICAL-c368t-5c645e863e34883e98a07ded5ee0ac58d0c227e9f5f0b8d1f86b5a2c7df22be33 |
| IEDL.DBID | RIE |
| ISSN | 0196-2892 |
| IngestDate | Wed Oct 01 13:38:42 EDT 2025 Sat Sep 27 23:32:27 EDT 2025 Mon Sep 29 04:09:41 EDT 2025 Mon Jul 21 09:12:14 EDT 2025 Thu Apr 24 22:53:46 EDT 2025 Wed Oct 01 05:07:13 EDT 2025 Tue Aug 26 16:39:20 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Keywords | Bayes estimation algorithms Random field Parameter estimation spectral signature Image processing algorithm performance imagery data processing segmentation remote sensing classification |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html CC BY 4.0 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c368t-5c645e863e34883e98a07ded5ee0ac58d0c227e9f5f0b8d1f86b5a2c7df22be33 |
| Notes | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 |
| PQID | 26217808 |
| PQPubID | 23500 |
| PageCount | 16 |
| ParticipantIDs | proquest_miscellaneous_29033718 ieee_primary_225529 proquest_miscellaneous_28579905 pascalfrancis_primary_4851125 proquest_miscellaneous_26217808 crossref_primary_10_1109_36_225529 crossref_citationtrail_10_1109_36_225529 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 1900 |
| PublicationDate | 1993-05-01 |
| PublicationDateYYYYMMDD | 1993-05-01 |
| PublicationDate_xml | – month: 05 year: 1993 text: 1993-05-01 day: 01 |
| PublicationDecade | 1990 |
| PublicationPlace | New York, NY |
| PublicationPlace_xml | – name: New York, NY |
| PublicationTitle | IEEE transactions on geoscience and remote sensing |
| PublicationTitleAbbrev | TGRS |
| PublicationYear | 1993 |
| Publisher | IEEE Institute of Electrical and Electronics Engineers |
| Publisher_xml | – name: IEEE – name: Institute of Electrical and Electronics Engineers |
| References | ref13 ref12 masson (ref21) 1990 ref15 ref14 ref31 ref30 ref11 ref32 ref10 celeux (ref4) 1986; 34 ref17 braathen (ref2) 1991 ref18 pieczynski (ref24) 1990 ref23 ref26 ref25 ref22 devijver (ref8) 1988; 5 masson (ref20) 1990 besag (ref1) 1986; 48 marhic (ref16) 1991; 16 ref28 celeux (ref5) 1986 ref27 (ref19) 0 ref29 ref9 ref3 ref6 dempster (ref7) 1977; 39 |
| References_xml | – ident: ref3 doi: 10.1109/IGARSS.1992.578461 – ident: ref31 doi: 10.1109/34.85674 – ident: ref12 doi: 10.1109/TGRS.1986.289563 – year: 1991 ident: ref2 article-title: Sur une nouvelle approche de segmentation Bayesienne non supervis e d'images publication-title: Proc Treisi me colloque GRETSI – volume: 48 start-page: 259 year: 1986 ident: ref1 article-title: On the statistical analysis of dirty pictures publication-title: Journal of the Royal Statistical Society – volume: 5 year: 1988 ident: ref8 article-title: Champs al atoires de Pickard et mod lisation d'images digitales publication-title: Traitement du Signal – ident: ref14 doi: 10.1109/29.7551 – ident: ref15 doi: 10.1109/34.6774 – ident: ref23 doi: 10.1080/02664768900000022 – ident: ref6 doi: 10.1016/0031-3203(89)90011-3 – ident: ref26 doi: 10.1080/02664768900000021 – year: 1990 ident: ref21 article-title: Segmentation of SPOT images by contextual SEM publication-title: Proc of eusipco – ident: ref25 doi: 10.1117/12.463182 – volume: 34 year: 1986 ident: ref4 article-title: L'algorithme SEM: an algorithme d'apprentissage probabiliste pour la reconnaissance de m langes de densit s publication-title: Revue de Statistique Appliques – ident: ref18 doi: 10.2307/2289127 – ident: ref32 doi: 10.1007/BF00341287 – ident: ref22 doi: 10.1109/TGRS.1987.289751 – ident: ref13 doi: 10.1109/TC.1976.1674719 – year: 0 ident: ref19 – ident: ref28 doi: 10.1109/IGARSS.1992.578356 – ident: ref9 doi: 10.1080/02664768900000014 – year: 1990 ident: ref20 article-title: Classification d'images du satellite SPOT pour la cartographie bathym trique du littoral publication-title: Proc PIXILES 90 Journ es internationales – ident: ref17 doi: 10.1109/IGARSS.1991.580308 – ident: ref30 doi: 10.1109/TGRS.1982.350410 – ident: ref29 doi: 10.1016/0031-3203(81)90005-4 – year: 1990 ident: ref24 publication-title: Mixture of distributions Markov random fields and unsupervised Bayesian