Publications
Detailed Information
Comparison of error metrics in iterative error analysis algorithm for endmember extraction from hyperspectral data : 초다분광 영상의 endmember 추출을 위한 iterative error analysis 알고리즘에서의 오차 측정방법 비교
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 박형동 | - |
dc.contributor.author | 최영민 | - |
dc.date.accessioned | 2017-07-14T03:19:02Z | - |
dc.date.available | 2017-07-14T03:19:02Z | - |
dc.date.issued | 2015-02 | - |
dc.identifier.other | 000000024853 | - |
dc.identifier.uri | https://hdl.handle.net/10371/123484 | - |
dc.description | 학위논문 (석사)-- 서울대학교 대학원 : 에너지시스템공학부, 2015. 2. 박형동. | - |
dc.description.abstract | This study represents the effect of methods for estimating error in iterative error analysis (IEA) algorithm. Three different methods are presented for estimating error in each iteration: the L2-norm, which is used in the original IEA, the L1-norm and the spectral angle. For comparing the effect of applying those error metrics and evaluating the performance of each algorithm, two hyperspectral datasets, simulated and real hyperspectral images, were used. The results of endmember extraction with those algorithms were compared to spectral library by spectral distance and the 2-D plane projection of datasets.
The results with the simulated image indicated that the spectral angle based IEA algorithm performed better than other two IEAs, the original and the L1-norm based algorithm. The spectral angle based IEA selected correct locations of endmember pixels while other two algorithms worked poorly. In addition, the spectral angle IEA produced stable results with various signal-to-noise ratio (SNR). In particular, the algorithm with the spectral angle showed a robustness when the data was highly affected by changes in pixel brightness. The 2-D projection illustrated illumination insensitivity of the spectral angle based IEA algorithm. The experiment with the real hyperspectral data displayed similar results to those of the simulated image. Even though big difference was not detected, the spectral angle based IEA produced slightly better results of endmember spectra. The 2-D projection plane of extracted endmembers also showed that the spectral angle based algorithm produced reliable results when the image contains topographically complex regions. The result of this study suggest that the IEA algorithms with different error metrics produce different results and the algorithm based on the spectral angle error is a reliable approach to extract endmembers from the image of topographically complex region. | - |
dc.description.tableofcontents | Chapter 1 Introduction 1
Chapter 2 Theoretical Backgrounds 5 2.1 Linear Mixing Model 5 2.2 Linear Spectral Unmixing 7 2.3 Spectral Error Metrics 8 2.4 Comparison of Spectral Error Metrics 10 Chapter 3 The Modified IEA algorithms 13 3.1 Original IEA algorithm 13 3.2 IEA algorithm based on the Spectral Angle Error 15 3.3 IEA algorithm based on the L1-norm Error 15 Chapter 4 Description of Datasets 17 4.1 Simulated Hyperspectral Image 17 4.2 Real Hyperpsectral Image 20 Chapter 5 Results and Discussion 23 5.1 Evaluation with Simulated Hyperspectral Image 23 5.1.1 Results of Extracted Endmembers 23 5.1.2 Comparison of Endmembers on 2-D Plane 31 5.2 Evaluation with Real hyperpsectral image 34 5.2.1 Results of Extracted Endmembers 34 5.2.2 Comparison of Endmembers on 2-D Plane 42 Chapter 6 Conclusions 46 References 48 Abstract 52 | - |
dc.format | application/pdf | - |
dc.format.extent | 3036668 bytes | - |
dc.format.medium | application/pdf | - |
dc.language.iso | en | - |
dc.publisher | 서울대학교 대학원 | - |
dc.subject | Hyperspectral image | - |
dc.subject | endmember extraction | - |
dc.subject | iterative error analysis (IEA) | - |
dc.subject | spectral angle | - |
dc.subject.ddc | 622 | - |
dc.title | Comparison of error metrics in iterative error analysis algorithm for endmember extraction from hyperspectral data | - |
dc.title.alternative | 초다분광 영상의 endmember 추출을 위한 iterative error analysis 알고리즘에서의 오차 측정방법 비교 | - |
dc.type | Thesis | - |
dc.description.degree | Master | - |
dc.citation.pages | 53 | - |
dc.contributor.affiliation | 공과대학 에너지시스템공학부 | - |
dc.date.awarded | 2015-02 | - |
- Appears in Collections:
- Files in This Item:
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.