• 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 2007년도 Proceedings of ISRS 2007
• /
• pp.6-10
• /
• 2007

Classification of hyperspectral images is challenging. A very high dimensional input space requires an exponentially large amount of data to adequately and reliably represent the classes in that space. In other words in order to obtain statistically reliable classification results, the number of necessary training samples increases exponentially as the number of spectral bands increases. However, in many situations, acquisition of the large number of training samples for these high-dimensional datasets may not be so easy. This problem can be overcome by using multiple classifiers. In this paper we compared the effectiveness of two approaches for creating multiple classifiers, feature selection and feature extraction. The methods are based on generating multiple feature subsets by running feature selection or feature extraction algorithm several times, each time for discrimination of one of the classes from the rest. A maximum likelihood classifier is applied on each of the obtained feature subsets and finally a combination scheme was used to combine the outputs of individual classifiers. Experimental results show the effectiveness of feature extraction algorithm for generating multiple classifiers.

• 한국공간정보시스템학회:학술대회논문집
• /
• 한국공간정보시스템학회 2002년도 춘계학술대회 논문집
• /
• pp.45-52
• /
• 2002

Artificial neural networks (ANN) have been successfully used for classifying remotely sensed imagery. However, ANN still is not the preferable choice for classification over the conventional classification methodology such as the maximum likelihood classifier commonly used in the industry production environment. This can be attributed to the ANN characteristic built-in stochastic process that creates difficulties in dealing with unequally represented training classes, and its training performance speed. In this paper we examined some practical aspects of training classes when using a back propagation neural network model for remotely sensed imagery. During the classification process of remotely sensed imagery, representative training patterns for each class are collected by polygons or by using a region-growing methodology over the imagery. The number of collected training patterns for each class may vary from several pixels to thousands. This unequally populated training data may cause the significant problems some neural network empirical models such as back-propagation have experienced. We investigate the effects of training over- or under- represented training patterns in classes and propose the pattern repopulation algorithm, and an adaptive alpha adjustment (AAA) algorithm to handle unequally represented classes. We also show the performance improvement when input patterns are presented in random fashion during the back-propagation training.

• 대한원격탐사학회지
• /
• 제31권3호
• /
• pp.205-214
• /
• 2015

이 연구에서는 자료변환기법을 이용해 추출된 여러 특징과 다양한 분류방법론을 결합하여 다중시기 SAR 자료를 위한 새로운 토지피복 분류기법을 제안하였다. 먼저, 다중시기 SAR 자료로부터 원본자료와는 다른 새로운 정보를 추출하기 위해 주성분분석과 3차원 웨이블렛 변환을 이용한 자료변환을 수행하였다. 그리고 나서 최대우도법 분류자, 신경망, support vector machine을 포함한 세 가지 다른 분류자를 변환된 특징자료들과 원본 후방산란계수 자료를 포함한 세가지 자료에 적용하여 다양한 초기 분류 결과를 얻도록 한다. 이후 다수결규칙을 통해 모든 초기결과를 결합하여 최종 분류 결과를 생성하게 된다. 다중시기 ENVISAT ASAR 자료를 이용한 사례연구에서 모든 초기 결과는 사용한 특징자료와 분류자의 종류에 따라 매우 다양한 분류정확도를 보였다. 이러한 9개의 초기 분류 결과를 결합한 최종 분류 결과는 가장 높은 분류 정확도를 보여주고 있는데, 이는 각 초기 분류 결과가 토지피복을 결정하기 위한 상호 보완적인 정보를 제공하기 때문이다. 이 연구에서의 분류정확도 향상은 주로 자료변환을 통해 얻어진 각기 다른 특징자료와 다른 분류자를 결합에 의한 다양성 확보에서 기인한다. 그러므로 이 연구에서 제안한 토지피복 분류방법론은 다중시기 SAR자료의 분류에 효과적으로 적용가능하며, 또한 다중센서 원격탐사 자료융합으로 확장이 가능하다.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1991년도 춘계학술대회
• /
• pp.65-70
• /
• 1991

A hybrid model which uses a probabilistic model and a MLP(multi layer perceptron) model for pattern recognition of EMG(electromyogram) signals is proposed in this paper. MLP model has problems which do not guarantee global minima of error due to learning method and have different approximation grade to bayesian probabilities due to different amounts and quality of training data, the number of hidden layers and hidden nodes, etc. Especially in the case of new test data which exclude design samples, the latter problem produces quite different results. The error probability of probabilistic model is closely related to the estimation error of the parameters used in the model and fidelity of assumtion. Generally, it is impossible to introduce the bayesian classifier to the probabilistic model of EMG signals because of unknown priori probabilities and is estimated by MLE(maximum likelihood estimate). In this paper we propose the method which get the MAP(maximum a posteriori probability) in the probabilistic model by estimating the priori probability distribution which minimize the error probability using the MLP. This method minimize the error probability of the probabilistic model as long as the realization of the MLP is optimal and approximate the minimum of error probability of each class of both models selectively. Alocating the reference coordinate of EMG signal to the outside of the body make it easy to suit to the applications which it is difficult to define and seperate using internal body coordinate. Simulation results show the benefit of the proposed model compared to use the MLP and the probabilistic model seperately.

