Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping
High-resolution (HR) satellite image time series (SITS) are a valuable data source for analyzing land cover change (LCC) due to their large amount of spatial, spectral, and temporal information. However, most existing LCC detection methods focus on binary change detection (CD) within a single year a...
- Autores:
-
Meshkini, Khatereh
Solano-Correa, Yady Tatiana
Bovolo, Francesca
Bruzzone, Lorenzo
- Tipo de recurso:
- Fecha de publicación:
- 2024
- Institución:
- Universidad Tecnológica de Bolívar
- Repositorio:
- Repositorio Institucional UTB
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.utb.edu.co:20.500.12585/12726
- Acceso en línea:
- https://hdl.handle.net/20.500.12585/12726
- Palabra clave:
- Dynamic time warping (DTW)
Hypertemporal feature
Land cover change (LCC)
Land cover (LC) transition
Multiannual
Remote sensing (RS)
LEMB
- Rights
- closedAccess
- License
- http://purl.org/coar/access_right/c_14cb
| id |
UTB2_3d06e755d7744c60bad7d69823bb1814 |
|---|---|
| oai_identifier_str |
oai:repositorio.utb.edu.co:20.500.12585/12726 |
| network_acronym_str |
UTB2 |
| network_name_str |
Repositorio Institucional UTB |
| repository_id_str |
|
| dc.title.spa.fl_str_mv |
Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping |
| title |
Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping |
| spellingShingle |
Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping Dynamic time warping (DTW) Hypertemporal feature Land cover change (LCC) Land cover (LC) transition Multiannual Remote sensing (RS) LEMB |
| title_short |
Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping |
| title_full |
Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping |
| title_fullStr |
Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping |
| title_full_unstemmed |
Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping |
| title_sort |
Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping |
| dc.creator.fl_str_mv |
Meshkini, Khatereh Solano-Correa, Yady Tatiana Bovolo, Francesca Bruzzone, Lorenzo |
| dc.contributor.author.none.fl_str_mv |
Meshkini, Khatereh Solano-Correa, Yady Tatiana Bovolo, Francesca Bruzzone, Lorenzo |
| dc.subject.keywords.spa.fl_str_mv |
Dynamic time warping (DTW) Hypertemporal feature Land cover change (LCC) Land cover (LC) transition Multiannual Remote sensing (RS) |
| topic |
Dynamic time warping (DTW) Hypertemporal feature Land cover change (LCC) Land cover (LC) transition Multiannual Remote sensing (RS) LEMB |
| dc.subject.armarc.none.fl_str_mv |
LEMB |
| description |
High-resolution (HR) satellite image time series (SITS) are a valuable data source for analyzing land cover change (LCC) due to their large amount of spatial, spectral, and temporal information. However, most existing LCC detection methods focus on binary change detection (CD) within a single year and fail to provide detailed information about the specific type of change. In this study, we propose a multiannual CD approach that identifies changes occurring between consecutive years and provides information about the type of LC transition. The proposed approach exploits multiannual and multispectral SITS to generate a hypertemporal feature space (FS). This FS is analyzed to create a set of CD maps that indicate the time, probability, and type of change. To measure the similarity between pixel time series, we use dynamic time warping (DTW) in the space of hypertemporal features. A hierarchical clustering technique is exploited to develop a set of class prototypes (CPs) that represent the characteristics of different LC classes. The CPs are then used to identify the most probable LC transition for each changed pixel. Two test areas were selected to evaluate the effectiveness of the proposed approach. The first one is located in Amazon and spans the years 2015 to 2019; and the second one is located in Sahel-Africa and covers the years 2015 and 2016, using multiannual Landsat 7 and 8 SITS. The results demonstrate that the proposed approach is effective in detecting multiannual changes and in identifying the LC transitions. |
