• 대한원격탐사학회지
• /
• 제36권1호
• /
• pp.55-65
• /
• 2020

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%.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2004년도 추계학술발표회 논문집
• /
• pp.251-256
• /
• 2004

The image classification is one of the most important studies in the remote sensing. In general, the MLC(Maximum Likelihood Classification) classification that in consideration of distribution of training information is the most effective way but it produces a bad result when we apply it to actual hyperspectral image with the same classification technique. The purpose of this research is to reveal that which one is the most effective and suitable way of the classification algorithms iii the hyperspectral image classification. To confirm this matter, we apply the MLC classification algorithm which has distribution information and SAM(Spectral Angle Mapper), SFF(Spectral Feature Fitting) algorithm which use average information of the training class to both multispectral image and hyperspectral image. I conclude this result through quantitative and visual analysis using confusion matrix could confirm that SAM and SFF algorithm using of spectral pattern in vector domain is more effective way in the hyperspectral image classification than MLC which considered distribution.

• 대한원격탐사학회지
• /
• 제22권2호
• /
• pp.111-121
• /
• 2006

분광각(Spectral Angle)을 이용한 분류는 같은 종류의 지표 대상물의 분광 특성이 대기 및 지형적인 영향으로 인해 원점을 기준으로 유사한 분광각을 가지며, 선형적인 분포 모양을 가진다는 가정에 기초한 분류 방식이다. 최근 분광각을 이용한 무감독 분류에 대한 연구가 활발히 이루어지고 있으나, 하이퍼스펙트럴 데이터의 특성을 반영한 효과적인 무감독 분류에 대한 연구는 미진한 상태이다 본 연구는 하이퍼스펙트럴 영상 분류에 있어서 기존 무감독 분광각 분류(USAC, Unsupervised Spectral Angle Classification) 연구에서 나타난 문제점들을 보완한 반복최적화 무감독 분광각 분류(ISOUSAC, Iterative Self-Organizing USAC) 기법을 제안하고 있다. 이를 위해, 무감독 분광각 분류에 적합한 각 분할(Angle Range Division) 기법을 적용하여 군집 초기 중심을 설정하였고, 군집 중심 계산에 있어서 각 중심을 이용하였다. 뿐만 아니라 병합(Merge)과 분할(Split)를 통한 유동적인 군집 분석을 수행하였다. 결과를 통해, 제안된 알고리즘이 기존의 기법보다 수행 시간뿐 아니라 시각적, 정량적인 면에서 우수한 결과를 도출하였으며, 분광각을 이용한 군집 유효성 지수(Validity Index)를 제안함으로써 기존의 무감독 분광각 분류와 정량적 비교를 수행하였다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.361-364
• /
• 2008

It is well known that combining spatial and spectral information can improve land use classification from satellite imagery. High spatial resolution classification has a limitation when only using the spectral information due to the complex spatial arrangement of features and spectral heterogeneity within each class. Therefore, extracting the spatial information is one of the most important steps in high resolution satellite image classification. In this paper, we propose a new spatial feature extraction method. The extracted features are integrated with spectral bands to improve overall classification accuracy. The classification is achieved by applying a Support Vector Machines classifier. In order to evaluate the proposed feature extraction method, we applied our approach to KOMPSAT-2 data and compared the result with the other methods.

• 대한원격탐사학회지
• /
• 제35권4호
• /
• pp.561-571
• /
• 2019

In this paper, we analyze the effect of the representative spectral indices, normalized difference vegetation index (NDVI), normalized difference water index (NDWI) and normalized difference built-up index (NDBI) on classification accuracies of Landsat-8 OLI image.After creating these spectral index images, we propose five methods to select the spectral index images as classification features together with Landsat-8 OLI bands from 1 to 7. From the experiments we observed that when the spectral index image of NDVI or NDWI is used as one of the classification features together with the Landsat-8 OLI bands from 1 to 7, we can obtain higher overall accuracy and kappa coefficient than the method using only Landsat-8 OLI 7 bands. In contrast, the classification method, which selected only NDBI as classification feature together with Landsat-8 OLI 7 bands did not show the improvement in classification accuracies.

