Browse > Article
http://dx.doi.org/10.22640/lxsiri.2016.46.2.239

The Study on Improving Accuracy of Land Cover Classification using Spectral Library of Hyperspectral Image  

Park, Jung-Seo (Department of Civil Engineering, Chonbuk National University)
Seo, Jin-Jae (Department of Civil Engineering, Chonbuk National University)
Go, Je-Woong (Department of Civil Engineering, Songwon University)
Cho, Gi-Sung (Department of Civil Engineering, Chonbuk National University, RCIT)
Publication Information
Journal of Cadastre & Land InformatiX / v.46, no.2, 2016 , pp. 239-251 More about this Journal
Abstract
Hyperspectral image is widely used for land cover classification because it has a number of narrow bands and allow each pixel to include much more information in comparison with previous multi-spectral image. However, Higher spectral resolution of hyperspectral image results in an increase in data volumes and a decrease in noise efficiency. SAM(Spectral Angle Mapping), a method based on vector inner product to compare spectrum distribution, is a highly valuable and popular way to analyze continuous spectrum of hyperspectral image. SAM is shown to be less accurate when it is used to analyze hyperspectral image for land cover classification using spectral library. this inaccuracy is due to the effects of atmosphere. We suggest a decision tree based method to compensate the defect and show that the method improved accuracy of land cover classification.
Keywords
Hyperspectral image; SAM(Spectral Angle Mapping); decision tree; land cover classification; spectral library;
Citations & Related Records
연도 인용수 순위
  • Reference
1 신정일, Yasser Maghsoudi, 김선화, 강성진, 이규성. 2008. 지상 초분광카메라 영상의 복사보전. 대한원격탐사학회. 24(2):213-222. Shin JI, Yasser Maghsoudi, Kim SW, Kang SJ, Lee KS. 2008. Vicarious Radiometric Calibration of the Ground-based Hyperspectral Gamera Image. Journal of Korean Society of Remote Sensing. 24(2):213-222.
2 신정일, 김선화, 이규성. 2010. 한반도 지역의 지표특성을 고려한 분광라이버리의 설계 및 구축. 대한원격탐사학회지. 26(5):465-475. Shin JI, Kim SW, Lee KS. 2010. Design and Construction of Spectral Library for the Korean Peninsular. Journal of Korean Society of Remote Sensing. 26(5):465-475.
3 이강철. 2014. 항공 하이퍼스펙트럴 영상을 이용한 토지피복분류. 석사학위논문. 전북대학교 산업기술대학원. Lee KC. 2014. Land Cover Classification Using Airborn Hyperspectral Imagery [Thesis]. Chonbuk National University.
4 조형갑. 2014. 수종분류를 위한 초분광영상과 다중분광영상의 정량적 비교 분석. 석사학위논문. 인하대교대학원. Cho HG. 2014. Quantitative Comparison Between Hyperspectral and Multispectral Image for Classification of Tree Species [Thesis]. Inha University.
5 Adams JB, Gillespie AR. 2006. Remote Sensing of Landscapes with Spectral Images-A Physical Modeling Approach. United Kingdom at the University Press Cambridge.
6 Clark RN, S wayze GA, Gallagher AJ, K ing A J, Calvin WM. 1993. The U. S. Geological Survey, Digital Spectral Library : Version 1 (0.2 to 3.0${\mu}m$). U.S. Geological Survey. Open file report. 95:592.
7 Geostroy. 2016a. CASI 1500 [Internet]. [http://www.geostory.co.kr/equipment/hyper.php]. Last accessed 24 November 2016.
8 Geostroy. 2016b. FieldSpec 3 [Internet]. [http://www.geostory.co.kr/equipment/spectroscope.php]. Last accessed 24 November 2016.
9 Kruse FA, Lefkorff AB, Boardman JW, Heiedbrecht KB, Shapiro AT, Barloon PJ, Goetz AFH. 1993. The Spectral Image Processing System(SIPS)-Interactive Visualization and Analysis of Imaging Spectrometer Data. Remote Sensing of Environment. 44:145-163.   DOI
10 Van der Meer FD, De Jong SM. 2001. Imaging Spectrometry : Basic Principles and Prospective Application. Kluwer Academic Puplishers.
11 김대성, 김진곤, 변용기, 김용일. 2004. 무감독 SAM 기법을 이용한 하이퍼스펙트럴 영상 분류. 한국 측량학회 춘계 학술발표회 논문집. p. 159-164. Kim DS, Kim JG, Byun YK, Kim YI. 2004. The Hyperspectral Image Classification with the Unsupervised SAM. The spring conference of KSGPC. p. 159-164.
12 Van der Meer FD. 2006. The Effectiveness of Spectral Similarity Measure for the Analysis of hyperspectral Imagery. International Journal of Applied Earth Observation and Geoinformation. 8(1):3-17.   DOI
13 김대성. 2010. Hyperion 초분광영상의 분광정보를 이용한 하이브리드 변화 탐지 기법 연구. 박사학위논문. 서울대학교 대학원. Kim DS. 2010. Hybrid Change Detection using Spectral Profile Information of Hyperion Hyperspectral Images-Focusing on Unsupervised change Detection [Thesis]. Seoul National University.