• 대한원격탐사학회지
• /
• 제21권5호
• /
• pp.405-415
• /
• 2005

It is difficult to classify tidal flat surface that is composed of a mixture of mud, sand, water and microphytobenthos. We used a Linear Spectral Unmixing (LSU) method for effectively classifying the tidal flat surface characteristics within a pixel. This study aims at 1) detecting algal mat using LSU in the Saemangeum tidal flats, 2) determining a suitable end-member selection method in tidal flats, and 3) find out a habitual characteristics of algal mat. Two types of end-member were built; one is a reference end-member derived from field spectrometer measurements and the other image end-member. A field spectrometer was used to measure spectral reflectance, and a spectral library was accomplished by shape difference of spectra, r.m.s. difference of spectra, continuum removal and Mann-Whitney U-test. Reference end-members were extracted from the spectral library. Image end-members were obtained by applying Principle Component Analysis (PCA) to an image. The LSU method was effective to detect microphytobenthos, and successfully classified the intertidal zone into algal mat, sediment, and water body components. The reference end-member was slightly more effective than the image end-member for the classification. Fine grained upper tidal flat is generally considered as a rich habitat for algal mat. We also identified unusual microphytobenthos that inhabited coarse grained lower tidal flats.

• 환경영향평가
• /
• 제17권2호
• /
• pp.105-112
• /
• 2008

Human activity has been the major threat to wetlands. Agriculture, industrial development, and urban and suburban sprawl have caused the greatest losses of coastal wetlands. In fact, riceland agriculture, because of the flooding that goes with it, provides some additional wetland habitat not otherwise available. The biggest current source of loss for freshwater coastal wetlands is from urban sprawl. In this study, spatial analysis method such as landscape index were applied to Sihwa area in Ansan city. The SMA (Spectral Mixture Analysis) method using Landsat image showed the change distribution of wetland vegetation from 1996 to 2004. The southern part of Sihwa wetland have been changed with Suda japonica of 24% and reed vegetation of 34% on coastal wetland which were covered with tidal flat.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 춘계학술대회 논문집
• /
• pp.279-282
• /
• 2006

분광혼합은 위성영상에서 공간해상도의 한계로 인해 다른 분광 속성을 가진 물질들이 하나의 픽셀 내에 존재하게 될 때 발생하게 된다. 이러한 문제를 해결하고자 분광분리 알고리즘을 통해 픽셀의 순수한 영역만을 선정하여 정확도 높은 탐지가 가능하도록 하는 분광혼합분석(Spectral Mixture Analysis, 이하 SMA)을 고해상도 영상에 적용하였다. 본 연구는 산림의 훼손이 심각한 강원도 정선군 임계지역의 QuickBird 다중분광 위성영상을 이용하였다. 주성분분석(Principal Component Analysis, 이하 PCA)으로 생성된 결과 영상의 1, 2, 3번 밴드를 추출한 후에 밴드간의 Scatter plots 내에서 끝지점에 위치하는 Endmember를 3개(나지, 산림, 초지) 선정하였다. 선정된 Endmember를 토대로 작성된 fraction 영상을 이용하여 강원도 임계지역의 산림훼손으로 초지와 나지로 변화된 지역을 탐지하여 보았다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.848-851
• /
• 2006

Green vegetation is one of the most critical factors for environment conditions thorough modulating evapotranspiration and absorption of solar radiation. Thus, fractional green vegetation cover (FVC) plays an important role in observing and managing environment. Remote sensing provides a seemingly obvious data source for quantifying FVC over large area. Therefore we compared a set of methods for estimating FVC using hyperspectral remote sensing data. For our study, we used Hyperion imagery acquired in April, 2002. In order to achieve our efforts, we analyzed simple NDVI-based method and spectral mixture analysis (SMA) models that were applied a variety of combinations of possible endmembers.

• 한국GIS학회:학술대회논문집
• /
• 한국GIS학회 2003년도 공동 춘계학술대회 논문집
• /
• pp.157-162
• /
• 2003

중저해상도 광학영상의 순간시야각(instantaneous filed of view -IFOV)에 포함되는 공간에는 반사특성이 상이한 두 개 이상의 지표물이 존재하는 경우가 대부분이다. 영상분류와 같은 기존의 영상처리기법에서는 하나의 화소가 단일의 지표물을 대표한다는 가정에서 접근하였으나, 최근 화소의 혼합정도를 세분하는 분광혼합분석(spectral mixture analysis)기법이 개발되고 있다. 분광혼합분석법을 이용하여 혼합된 화소에 포함된 지표물을 분해(unmixing) 하고 그 효과를 분석하고자 하여 경기도 광릉국립수목원의 시험림 지역을 대상으로 Landsat-7 ETM＋영상을 이용하여 선형혼합 모델을 적용하였고, 그 결과 각각의 화소를 6개의 End-member의 혼합비로 구분하였다. Endmember의 비율을 나타낸 영상을 분석하여 점유비율에 따른 활엽수와 침엽수의 구분을 할 수 있었고, 각 임상별의 특징도 얻을 수 있었다. 특히 침엽수의 경우 그림자의 효과가 높다는 특성도 파악 할 수 있었다. 분광혼합분석법은 기존의 전통 분류방법과는 달리 다양한 산림의 정보를 추출해 낼 수 있다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2005년도 한국컴퓨터종합학술대회 논문집 Vol.32 No.1 (B)
• /
• pp.769-771
• /
• 2005

In this paper we present a method of separating musical instrument sound sources from their monaural mixture, where we take the harmonic structure of music into account and use the sparseness and the overlapping NMF [1] to select representative spectral basis vectors which are used to reconstruct unmixed sound. A method of spectral basis selection is illustrated and experimental results with monaural mixture of voice/cello and trumpet/viola are shown to confirm the validity of our proposed method.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2010년도 춘계학술대회 논문집
• /
• pp.819-820
• /
• 2010

• 한국GIS학회:학술대회논문집
• /
• 한국GIS학회 2004년도 GIS/RS 공동 춘계학술대회 논문집
• /
• pp.517-521
• /
• 2004

• 말소리와 음성과학
• /
• 제6권4호
• /
• pp.127-132
• /
• 2014

This paper describes a robust speech recognition technique by reconstructing spectral components mismatched with a training environment. Although the cluster-based reconstruction method can compensate the unreliable components from reliable components in the same spectral vector by assuming an independent, identically distributed Gaussian-mixture process of training spectral vectors, the presented method exploits the temporal dependency of speech to reconstruct the components by introducing a hidden-Markov-model prior which incorporates an internal state transition plausible for an observed spectral vector sequence. The experimental results indicate that the described method can provide temporally consistent reconstruction and further improve recognition performance on average compared to the conventional method.

• Journal of Information Processing Systems
• /
• 제14권1호
• /
• pp.218-227
• /
• 2018

Vocal effort detection is important for both robust speech recognition and speaker recognition. In this paper, the spectral information entropy feature which contains more salient information regarding the vocal effort level is firstly proposed. Then, the model fusion method based on complementary model is presented to recognize vocal effort level. Experiments are conducted on isolated words test set, and the results show the spectral information entropy has the best performance among the three kinds of features. Meanwhile, the recognition accuracy of all vocal effort levels reaches 81.6%. Thus, potential of the proposed method is demonstrated.