| publishDate |
2024 |
| dc.date.accessioned.none.fl_str_mv |
2024-09-12T13:51:58Z |
| dc.date.available.none.fl_str_mv |
2024-09-12T13:51:58Z |
| dc.date.issued.none.fl_str_mv |
2024-07-22 |
| dc.date.submitted.none.fl_str_mv |
2024-09-11 |
| dc.type.coarversion.fl_str_mv |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| dc.type.coar.fl_str_mv |
http://purl.org/coar/resource_type/c_2df8fbb1 |
| dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/article |
| dc.type.hasversion.spa.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
| dc.type.spa.spa.fl_str_mv |
http://purl.org/coar/resource_type/c_6501 |
| status_str |
publishedVersion |
| dc.identifier.citation.spa.fl_str_mv |
K. Meshkini, Y. T. Solano-Correa, F. Bovolo and L. Bruzzone, “Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping,” IEEE Trans. on Geosci. and Remote Sens., vol. 62, pp. 1-12. Jul. 2024. DOI: 10.1109/TGRS.2024.3431631. |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/20.500.12585/12726 |
| dc.identifier.doi.none.fl_str_mv |
10.1109/TGRS.2024.3431631 |
| dc.identifier.instname.spa.fl_str_mv |
Universidad Tecnológica de Bolívar |
| dc.identifier.reponame.spa.fl_str_mv |
Repositorio Universidad Tecnológica de Bolívar |
| identifier_str_mv |
K. Meshkini, Y. T. Solano-Correa, F. Bovolo and L. Bruzzone, “Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping,” IEEE Trans. on Geosci. and Remote Sens., vol. 62, pp. 1-12. Jul. 2024. DOI: 10.1109/TGRS.2024.3431631. 10.1109/TGRS.2024.3431631 Universidad Tecnológica de Bolívar Repositorio Universidad Tecnológica de Bolívar |
| url |
https://hdl.handle.net/20.500.12585/12726 |
| dc.language.iso.spa.fl_str_mv |
eng |
| language |
eng |
| dc.rights.coar.fl_str_mv |
http://purl.org/coar/access_right/c_14cb |
| dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/closedAccess |
| eu_rights_str_mv |
closedAccess |
| rights_invalid_str_mv |
http://purl.org/coar/access_right/c_14cb |
| dc.format.extent.none.fl_str_mv |
12 páginas |
| dc.format.mimetype.spa.fl_str_mv |
application/pdf |
| dc.coverage.spatial.none.fl_str_mv |
Brazil y Sahel |
| dc.publisher.place.spa.fl_str_mv |
Cartagena de Indias |
| dc.publisher.faculty.spa.fl_str_mv |
Ciencias Básicas |
| dc.publisher.sede.spa.fl_str_mv |
Campus Tecnológico |
| dc.source.spa.fl_str_mv |
IEEE Transactions on Geoscience and Remote Sensing |
| institution |
Universidad Tecnológica de Bolívar |
| bitstream.url.fl_str_mv |
https://repositorio.utb.edu.co/bitstream/20.500.12585/12726/1/2024-J-Multiannual%20Change%20Detection%20in%20Long%20and%20Dense%20Satellite%20Image%20Time%20Series%20Based%20on%20Dynamic%20Time%20Warping.pdf https://repositorio.utb.edu.co/bitstream/20.500.12585/12726/2/license.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/12726/3/2024-J-Multiannual%20Change%20Detection%20in%20Long%20and%20Dense%20Satellite%20Image%20Time%20Series%20Based%20on%20Dynamic%20Time%20Warping.pdf.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/12726/4/2024-J-Multiannual%20Change%20Detection%20in%20Long%20and%20Dense%20Satellite%20Image%20Time%20Series%20Based%20on%20Dynamic%20Time%20Warping.pdf.jpg |
