File Download

There are no files associated with this item.

  • Find it @ UNIST can give you direct access to the published full text of this article. (UNISTARs only)
Related Researcher


Im, Jungho
Intelligent Remote sensing and geospatial Information Science Lab.
Read More

Views & Downloads

Detailed Information

Cited time in webofscience Cited time in scopus
Metadata Downloads

Full metadata record

DC Field Value Language
dc.citation.endPage 4617 -
dc.citation.number 12 -
dc.citation.startPage 4604 -
dc.citation.volume 11 - Kim, Miae - Lee, Junghee - Han, Daehyun - Shin, Minso - Im, Jungho - Lee, Junghye - Quackenbush, Lindi J. - Gu, Zhu - 2023-12-21T19:47:30Z - 2023-12-21T19:47:30Z - 2019-01-08 - 2018-12 -
dc.description.abstract Researchers constantly seek more efficient detection techniques to better utilize enhanced image resolution in accurately detecting and monitoring land cover. Recently, convolutional neural networks (CNNs) have shown high performances comparable to or even better than widely used and adopted machine learning techniques. The aim of this study is to investigate the application of CNNs for land cover classification by using two-dimensional (2-D) spectral curve graphs from multispectral satellite images. The land cover classification was conducted in Concord, New Hampshire, USA, and South Korea by using multispectral images acquired from 30-m Landsat-8 and 500-m Geostationary Ocean Color Imager images. For the construction of input data specific to CNNs, two seasons (winter and summer) of multispectral bands were transformed into 2-D spectral curve graphs for each class. Land cover classification results of CNNs were compared with the results of support vector machines (SVMs) and random forest (RFs). The CNNs model showed higher performance than RFs and SVMs in both study sites. The examination of land cover classification maps demonstrates a good agreement with reference maps, Google Earth images, and existing global scale land cover map, especially for croplands. Using the spectral curve graph could incorporate the phenological cycles on classifying the land cover types. This study shows that the use of a new transformation of spectral bands into a 2-D form for application in CNNs can improve land cover classification performance. -
dc.identifier.bibliographicCitation IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, v.11, no.12, pp.4604 - 4617 -
dc.identifier.doi 10.1109/JSTARS.2018.2880783 -
dc.identifier.issn 1939-1404 -
dc.identifier.scopusid 2-s2.0-85058126797 -
dc.identifier.uri -
dc.identifier.url -
dc.identifier.wosid 000455462100006 -
dc.language 영어 -
dc.title Convolutional Neural Network-Based Land Cover Classification Using 2-D Spectral Reflectance Curve Graphs With Multitemporal Satellite Imagery -
dc.type Article -
dc.description.isOpenAccess FALSE -
dc.relation.journalWebOfScienceCategory Engineering, Electrical & Electronic; Geography, Physical; Remote Sensing; Imaging Science & Photographic Technology -
dc.relation.journalResearchArea Engineering; Physical Geography; Remote Sensing; Imaging Science & Photographic Technology -
dc.description.journalRegisteredClass scie -
dc.description.journalRegisteredClass scopus -
dc.subject.keywordAuthor Convolutional neural networks (CNNs) -
dc.subject.keywordAuthor Geo-stationary Ocean Color Imager (GOCI) -
dc.subject.keywordAuthor land cover classification -
dc.subject.keywordAuthor Landsat-8 -
dc.subject.keywordAuthor multitemporal -
dc.subject.keywordAuthor phenological cycle -
dc.subject.keywordAuthor spectral curve graph -
dc.subject.keywordPlus SUPPORT VECTOR MACHINE -
dc.subject.keywordPlus COCHRANS Q-TEST -
dc.subject.keywordPlus TIME-SERIES -
dc.subject.keywordPlus SCENE CLASSIFICATION -
dc.subject.keywordPlus IMPERVIOUS SURFACE -
dc.subject.keywordPlus RANDOM FOREST -
dc.subject.keywordPlus GOOGLE EARTH -
dc.subject.keywordPlus CROP -
dc.subject.keywordPlus NDVI -
dc.subject.keywordPlus TM -


Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.