Browse > Article
http://dx.doi.org/10.11108/kagis.2015.18.4.100

Analysis of Land Cover Classification and Pattern Using Remote Sensing and Spatial Statistical Method - Focusing on the DMZ Region in Gangwon-Do -  

NA, Hyun-Sup (Dept. of Forest Management, Kangwon National University)
PARK, Jeong-Mook (Dept. of Forest Management, Kangwon National University)
LEE, Jung-Soo (Dept. of Forest Management, Kangwon National University)
Publication Information
Journal of the Korean Association of Geographic Information Studies / v.18, no.4, 2015 , pp. 100-118 More about this Journal
Abstract
This study established a land-cover classification method on objects using satellite images, and figured out distributional patterns of land cover according to categories through spatial statistics techniques. Object-based classification generated each land cover classification map by spectral information, texture information, and the combination of the two. Through assessment of accuracy, we selected optimum land cover classification map. Also, to figure out spatial distribution pattern of land cover according to categories, we analyzed hot spots and quantified them. Optimal weight for an object-based classification has been selected as the Scale 52, Shape 0.4, Color 0.6, Compactness 0.5, Smoothness 0.5. In case of using the combination of spectral information and texture information, the land cover classification map showed the best overall classification accuracy. Particularly in case of dry fields, protected cultivation, and bare lands, the accuracy has increased about 12 percent more than when we used only spectral information. Forest, paddy fields, transportation facilities, grasslands, dry fields, bare lands, buildings, water and protected cultivation in order of the higher area ratio of DMZ according to categories. Particularly, dry field sand transportation facilities in Yanggu occurred mainly in north areas of the civilian control line. dry fields in Cheorwon, forest and transportation facilities in Inje fulfilled actively in south areas of the civilian control line. In case of distributional patterns according to categories, hot spot of paddy fields, dry fields and protected cultivation, which is related to agriculture, was distributed intensively in plains of Yanggu and in basin areas of Cheorwon. Hot spot areas of bare lands, waters, buildings and roads have similar distribution patterns with hot spot areas related to agriculture, while hot spot areas of bare lands, water, buildings and roads have different distributional patterns with hot spot areas of forest and grasslands.
Keywords
DMZ; Object-Based Classification; Land-Cover Classification; Hotspots Analysis;
Citations & Related Records
Times Cited By KSCI : 7  (Citation Analysis)
연도 인용수 순위
1 An, C.K. 2013. A study on the systematic management measures of natural resources in the demilitarizes. Master Thesis, Univ. of Dankook, Korea. pp.1-3 (안치권. 2013. 비무장지대 일원자원의 체계적 관리방안에 관한 연구. 단국대학교 대학원 석사학위논문. 1-3쪽).
2 Benz, U.C., P. Hofmann, G. Willhauck, I. Lingenfelder and M. Heynen. 2004. Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS Journal of Photogrammetry and Remote Sensing 58(2004):239-258.   DOI
3 Blaschke, T. 2010. Object based image analysis for remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing 65(2010):2-16.   DOI
4 Coburn, C.A. and A.C.B. Robert. 2004. A multiscale texture analysis procedure to improve forest stand classification. International Journal of Remote Sensing 20(2):4287-4308.
5 Griffith. D.A. 2009. Spatial Autocorrelation. International Encyclopedia of Human Geography. pp.308-316.
6 Ham, B.Y., C.Y. Lee, H.K. Byun and B.K. Min. 2013. A study on detection of deforested land using aerial photographs. Journal of The Korea Society For Geospatial Information Science 21(3):11-17 (함보영, 이천용, 변혜경, 민병걸. 2013. 항공사진을 이용한 훼손 산지 탐지연구. 한국지형공간정보학회지 21(3):11-17).
7 Han, J.Y. 2013. Space design policy alternative for the creation of the DMZ Peace park. Korean Institute of Spatial Design 8(3):137-145 (한정엽. 2013. DMZ 평화공원조성을 위한 공간디자인 정책방안. 한국공간디자인학회논문집 8(3):137-145).