| bitstream.checksum.fl_str_mv |
a08ccdeff057c79fde9fa357597cb4d1 e20ad307a1c5f3f25af9304a7a7c86b6 6c4fc8ec71b8a5ed3bc6e86268cf7b35 b982cb1d8d80d663bdeaaf0abefbfb44 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Institucional UTB |
| repository.mail.fl_str_mv |
repositorioutb@utb.edu.co |
| _version_ |
1814021803661590528 |
| spelling |
Meshkini, Khaterehe1657908-5a71-4074-b0ca-13e9bb0017bcSolano-Correa, Yady Tatianac3d85b81-c6f5-4ad0-80dc-65e4cf4283b1Bovolo, Francesca3b4222a3-2890-417f-9c1b-efaaaf968b29Bruzzone, Lorenzob8f57b84-bfb7-4157-91e4-d763d266bb4aBrazil y Sahel2024-09-12T13:51:58Z2024-09-12T13:51:58Z2024-07-222024-09-11K. Meshkini, Y. T. Solano-Correa, F. Bovolo and L. Bruzzone, “Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping,” IEEE Trans. on Geosci. and Remote Sens., vol. 62, pp. 1-12. Jul. 2024. DOI: 10.1109/TGRS.2024.3431631.https://hdl.handle.net/20.500.12585/1272610.1109/TGRS.2024.3431631Universidad Tecnológica de BolívarRepositorio Universidad Tecnológica de BolívarHigh-resolution (HR) satellite image time series (SITS) are a valuable data source for analyzing land cover change (LCC) due to their large amount of spatial, spectral, and temporal information. However, most existing LCC detection methods focus on binary change detection (CD) within a single year and fail to provide detailed information about the specific type of change. In this study, we propose a multiannual CD approach that identifies changes occurring between consecutive years and provides information about the type of LC transition. The proposed approach exploits multiannual and multispectral SITS to generate a hypertemporal feature space (FS). This FS is analyzed to create a set of CD maps that indicate the time, probability, and type of change. To measure the similarity between pixel time series, we use dynamic time warping (DTW) in the space of hypertemporal features. A hierarchical clustering technique is exploited to develop a set of class prototypes (CPs) that represent the characteristics of different LC classes. The CPs are then used to identify the most probable LC transition for each changed pixel. Two test areas were selected to evaluate the effectiveness of the proposed approach. The first one is located in Amazon and spans the years 2015 to 2019; and the second one is located in Sahel-Africa and covers the years 2015 and 2016, using multiannual Landsat 7 and 8 SITS. The results demonstrate that the proposed approach is effective in detecting multiannual changes and in identifying the LC transitions.12 páginasapplication/pdfengIEEE Transactions on Geoscience and Remote SensingMultiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warpinginfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501http://purl.org/coar/version/c_970fb48d4fbd8a85http://purl.org/coar/resource_type/c_2df8fbb1Dynamic time warping (DTW)Hypertemporal featureLand cover change (LCC)Land cover (LC) transitionMultiannualRemote sensing (RS)LEMBinfo:eu-repo/semantics/closedAccesshttp://purl.org/coar/access_right/c_14cbCartagena de IndiasCiencias BásicasCampus TecnológicoInvestigadoresJ. Verbesselt, A. Zeileis and M. Herold, "Near real-time disturbance detection using satellite image time series", Remote Sens. Environ., vol. 123, pp. 98-108, Aug. 2012.M. Decuyper et al., "Continuous monitoring of forest change dynamics with satellite time series", Remote Sens. Environ., vol. 269, Feb. 2022.D. Lu, E. Moran and S. Hetrick, "Detection of impervious surface change with multitemporal Landsat images in an urban–rural frontier", ISPRS J. Photogramm. Remote Sens., vol. 66, no. 3, pp. 298-306, May 