• 한국컴퓨터정보학회논문지
• /
• 제22권1호
• /
• pp.9-14
• /
• 2017

In this paper, we propose that the contrast features of octave spectrum can be used to show spectral contrast features of some music clips. It shows the relative spectral distribution rather than average spectrum. From the experiment, it can be seen the method of spectral contrast features has a good performance in classification of music styles. Another comparative experiment shows that the method of spectral contrast features can better distinguish different music styles than the method of MFCC features that commonly used previously in the classification system of music styles.

• 한국음향학회지
• /
• 제29권4호
• /
• pp.265-269
• /
• 2010

본 논문에서는 새로운 형태의 스펙트럼 특징인 스펙트럼 대비 MFCC (SCMFCC)를 제안하고 음악 장르 분류 성능을 분석하였다. 음악 장르 분류를 위해서는 장르 간의 차이를 두드러지게 할 수 있는 특징을 사용해야 하므로, 음악의 화음 구조 및 강약을 잘 표현하는 스펙트럼 대비 특징들이 관심을 받아왔다. 본 논문에서 제안된 SCMFCC는 멜 켑스트럼 상에서 스펙트럼의 대비를 이용하여 기존의 MFCC를 음악 분류에 적합하도록 변형했다. 널리 사용되고 있는 음악 장르 데이터베이스에서 실험을 수행하여, 제안된 SCMFCC 특징의 음악 장르 분류 성능을 기존의 다른 특징들과 비교하였다.

• 대한원격탐사학회지
• /
• 제31권4호
• /
• pp.303-319
• /
• 2015

The objectives of this paper are to measure surface imperviousness using three different classification methods: per-pixel, sub-pixel, and object-oriented classification. They are tested on high-spatial resolution QuickBird data at 2.4 meters (four spectral bands and three principal component bands) as well as a medium-spatial resolution Landsat TM image at 30 meters. To measure impervious surfaces, we selected 30 sample sites with different land uses and residential densities across image representing the city of Phoenix, Arizona, USA. For per-pixel an unsupervised classification is first conducted to provide prior knowledge on the possible candidate spectral classes, and then a supervised classification is performed using the maximum-likelihood rule. For sub-pixel classification, a Linear Spectral Mixture Analysis (LSMA) is used to disentangle land cover information from mixed pixels. For object-oriented classification several different sets of scale parameters and expert decision rules are implemented, including a nearest neighbor classifier. The results from these three methods show that the object-oriented approach (accuracy of 91%) provides more accurate results than those achieved by per-pixel algorithm (accuracy of 67% and 83% using Landsat TM and QuickBird, respectively). It is also clear that sub-pixel algorithm gives more accurate results (accuracy of 87%) in case of intensive and dense urban areas using medium-resolution imagery.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.134-137
• /
• 2005

Unsupervised spectral angle classification (USAC) is the algorithm that can extract ground object information with the minimum 'Spectral Angle' operation on behalf of 'Spectral Euclidian Distance' in the clustering process. In this study, our algorithm uses the unit vector instead of the spectral distance to compute the mean of cluster in the unsupervised classification. The proposed algorithm (MUSAC) is applied to the Hyperion and ETM+ data and the results are compared with K-Meails and former USAC algorithm (FUSAC). USAC is capable of clearly classifying water and dark forest area and produces more accurate results than K-Means. Atmospheric correction for more accurate results was adapted on the Hyperion data (Hyperion-FLAASH) but the results did not have any effect on the accuracy. Thus we anticipate that the 'Spectral Angle' can be one of the most accurate classifiers of not only multispectral images but also hyperspectral images. Furthermore the cluster unit vector can be an efficient technique for determination of each cluster mean in the USAC.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.820-824
• /
• 2003

One of the most important research areas on remote sensing is spectral unmixing of hyper-spectral data. For spectral unmixing of hyper spectral data, accurate land cover information is necessary. But obtaining accurate land cover information is difficult process. Obtaining land cover information from high-resolution data may be a useful solution. In this study spectral signature of endmembers on ASTER acquired in October was calculated from land cover information on IKONOS acquired in September. Then the spectral signature of endmembers applied to ASTER images acquired on January and March. Then the result of spectral unmxing of them evauateted. The spectral signatures of endmembers could be applied to different seasonal images. When it applied to an ASTER image which have similar zenith angle to the image of the spectral signatures of endmembers, spectral unmixing result was reliable. Although test data has different zenith angle from the image of spectral signatures of endmembers, the spectral unmixing results of urban and vegetation were reliable.