8 Haralik, R.M., K. Shanmugam and I. Dinstein. 1973. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics SMC-3(6):610-621.   DOI
9 Hyun, C.U. and H.D. Park. 2012. Assessment of topographic normalization in Jeju island with Landsat7 ETM+ and ASTER GDEM data. Korean Journal of Remote Sensing 28(4):393-407 (현창욱, 박형동. 2012. Landsat ETM+영상과 ASTER GDEM자료를 이용한 제주도 지역의 지형보정 효과 분석. 대한원격탐사학회지 28(4):393-407).   DOI
10 Kim, C.H. 2009. The survey of disappeared villages in the demilitarized zone. Journal of the Korean Association of Geographic Information Studies 12(1):96-105 (김창환. 2009. DMZ 내 사라진 마을의 공간적 분포와 특성. 한국지리정보학회지 12(1):96-105).
11 Kim, D.H., H.S. Kim and C.H. Oh. 2008. The injury status of forest around the Korea demilitarized. Proceedings of Korean Society of Environment and Ecology. pp.77-79 (김동효, 김한수, 오충현. 2008. DMZ일원 산림훼손 현황. 한국환경생태학회 학술발표논문집. 77-79쪽).
12 Kim, H.O. and J.M. Yeom. 2012. A study on object-based image analysis methods for land cover classification in agricultural areas. Journal of the Korean Association of Geographic Information Studies 15(4):26-41 (김현옥, 염종민. 2012. 농촌지역 토지피복분류를 위한 객체기반 영상분석기법 연구. 한국지리정보학회지 15(4):26-41).   DOI
13 Kim, M.J. 2014. Spatial agglomeration pattern analysis using Geis-ord's Gi and FLQ: in case of knowledge-based industries in Gyeonggi province. Journal of the Korean Cartographic Association 14(1):107-123 (김명진. 2014. Geisord's Gi와 FLQ를 이용한 공간 집적 분석:경기도 지식기반산업을 대상으로. 한국지도학회지 14(1):107-123).   DOI
14 Kim, S.W. 2003. Preparation of land cover and use map by object oriented classification of IKONOS imagery. Master Thesis, Univ. of Korea, Seoul, Korea. pp.41-45 (김상우. 2003. IKONOS 영상의 객체지향 분류방식에 의한 토지피복 및 이용도 제작. 고려대학교 대학원 석사학위논문. 41-45쪽).
15 Kim, T.G. and K.S. Lee. 2003. Analysis of texture information of forest stand on high resolution satellite imagery. Proceedings of the Spring and Fall of Journal of Korea Spatial Information Society pp.145-150 (김태근, 이규성. 2003. 임분 특성에 따른 고해상도 위성영상의 Texture 정보 분석. 한국공간정보학회춘.추계 학술대회논문집. 145-150쪽).
16 Lee, K.W., S.H. Jeon and B.D. Kwon. 2005. Implementation of GLCM/GLDV -based texture algorithm and its application to high resolution imagery analysis. Korean Journal of Remote Sensing 21(2):121-133 (이기원, 전소희, 권병두. 2005. GLCM/GLDV기반 Texture 알고리즘 구현과 고해상도 영상분석 적용. 대한원격탐사학회지 21(2):121-133).
17 Korea Forest Service. 2011. Comprehensive measures for the forest management of DMZ. pp.40-42 (산림청. 2011. DMZ일원의 산림관리 종합대책. 40-42쪽).
18 Lee. J.B., D.Y. Heo and Y.D. Eo. 2007. Study on selection of optimized segmentation parameters and analysis of classification accuracy for objectoriented classification. Korean Journal of Remote Sensing 23(6):521-528 (이정빈, 허준, 어양담. 2007. 객체기반 영상분류에서 최적 가중치 선정과 정확도 분석 연구. 대한원격탐사학회지 23(6):521-528).