2011.S. Stramondo, C. Bignami, M. Chini, N. Pierdicca and A. Tertulliani, "Satellite radar and optical remote sensing for earthquake damage detection: Results from different case studies", Int. J. Remote Sens., vol. 27, no. 20, pp. 4433-4447, Oct. 2006.K. Meshkini, F. Bovolo and L. Bruzzone, "A 3D CNN approach for change detection in HR satellite image time series based on a pretrained 2D CNN", Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., vol. 43, pp. 143-150, May 2022.A. Rodrigues, A. R. S. Marcal and M. Cunha, "Monitoring vegetation dynamics inferred by satellite data using the PhenoSat tool", IEEE Trans. Geosci. Remote Sens., vol. 51, no. 4, pp. 2096-2104, Apr. 2013.Y. T. Solano-Correa, F. Bovolo, L. Bruzzone and D. Fernández-Prieto, "A method for the analysis of small crop fields in Sentinel-2 dense time series", IEEE Trans. Geosci. Remote Sens., vol. 58, no. 3, pp. 2150-2164, Mar. 2020.C. Senf, D. Pflugmacher, M. A. Wulder and P. Hostert, "Characterizing spectral–temporal patterns of defoliator and bark beetle disturbances using Landsat time series", Remote Sens. Environ., vol. 170, pp. 166-177, Dec. 2015.A. Asokan and J. Anitha, "Change detection techniques for remote sensing applications: A survey", Earth Sci. Inform., vol. 12, no. 2, pp. 143-160, Jun. 2019.G. Jianya, S. Haigang, M. Guorui and Z. Qiming, "A review of multi-temporal remote sensing data change detection algorithms", Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., vol. 37, no. B7, pp. 757-762, 2008.I. Pôças, M. Cunha, A. R. S. Marcal and L. S. Pereira, "An evaluation of changes in a mountainous rural landscape of Northeast Portugal using remotely sensed data", Landscape Urban Planning, vol. 101, no. 3, pp. 253-261, Jun. 2011.X. Zhang, P. Xiao, X. Feng and M. Yuan, "Separate segmentation of multi-temporal high-resolution remote sensing images for objectbased change detection in urban area", Remote Sens. Environ., vol. 201, pp. 243-255, Nov. 2017.G. Vivekananda, R. Swathi and A. Sujith, "Multi-temporal image analysis for LULC classification and change detection", Eur. J. Remote Sens., vol. 54, no. 2, pp. 189-199, Mar. 2021.B. Wang, J. Choi, S. Choi, S. Lee, P. Wu and Y. Gao, "Image fusionbased land cover change detection using multi-temporal high-resolution satellite images", Remote Sens., vol. 9, no. 8, pp. 804, Aug. 2017.S. Jamali, P. Jönsson, L. Eklundh, J. Ardö and J. Seaquist, "Detecting changes in vegetation trends using time series segmentation", Remote Sens. Environ., vol. 156, pp. 182-195, Jan. 2015.W. B. Cohen, Z. Yang and R. E. Kennedy, "Detecting trends in forest disturbance and recovery using yearly Landsat time series: 1. LandTrendr—Temporal segmentation algorithms", Remote Sens. Environ., vol. 114, no. 12, pp. 2897-2910, 2010.R. De Jong, J. Verbesselt, M. E. Schaepman and S. De Bruin, "Trend changes in global greening and browning: Contribution of short-term trends to longer-term change", Global Change Biol., vol. 18, no. 2, pp. 642-655, 2012.E. B. Brooks, R. H. Wynne, V. A. Thomas, C. E. Blinn and J. W. Coulston, "On-the-fly massively multitemporal change detection using statistical quality control charts and Landsat data", IEEE Trans. Geosci. Remote Sens., vol. 52, no. 6, pp. 3316-3332, Jun. 2014.J. Verbesselt, R. Hyndman, G. Newnham and D. Culvenor, "Detecting trend and seasonal changes in satellite image time series", Remote Sens. Environ., vol. 114, no. 1, pp. 106-115, Jan. 2010.J. Lambert, C. Drenou, J.