segmentation of images – volume: 16 year: 1991 ident: ref16 article-title: M lange de lois et segmentation non supervis e des donnees SPOT publication-title: Statistique et Analyse des Donn es – year: 1986 ident: ref5 publication-title: Comportement asymptotique d'un algorithme d'apprentissage probabiliste pour les m langes de lois de probabilit s – ident: ref10 doi: 10.1109/IGARSS.1992.578462 – ident: ref11 doi: 10.1109/TPAMI.1984.4767596 – ident: ref27 doi: 10.1109/IGARSS.1991.575472 – volume: 39 start-page: 1 year: 1977 ident: ref7 article-title: Maximum likelihood from incomplete data via the EM algorithm publication-title: Journal of the Royal Statistical Society |
| SSID | ssj0014517 |
| Score | 1.8136994 |
| Snippet | The work addresses Bayesian unsupervised satellite image segmentation, using contextual methods. It is shown, via a simulation study, that the spatial or... This work addresses Bayesian unsupervised satellite image segmentation. We propose, as an alternative to global methods like MAP or MPM, the use of contextual... |
| SourceID | proquest pascalfrancis crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 618 |
| SubjectTerms | Areal geology. Maps Bayesian methods Context modeling Earth sciences Earth, ocean, space Exact sciences and technology Geologic maps, cartography Histograms Image segmentation Iterative algorithms Noise robustness Parameter estimation Random variables Satellites Soils Stochastic resonance Surficial geology |
| Title | SEM algorithm and unsupervised statistical segmentation of satellite images |
| URI | https://ieeexplore.ieee.org/document/225529 https://www.proquest.com/docview/26217808 https://www.proquest.com/docview/28579905 https://www.proquest.com/docview/29033718 |
| Volume | 31 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) issn: 0196-2892 databaseCode: RIE dateStart: 19800101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://ieeexplore.ieee.org/ omitProxy: false ssIdentifier: ssj0014517 providerName: IEEE |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3NT6QwFG_UxEQPu-uocVw_GuPBC2OhtLRHY5yY3YwXNfFGSvtQowPGwmX_etvCjB9rjDcCDwJ97fug7_d7CB3GphRMZyQSUvEoNZRFRazLSFOuhdQugRAenDy54OfX6Z8bdtPzbAcsDACE4jMY-cOwl29q3fpfZcdu7rFELqLFTPAOqjXfMEhZ3COjeeRyiKQnEYqJPKZ81N34zvWEXiq-ElJZNxhl18XiP4McvMz4ZwfftoGc0BeXPIzaphjpfx-oG7_5Ab_Qjz7axCfd9FhDC1AN0OobDsIBWg41oNquo7-XZxOsHm_r5_vmbopVZXBb2fbJWxMLBnvsUaB1dk-0cDvtUUsVrktsVWD2bADfT52Fshvoenx2dXoe9b0WvFZEEzHNUwaCU6BuSVOQQpHMgGEARGkmDNFJkoEsWUkKYeJS8IKpRGemTJICKN1ES1VdwRbC3BlYwpTMNHfhgmGykEaLmADV4IIlM0RHMzXkuici9_0wHvOQkBCZU553IzVEB3PRp4594zOhgR_pucDs7O471c4vpyHGZEO0P1N17laU3yZRFdStzRPu0jRBxBcSgmXOi3_1DEkodW5_-9N3-41WXusmd9BS89zCrottmmIvzOoXfoL41Q |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB5BEYIeeCwgtrTUQhy4ZOvEsWMfEWq10G4vtFJvkWNPSkU3qerkwq_HdrILpVXFLUomUeKx5xHP9w3Ax9TWkpuCJlJpkeSW8aRKTZ0YJoxUxicQMoCTF8difpp_O-NnI892xMIgYiw-w1k4jHv5tjV9-FW25-cez9RDeMTzPOcDWGu9ZZDzdMRGi8RnEdlII5RStcfEbLj1hvOJ3VRCLaR2fjjqoY_FLZMc_czB8wHA7SI9YSgv-Tnru2pmfv1D3vifn_ACno3xJvk8TJCX8ACbCWz-xUI4gcexCtS4V3D4fX9B9OV5e33R_VgS3VjSN66_CvbEoSUBfRSJnf0THZ4vR9xSQ9qaOB25PTskF0tvo9xrOD3YP_kyT8ZuC0Evsku4ETlHKRgyv6gZKqlpYdFyRKoNl5aaLCtQ1bymlbRpLUXFdWYKW2dZhYy9gY2mbfAtEOFNLOVaFUb4gMFyVSlrZEqRGfThkp3Cp5UaSjNSkYeOGJdlTEmoKpkoh5Gawoe16NXAv3GX0CSM9FpgdXbnhmrXl_MYZfIp7K5UXfo1FTZKdINt78pM-ERNUnmPhOSF9-P3PUNRxrzj37rz3XbhyfxkcVQefT0-fAdP_1RRbsNGd93jjo90uup9nOG_AaKy_CI |
| 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=SEM+algorithm+and+unsupervised+statistical+segmentation+of+satellite+images&rft.jtitle=IEEE+transactions+on+geoscience+and+remote+sensing&rft.au=MASSON%2C+P&rft.au=PIECZYNSKI%2C+W&rft.date=1993-05-01&rft.pub=Institute+of+Electrical+and+Electronics+Engineers&rft.issn=0196-2892&rft.volume=31&rft.issue=3&rft.spage=618&rft.epage=633&rft_id=info:doi/10.1109%2F36.225529&rft.externalDBID=n%2Fa&rft.externalDocID=4851125 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0196-2892&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0196-2892&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0196-2892&client=summon |