• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.2
• /
• pp.289-297
• /
• 2009

In the paper, we propose the methodology to extract training dataset automatically for supervised classification of road networks. For the preprocessing, we co-register the airborne photos, LIDAR data and large-scale digital maps and then, create orthophotos and intensity images. By overlaying the large-scale digital maps onto generated images, we can extract the initial training dataset for the supervised classification of road networks. However, the initial training information is distorted because there are errors propagated from registration process and, also, there are generally various objects in the road networks such as asphalt, road marks, vegetation, cars and so on. As such, to generate the training information only for the road surface, we apply the Expectation Maximization technique and finally, extract the training dataset of the road surface. For the accuracy test, we compare the training dataset with manually extracted ones. Through the statistical tests, we can identify that the developed method is valid.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.423-423
• /
• 2019

RGB나 다중분광영상은 높은 공간 해상도로 인해 크기가 작은 물질의 클래스를 부여하는데 있어서는 효과적이지만 분광해상도가 낮아 다양한 종류의 지표물 분류 및 분광적으로 미세한 차이를 보이는 대상 체간의 분류에는 한계를 가지고 있다. 그러나 초분광 영상(Hyperspectral Image)은 대상 객체의 분광 반사곡선을 수백개의 연속적인 분광 파장대 영역으로 상세하게 해당 물체의 정보를 취득할 수 있는 기능을 가지고 있다. 최근 국내에서도 초분광 영상을 이용한 토지피복도 작성 및 환경 모니터링 등 다양한 분야에 적용하기 위한 연구가 시도되고 있다. 최근에는 드론과 같은 소형 UAV를 활용하여 경제적인 비용으로 시공간해상도가 높은 영상을 획득하는 것이 가능하게 되었으며 분광정보를 수집하는 영상 장비의 발전으로 드론에 탑재가 가능한 경량의 소형 초분광센서가 개발됨으로써 보다 높은 분광해상도의 영상을 취득할 수 있게 되었다. 본 연구에서는 효율적인 하천환경조사를 위해 UAV를 활용하여 고해상도 초분광 영상을 취득하였으며, 차원축소법과 분류기 적용에 따른 공간 분류 정확도 분석을 통해 하천환경에 대한 분류 및 평가를 실시하였다. 연구지역에서 획득한 초분광 영상은 노이즈로 인한 영향을 줄이고자 MNF와 PCA 기법으로 차원축소를 수행하였으며, MLC(Maximum Likelihood Classification)와 SVM(Support Vector Machine), SAM(Spectral Angle Mapping) 감독분류기법을 적용하여 하천환경특성에 따른 공간분류를 수행하였다. 연구 결과 MNF기법으로 차원 축소한 영상을 적용하여 MLC 감독분류를 수행하였을 때 가장 높은 분류정확도를 얻을 수 있었으나, 일부 클래스 및 수역의 경계와 그림자 공간에서 주로 오분류가 나타나는 것을 확인할 수 있었다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.5
• /
• pp.451-457
• /
• 2014

Recently, the land degradation and pasture erosion in Tuv, located around Ulaanbaatar of Mongolia, have been increasing sharply due to escalating developments of mining sectors, well as the density of populations. Because of that, we have chosen the urban and mining area of Tuv for our study target. During the study, the temporal changes of land cover in Tuv, Mongolia were observed by the Landsat TM/+ETM satellite images from 2001 to 2009 that provided the fundamental dataset to apply NDVI and K-Mean algorithm of Unsupervised Classification and Maximum likelihood classification(MLC) of Supervised Classification in order to conclude in land cover change analyzation. The result of our study implies that the growth of mining area, the climate change, and the density of population led the land degradation to desertification.

• Journal of KIISE
• /
• v.42 no.6
• /
• pp.817-822
• /
• 2015

Relation extraction is an important information extraction technique that can be widely used in areas such as question-answering and knowledge population. Previous studies on relation extraction have been based on supervised machine learning models that need a large amount of training data manually annotated with relation categories. Recently, to reduce the manual annotation efforts for constructing training data, distant supervision methods have been proposed. However, these methods suffer from a drawback: it is difficult to use these methods for collecting negative training data that are necessary for resolving classification problems. To overcome this drawback, we propose a one-class classification model that can be trained without using negative data. The proposed model determines whether an input data item is included in an inner category by using a similarity measure based on lexical information and syntactic patterns in a vector space. In the experiments conducted in this study, the proposed model showed higher performance (an F1-score of 0.6509 and an accuracy of 0.6833) than a representative one-class classification model, one-class SVM(Support Vector Machine).