-P. Denux, G. Balent and V. Cheret, "Monitoring forest decline through remote sensing time series analysis", GIScience Remote Sens., vol. 50, no. 4, pp. 437-457, Aug. 2013.O. A. C. Júnior et al., "A new approach to change vector analysis using distance and similarity measures", Remote Sens., vol. 3, no. 11, pp. 2473-2493, Nov. 2011F. Bovolo and L. Bruzzone, "A theoretical framework for unsupervised change detection based on change vector analysis in the polar domain", IEEE Trans. Geosci. Remote Sens., vol. 45, no. 1, pp. 218-236, Jan. 2007.K. Meshkini, F. Bovolo and L. Bruzzone, "A multi-feature hypertemporal change vector analysis method for change detection in multi-annual time series of HR satellite images", Proc. IEEE Int. Geosci. Remote Sens. Symp. (IGARSS), pp. 8315-8318, Jul. 2023.D. J. Berndt and J. Clifford, "Using dynamic time warping to find patterns in time series", Proc. KDD Workshop, pp. 356-370, 1994.T. Rakthanmanon et al., "Searching and mining trillions of time series subsequences under dynamic time warping", Proc. 18th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, pp. 262-270, Aug. 2012.F. Petitjean, J. Inglada and P. Gançarski, "Satellite image time series analysis under time warping", IEEE Trans. Geosci. Remote Sens., vol. 50, no. 8, pp. 3081-3095, Aug. 2012.F. Petitjean and J. Weber, "Efficient satellite image time series analysis under time warping", IEEE Geosci. Remote Sens. Lett., vol. 11, no. 6, pp. 1143-1147, Jun. 2014.M. Baumann, M. Ozdogan, A. D. Richardson and V. C. Radeloff, "Phenology from Landsat when data is scarce: Using MODIS and dynamic time-warping to combine multi-year Landsat imagery to derive annual phenology curves", Int. J. Appl. Earth Observ. Geoinf., vol. 54, pp. 72-83, Feb. 2017.M. Belgiu and O. Csillik, "Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis", Remote Sens. Environ., vol. 204, pp. 509-523, Jan. 2018.Google Earth Engine, May 2023, [online] Available: https://developers.google.com/earth-engine/datasets/catalog/landsat.http://purl.org/coar/resource_type/c_2df8fbb1ORIGINAL2024-J-Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping.pdf2024-J-Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping.pdfMultiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warpingapplication/pdf27089012https://repositorio.utb.edu.co/bitstream/20.500.12585/12726/1/2024-J-Multiannual%20Change%20Detection%20in%20Long%20and%20Dense%20Satellite%20Image%20Time%20Series%20Based%20on%20Dynamic%20Time%20Warping.pdfa08ccdeff057c79fde9fa357597cb4d1MD51LICENSElicense.txtlicense.txttext/plain; charset=utf-83182https://repositorio.utb.edu.co/bitstream/20.500.12585/12726/2/license.txte20ad307a1c5f3f25af9304a7a7c86b6MD52TEXT2024-J-Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping.pdf.txt2024-J-Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping.pdf.txtExtracted texttext/plain64710https://repositorio.utb.edu.co/bitstream/20.500.12585/12726/3/2024-J-Multiannual%20Change%20Detection%20in%20Long%20and%20Dense%20Satellite%20Image%20Time%20Series%20Based%20on%20Dynamic%20Time%20Warping.pdf.txt6c4fc8ec71b8a5ed3bc6e86268cf7b35MD53THUMBNAIL2024-J-Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping.pdf.jpg2024-J-Multiannual Change Detection in Long and Dense Satellite Image Time Series Based on Dynamic Time Warping.pdf.jpgGenerated Thumbnailimage/jpeg10902https://repositorio.utb.edu.co/bitstream/20.500.12585/12726/4/2024-J-Multiannual%20Change%20Detection%20in%20Long%20and%20Dense%20Satellite%20Image%20Time%20Series%20Based%20on%20Dynamic%20Time%20Warping.pdf.jpgb982cb1d8d80d663bdeaaf0abefbfb44MD5420.500.12585/12726oai:repositorio.utb.edu.co:20.500.12585/127262024-09-13 00:18:22.662Repositorio Institucional UTBrepositorioutb@utb.edu.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 |