• 한국지리정보학회지
• /
• 제5권1호
• /
• pp.27-37
• /
• 2002

정량적인 토지피복도의 확보는 유역에 분포하는 비점오염원의 규명에 있어서 매우 중요한 과제로 인식되고 있다. 본 연구는 위성영상을 이용한 토지피복분류 과정에 있어서, 훈련지역의 취득방법 및 규모가 분류정확도에 미치는 영향을 JERS-1 OPS 위성영상을 기반으로 평가하였다. 전체 연구대상지역 중에서 0.3%, 0.5%, 1.0%를 훈련지역으로 추출함에 있어서 두 가지 기법을 제안하였다. 첫번째 기법은 해당지역에 대한 사전 지식을 갖춘 연구자가 훈련지역을 추출하였으며, 두번째 기법은 기하학적 보정을 행한 항공사진과 수치지도를 이용하여 훈련지역을 추출하였다. 영상의 토지피복 분류는 최대우도분류법을 이용하였다. 연구결과 사용자에 의한 훈련지역 취득기법보다 항공사진과 수치지도를 이용하여 훈련지역을 추출하여 최대우도분류법을 적용할 경우 전체정확도가 최대 18% 정도 향상하였다. 우리나라와 같이 복잡하고 다양한 토지이용을 가진 지형에서 JERS-1 영상을 이용하여 95%의 신뢰도를 얻기 위해서는 적어도 훈련지역을 전체지역의 약 1% 이상 추출하여야 만족할 만한 토지피복분류를 수행할 수 있었다.

• Asian-Australasian Journal of Animal Sciences
• /
• 제28권4호
• /
• pp.476-484
• /
• 2015

The objective of this study was to estimate genetic and phenotypic parameters for linear type traits, as well as milk yield (MY), fat yield (FY) and protein yield (PY) in 18,831 Holstein cows reared in 495 herds in Brazil. Restricted maximum likelihood with a bivariate model was used for estimation genetic parameters, including fixed effects of herd-year of classification, period of classification, classifier and stage of lactation for linear type traits and herd-year of calving, season of calving and lactation order effects for production traits. The age of cow at calving was fitted as a covariate (with linear and quadratic terms), common to both models. Heritability estimates varied from 0.09 to 0.38 for linear type traits and from 0.17 to 0.24 for production traits, indicating sufficient genetic variability to achieve genetic gain through selection. In general, estimates of genetic correlations between type and production traits were low, except for udder texture and angularity that showed positive genetic correlations (>0.29) with MY, FY, and PY. Udder depth had the highest negative genetic correlation (-0.30) with production traits. Selection for final score, commonly used by farmers as a practical selection tool to improve type traits, does not lead to significant improvements in production traits, thus the use of selection indices that consider both sets of traits (production and type) seems to be the most adequate to carry out genetic selection of animals in the Brazilian herd.

• 한국지리정보학회지
• /
• 제2권1호
• /
• pp.32-44
• /
• 1999

본 연구의 목적은 질감을 분광정보와 함께 사용했을 때의 분류정확도의 향상을 평가하는데 있다. 먼저 부산지역의 SPOT HRV 영상에 최대우도분류를 적용하여 토지피복도를 작성하였다. 그리고 3번 파장에서 다양한 질감을 추출한 다음, 이 질감을 신파장의 형태로 분광정보에 통합하여 분류하여 질감의 사용이 분류의 정확도에 미치는 영향을 질감별로 평가하였다. 정확도 평가는 전체적인 정확도와 토지피복별 정확도로 구분하였다. 연구결과 전체적인 정확도 향상을 관측할 수 있었는데, 특히 엔트로피의 개선 효과가 우수하였다. 그리고 창의 크기는 $5{\times}5$와 $7{\times}7$이 적절한 것으로 나타났다. 그리고 질감에 따라서는 전체적인 정확도는 향상되지 않더라도 일부 토지피복의 정확도는 개선되는 것으로 나타났다. 토지피복별로는 저층건물지역, 아파트 단지. 고층건물지역, 공업지역 등 도시지역의 개선효과가 높은 것으로 나타났다.