19 Lee, J.H., S.I. Kim, K.S. Han and Y.W. Lee. 2011. Hotspot detection for land cover changes using spatial statistical methods. Korean Journal of Remote Sensing 27(5):601-611 (이정훈, 김상일, 한경수, 이양원. 2011. 공간통계기법을 이용한 토지피복변화의 핫스팟탐지. 대한원격탐사학회 27(5):601-611).   DOI
20 Lee, M.B., N.S. Kim, S.Z. Jin and H.D. Kim. 2008. A study on the soil erosion by landuse in the Imjin river basin, DMZ of cental Korea. Journal of the Korean Geographical Society 43(3):263 -275 (이민부, 김남신, Shuzhu Jin, 김항덕. 2008. 임진강유역의 토지이용에 따른 지표침식에 관한 연구. 대한지리학회지 43(3):263-275).
21 Ministry of Environment. 2014. Establishing sub-classification land cover maps using satellite image(5th) and the national. pp.3-60 (환경부. 2014. 영상자료를 이용한 세분류 토지피복지도 구축(5차) 및 국가환경지도시스템 주제도 제작. 3-60쪽).
22 Ministry of Environment and National Institute of Environmental Research. 2010. 2010 Ecological and environmental excellence excavation area. pp.146-147 (환경부, 국립환경과학원. 2010. 2010 생태 환경 우수지역 발굴조사. 78-125쪽).
23 Ministry of Environment and National Institute of Environmental Research. 2012. Ecological survey of the DMZ. pp.146-147 (환경부, 국립환경과학원. 2012. DMZ일원 생태계 조사. 146-147쪽).
24 Pu, R., S. Landry and Q. Yu. 2011. Object-based urban detailed land cover classification with high spatial resolution IKONOS imagery. International Journal of Remote Sensing 32(12):3285-3308.   DOI
25 Oh, C.Y., S.Y. Park, H.S. Kim, Y.W. Lee and C.U. Choi. 2010. Comparison of landcover map accuracy using high resolution satellite imagery. Journal of the Korean Association of Geographic Information Studies 13(1):89-100 (오치영, 박소영, 김형석, 이양원, 최철웅. 2010. 고해상도 위성영상의 토지피복분류와 정확도 비교 연구. 한국지리정보학회지 13(1):89-100).
26 Park, J.J., C.Y. Ku and B.S. Kim. 2007. Improvement of the level-2 land cover map with satellite image. The Journal of GIS Association of Korea 15(1):67-80 (박정재, 구자용, 김병선. 2007. 위성영상을 이용한 중분류 토지피복도의 제작과정 개선. 한국 GIS학회지 15(1):67-80).
27 Park, J.M. 2013. Land cover classification and change analysis using pixel-based and object-based. Master Thesis, Univ. of Gangwon, Kangwon-do, Korea. pp.13-14 (박정묵. 2013. 토지피복 변화탐지의 정확도 향상을 위한 픽셀 및 객체기반 분석기법 연구. 강원대학교 대학원 석사학위논문. 13-14쪽).
28 Research Institute for Gangwon. 2014. The DMZ of Gangwon province and its implications for redesigning the Korean peninsula. pp.15-81 (강원발전연구원. 2014. 강원도 DMZ와 한반도 공간관리. 15-81쪽).
29 Roy, A. and V.K. Srivastava. 2012. Geospatial approach to identification of potential hotspots of land-use and land-cover change for biodiversity conservation. Current Science 102(8):1174-1180.
30 Seol, K.J. 2005. A study on the classification of high-resolution satellite image by texture analysis : focus on the extracting urban area. Master Thesis, Univ. of Sangmyoung, Seoul, Korea. pp.38-41 (설경진. 2005. 텍스쳐 분석에 의한 고해상도 위성영상의 분류. 상명대학교 대학원 석사학위논문. 38-41쪽).
31 Son, K.W. 2015. Significance of DMZ world peace park and directions to pursue. Journal of Policy Sciences 23(2):129-143 (손기웅. 2014. 세계평화 공원의 의의와 추진방향. 정책과학연구 23(2):129-143).
32 Statistics Korea. 2013. Gangwon Statistical Yearbook. pp.43-49 (통계청. 2013. 강원도 기본통계. 43-49쪽).
33 Vadrevu, K.P., I. Csiszar, E. Ellicott, L. Giglio, K.V.S. Badarinath, E. Vermote and C. Justice. 2013. Hotspot analysis of vegetation fires and intensity in the Indian region. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 6(1):22-238.