Show simple item record

dc.contributor.authorZhu, Yueen
dc.contributor.authorGeis, Cen
dc.contributor.authorSo, Emilyen
dc.contributor.authorJin, Yingen
dc.date.accessioned2021-02-18T00:30:47Z
dc.date.available2021-02-18T00:30:47Z
dc.date.issued2021-01-01en
dc.identifier.issn1939-1404
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/317828
dc.description.abstractIn this article, we present a novel hybrid framework, which integrates spatial–temporal semantic segmentation with postclassification relearning, for multitemporal land use and land cover (LULC) classification based on very high resolution (VHR) satellite imagery. To efficiently obtain optimal multitemporal LULC classification maps, the hybrid framework utilizes a spatial–temporal semantic segmentation model to harness temporal dependency for extracting high-level spatial–temporal features. In addition, the principle of postclassification relearning is adopted to efficiently optimize model output. Thereby, the initial outcome of a semantic segmentation model is provided to a subsequent model via an extended input space to guide the learning of discriminative feature representations in an end-to-end fashion. Last, object-based voting is coupled with postclassification relearning for coping with the high intraclass and low interclass variances. The framework was tested with two different postclassification relearning strategies (i.e., pixel-based relearning and object-based relearning) and three convolutional neural network models, i.e., UNet, a simple Convolutional LSTM, and a UNet Convolutional-LSTM. The experiments were conducted on two datasets with LULC labels that contain rich semantic information and variant building morphologic features (e.g., informal settlements). Each dataset contains four time steps from WorldView-2 and Quickbird imagery. The experimental results unambiguously underline that the proposed framework is efficient in terms of classifying complex LULC maps with multitemporal VHR images.
dc.publisherInstitute of Electrical and Electronics Engineers
dc.rightsAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleMultitemporal Relearning with Convolutional LSTM Models for Land Use Classificationen
dc.typeArticle
prism.endingPage3265
prism.publicationDate2021en
prism.publicationNameIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensingen
prism.startingPage3251
prism.volume14en
dc.identifier.doi10.17863/CAM.64943
dcterms.dateAccepted2021-01-20en
rioxxterms.versionofrecord10.1109/JSTARS.2021.3055784en
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2021-01-01en
dc.contributor.orcidZhu, Yue [0000-0002-3154-9659]
dc.contributor.orcidGeis, C [0000-0002-7961-8553]
dc.contributor.orcidSo, Emily [0000-0002-2460-0452]
dc.contributor.orcidJin, Ying [0000-0003-2683-6829]
dc.identifier.eissn2151-1535
rioxxterms.typeJournal Article/Reviewen
pubs.funder-project-idEPSRC (EP/N021614/1)
pubs.funder-project-idEPSRC (EP/L010917/1)
pubs.funder-project-idEPSRC (EP/N010221/1)
cam.orpheus.successMon Jun 28 07:31:55 BST 2021 - The item has an open VoR version.*
cam.orpheus.counter18*
rioxxterms.freetoread.startdate2100-01-01


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International
Except where otherwise noted, this item's licence is described as Attribution 4.0 International