• Journal of Wetlands Research
• /
• v.16 no.3
• /
• pp.393-401
• /
• 2014

The purpose of this study was to investigate the objective impact in accuracy and reliability with tendency depend on training samples by using the high-resolution images. Supervised classification was performed based on multi-spectral images which made by each satellite and aerial images for considering all of bands' characteristics. The highest accuracy was 84.7% with satellite image(3*3) and 83% with aerial image(5*5) at the accuracy verification phase. Also, the overall accuracy with the consideration of Kappa coefficient were 0.84 for satellite images and 0.82 for aerial images. In all of the images, the smaller training sample was, the higher accuracy showed. Therefore, tree species classification accuracy was tended to rely on training sample size.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.6
• /
• pp.2751-2756
• /
• 2012

Selection of training set influences the classification accuracy in supervised classification using satellite imagery. Generally, if pure pixels which character of training set is clear were selected, whole accuracy is high while if mixed pixels were selected, accuracy is decreased because of low-resolution imagery or unclear distinguishment. However, it is too difficult to choose the pure pixels as training set actually. Accordingly, this study should be suggested the suitable classification method in case of mixed pixels choice. To achieve this, a few pure pixels were chosen as training set and classification accuracy was calculated which was compared with classification result using an equal number of mixed pixels. As a result, accuracy of SVM was the highest among the classification method using mixed pixels and it was a relatively small difference with the result of classification using pure pixels. Therefore, imagery classification using SVM is most suitable in the mixed area of construction and green because it is high possibility to choose mixed pixels as training set.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_2
• /
• pp.689-698
• /
• 2017

In this paper, a new classification method based on the combination of semi-supervised learning with spatial similarity of adjacent pixels is presented for crop classification in inaccessible areas. Iterative classification based on semi-supervised learning is applied to extract reliable training data from both the initial classification result with a small number of training data, and classification results of adjacent pixels are also considered to extract new training pixels with less uncertainty. To evaluate the applicability of the proposed method, a case study of the classification of field crops was carried out using multi-temporal Landsat-8 OLI acquired in the Daehongdan region, North Korea. From a case study, the misclassification of crops and forests, and isolated pixels in the initial classification result were greatly reduced by applying the proposed semi-supervised learning method. In addition, the combination of classification results of adjacent pixels for the extraction of new training data led to the great reduction of both misclassification results and isolated pixels, compared to the initial classification and traditional semi-supervised learning results. Therefore, it is expected that the proposed method would be effectively applied to classify areas in which it is difficult to collect sufficient training data.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.6 no.2
• /
• pp.80-91
• /
• 2003

In this research, re-using band ratio data was proposed and examined as a method of raising the accuracy in landcover classification which is using satellite data.In order to determine the band which is used to calculation in the classified item, the six bands except the band 6 were combined with the band in which combination is possible and the landcover classification by MLC of supervised classification was carried out. In the result of landcover classification which is combined with forty nine combination, Two bands which were mostly used by band combination in the accuracy belonged inside the 10th place of a higher rank were selected and also calculated. landcover classification were performed again after the calculation result had been recombinated from the research. In addition, the new landcover classification result was compared and examined with the landcover classification using the old data. From the result of which was compared and examined the new landcover classification data recombinated calculation result with landcover classification using the original data, The classification accuracy of the new landcover classification data recombinated calculation result became low in ground but became improved in the all class. Specially The accuracy to urban area is very improved. therefore, it determined that reusing band ratio data is very useful when we need to analyze landcover classification and land information to urban area after that.

• Korean Journal of Remote Sensing
• /
• v.18 no.6
• /
• pp.369-376
• /
• 2002

This paper presents a method to enhance the performance of supervised classification by separating the spectral signature of the training data sets for each class. Using clustering technique, a training data set is divided into several subsets which show a pattern of the normal distribution with small value of spectral variances. Then a supervised classification is applied with the divided training data set as training data for the temporary subclasses of the original class. The proposed method is applied to a Landsat TM image of Busan area for the applicability test. The result shows that the proposed method produces better classified results than the conventional statistical classification methods. It is expected that the proposed method will reduce the effort and expense for selecting the training data set for each class in an area which has spectrally homogeneous signature.

• Journal of Korean Society for Geospatial Information Science
• /
• v.19 no.2
• /
• pp.9-17
• /
• 2011

For the exact status of the land such as land cover classification and land use classification, feature classification system has been utilized in several organizations and agencies. However, those classification systems are limited to detection of land change and it's also not suited for the extraction of land changed. In this study, we would proposed a standard feature classification system which presents both in natural and artificial change of land effectively. Based on comparison and analysis of domestic and foreign relevant feature classification system, we proposed a standard feature classification system. In order to validate the applicability of the proposed feature classification system, we evaluated the accuracy with using automatic feature classification based on supervised classification and pre-knowledge hierarchical classification.