• 한국토양비료학회지
• /
• 제34권5호
• /
• pp.342-349
• /
• 2001

Landsat TM 인공위성 자료(1997년 6월 16일 촬영)를 이용하여 평택시에 대한 지표피복분류도를 만들고 정확도를 평가하였고, 또한 우리 나라의 농업실정에 맞는 지표피복 분류체계를 세우기 위해 Anderson의 지표피복분류안을 응용하여 새로운 분류안을 만들었다. 분류방식으로는 감독분류를 사용하였는데 결과에 직접적인 영향을 주는 훈련장소(training site)의 선정을 위해 지형도, 항공사진 등과 현지 실사자료인 DGPS 자료를 사용하여 논, 밭 등 13개의 훈련조(training sets)를 작성 후 최대우도법(最大尤度法)(maximum likelihood classifier)을 적용하여 주제도를 만들었다. 이의 정확도 평가를 위해 DGPS, 항공사진, 지형도 등을 이용한 분류정확도 평가에서 전체 정확도는 86.8%이며, 카파계수가 85.4%로 매우 양호한(Excellent) 것으로 판명되었다. 그러나 도시/촌락, 비닐하우스 등의 사용자 정확도는 60% 정도로서 낮은 편이며, 도로, 비닐하우스 등의 생산자 정확도는 70% 정도로 낮은 편인데, 이는 인공건조물이라는 특징에 따른 분광학적 반사특성과 이질성(異質性)과 분포면적이 적은데 기인된 것으로 생각된다. 한편 원격탐사자료를 이용하여 토지피복 분류도를 작성할 때 우리나라 농업실정에 알맞은 농업적(農業的) 지표피복분류안(地表被覆分類案)을 만들었는데, 수준 I에는 농경지, 산림지, 물, 불모지, 도시나 인공건조물 등으로 나눌 수 있다.

• 대한원격탐사학회지
• /
• 제21권3호
• /
• pp.189-211
• /
• 2005

This paper makes an effort to compare the recently evolved soft classification method based on Linear Spectral Mixture Modeling (LSMM) with the traditional hard classification methods based on Iterative Self-Organizing Data Analysis (ISODATA) and Maximum Likelihood Classification (MLC) algorithms in order to achieve appropriate results for mapping, monitoring and preserving valuable coastal wetland ecosystems of southern India using Indian Remote Sensing Satellite (IRS) 1C/1D LISS-III and Landsat-5 Thematic Mapper image data. ISODATA and MLC methods were attempted on these satellite image data to produce maps of 5, 10, 15 and 20 wetland classes for each of three contrast coastal wetland sites, Pitchavaram, Vedaranniyam and Rameswaram. The accuracy of the derived classes was assessed with the simplest descriptive statistic technique called overall accuracy and a discrete multivariate technique called KAPPA accuracy. ISODATA classification resulted in maps with poor accuracy compared to MLC classification that produced maps with improved accuracy. However, there was a systematic decrease in overall accuracy and KAPPA accuracy, when more number of classes was derived from IRS-1C/1D and Landsat-5 TM imagery by ISODATA and MLC. There were two principal factors for the decreased classification accuracy, namely spectral overlapping/confusion and inadequate spatial resolution of the sensors. Compared to the former, the limited instantaneous field of view (IFOV) of these sensors caused occurrence of number of mixture pixels (mixels) in the image and its effect on the classification process was a major problem to deriving accurate wetland cover types, in spite of the increasing spatial resolution of new generation Earth Observation Sensors (EOS). In order to improve the classification accuracy, a soft classification method based on Linear Spectral Mixture Modeling (LSMM) was described to calculate the spectral mixture and classify IRS-1C/1D LISS-III and Landsat-5 TM Imagery. This method considered number of reflectance end-members that form the scene spectra, followed by the determination of their nature and finally the decomposition of the spectra into their endmembers. To evaluate the LSMM areal estimates, resulted fractional end-members were compared with normalized difference vegetation index (NDVI), ground truth data, as well as those estimates derived from the traditional hard classifier (MLC). The findings revealed that NDVI values and vegetation fractions were positively correlated ($r^2$= 0.96, 0.95 and 0.92 for Rameswaram, Vedaranniyam and Pitchavaram respectively) and NDVI and soil fraction values were negatively correlated ($r^2$ =0.53, 0.39 and 0.13), indicating the reliability of the sub-pixel classification. Comparing with ground truth data, the precision of LSMM for deriving moisture fraction was 92% and 96% for soil fraction. The LSMM in general would seem well suited to locating small wetland habitats which occurred as sub-pixel inclusions, and to representing continuous gradations between different habitat types.