Evaluating the Contribution of Spectral Features to Image Classification Using Class Separability

다국어 초록 (Multilingual Abstract)

Image classification needs the spectral similarity comparison between spectral features of each pixel and the representative spectral features of each class. The spectral similarity is obtained by computing the spectral feature vector distance between the pixel and the class. Each spectral feature contributes differently in the image classification depending on the class separability of the spectral feature, which is computed using a suitable vector distance measure such as the Bhattacharyya distance. We propose a method to determine the weight value of each spectral feature in the computation of feature vector distance for the similarity measurement. The weight value is determined by the ratio between each feature separability value to the total separability values of all the spectral features. We created ten spectral features consisting of seven bands of Landsat-8 OLI image and three indices, NDVI, NDWI and NDBI. For three experimental test sites, we obtained the overall accuracies between 95.0% and 97.5% and the kappa coefficients between 90.43% and 94.47%.

참고문헌 (Reference)

1 유희영, "고해상도 다중시기 위성영상을 이용한 밭작물 분류: 마늘/양파 재배지 사례연구" 대한원격탐사학회 33 (33): 621-630, 2017

2 Zha, Y., "Use of normalized difference built-up index in automatically mapping urban areas from TM imagery" 24 (24): 583-594, 2003

3 Mcfeeters, S. K., "The use of normalized difference water index (NDWI) in the delineation of open water features" 17 (17): 1425-1432, 1996

4 Szabo, S., "Specific features of NDVI, NDWI and MNDWI as reflected in land cover categories" 10 (10): 194-202, 2016

5 Nussbaum, S., "Object-based image analysis and treaty verification: new approaches in remote sensing-applied to nuclear facilities in Iran" Springer Science & Business Media 2008

6 Rouse, J. W., "Monitoring vegetation systems in the Great Plains with ERTS" NASA 1 : 309-317, 1974

7 Park, J. H., "Improvement of classification accuracy using index image combination" 619-620, 2018

8 정윤식, "IIR과 EO 영상 융합 환경의 표적 크기추정 알고리즘 F-TSE 연구" 제어·로봇·시스템학회 23 (23): 138-143, 2017

9 Ye, C. S., "Feature weight determination based on class separability" 2019

10 손민석, "Dempster-Shafer Theory 기반의 CCD-IR 영상 융합 기법을 이용한 주/야간 보행자 검출 성능 향상 연구" 제어·로봇·시스템학회 23 (23): 482-487, 2017

11 예철수, "Classification of Fused SAR/EO Images Using Transformation of Fusion Classification Class Label" 대한원격탐사학회 28 (28): 671-682, 2012

12 Abraham T. Magpantay, "Analysis on the Effect of Spectral Index Images on Improvement of Classification Accuracy of Landsat-8 OLI Image" 대한원격탐사학회 35 (35): 561-571, 2019

13 전우현, "An Assessment of a Random Forest Classifier for a Crop Classification Using Airborne Hyperspectral Imagery" 대한원격탐사학회 34 (34): 141-150, 2018