• Journal of the Korean Association of Geographic Information Studies
• /
• v.5 no.1
• /
• pp.27-37
• /
• 2002

The classification accuracy of land cover has been considered as one of the major issues to estimate pollution loads generated from diffuse landuse patterns in a watershed. This research aimed to assess the effects of the acquisition methods and sampling size of training reference data on the classification accuracy of land cover using an imagery acquired by optical sensor(OPS) on JERS-1. Two kinds of data acquisition methods were considered to prepare training data. The first was to assign a certain land cover type to a specific pixel based on the researchers subjective discriminating capacity about current land use and the second was attributed to an aerial photograph incorporated with digital maps with GIS. Three different sizes of samples, 0.3%, 0.5%, and 1.0% of all pixels, were applied to examine the consistency of the classified land cover with the training data of corresponding pixels. Maximum likelihood scheme was applied to classify the land use patterns of JERS-1 imagery. Classification run applying an aerial photograph achieved 18 % higher consistency with the training data than the run applying the researchers subjective discriminating capacity. Regarding the sample size, it was proposed that the size of training area should be selected at least over 1% of all of the pixels in the study area in order to obtain the accuracy with 95% for JERS-1 satellite imagery on a typical small-to-medium-size urbanized area.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1567-1577
• /
• 2020

Urban land cover classification is role in urban planning and management. So, it's important to improve classification accuracy on urban location. In this paper, machine learning model, Support Vector Machine (SVM) and Artificial Neural Network (ANN) are proposed for urban land cover classification based on high resolution satellite imagery (KOMPSAT-3A). Satellite image was trained based on 25 m rectangle grid to create training data, and training models used for classifying test area. During the validation process, we presented confusion matrix for each result with 250 Ground Truth Points (GTP). Of the four SVM kernels and the two activation functions ANN, the SVM Polynomial kernel model had the highest accuracy of 86%. In the process of comparing the SVM and ANN using GTP, the SVM model was more effective than the ANN model for KOMPSAT-3A classification. Among the four classes (building, road, vegetation, and bare-soil), building class showed the lowest classification accuracy due to the shadow caused by the high rise building.

• Korean Journal of Plant Resources
• /
• v.25 no.1
• /
• pp.105-122
• /
• 2012

This study was carried out to illuminate the flora of vascular plants of islands at Chungnam. This study was conducted from March to November, 2010. Based on the voucher, vascular plants of in investigated islands were 105 families 326 genera 454 species 4 subspecies 45 varieties 9 forms, totally 512 taxa. Korean endemic plants were 6 species such as Aster koraiensis, Salix koriyanagi, Indigofera koreana, Hemerocallis taeanensis, Hepatica insularis, Philadelphus schrenckii, rare and endangered plants of designated by Korea Forest Service were 4 taxa, such as Magnolia kobus (planted), Koelreuteria paniculata, Berchemia racemosa var. magna, Glehnia littoralis respectively. Phytogeographical special plants were totally 69 taxa, which were grade I of 50 taxa, grade II of 1 axon, grade III of 11 taxa, grade IV of 4 taxa, and grade V of 3 taxa. 14 southern plants and 4 northern plant by criterion from climate change study were found in this area. Naturalized plants were 17 families 46 taxa, that was 9.1% of total vascular plants in this area. Even naturalized plants has not influence on the islands vegetation. However, regular passenger ferry between islands and increasing of visiter will be affecting vegetation.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2003.04a
• /
• pp.94-99
• /
• 2003

다중분광 영상의 정확한 지형지물 분류를 수행하기 위하여 분류 클래스의 훈련지역 선정과 선정된 클래스의 분리도 분포가 중요하다. 최근에 이용되고 있는 위성탑재 초다중분광 영상은 많은 밴드를 포함하고 있기 때문에 데이터 처리가 어렵고, 노이즈로 인하여 다중분광 영상보다 분류 결과가 나쁜 경우도 나타난다. 특히 대상지역의 클래스에 따른 훈련지역의 선정시 밴드수에 비해 상대적으로 제한된 훈련화소 크기로 인하여 공분산 행렬의 계산에 어려움이 따른다. 따라서 본 연구에서는 Hyperion 데이터를 이용한 분류를 수행하기 위하여 필요한 유효 밴드 추출 방식을 알아보고, 분류영상의 정확도 평가를 통하여 추출된 밴드와 분류 클래스의 적합성 관계를 확인하고자 한다 이 과정에서 클래스 분리도를 이용하여 정확도 평가 이전에 밴드와 클래스 선정의 타당성을 확인할 수 있다.

• Korean Journal of Remote Sensing
• /
• v.30 no.2
• /
• pp.219-226
• /
• 2014

Fractional values resulted from the spectral mixture analysis could be used to classify not only urban area with various materials but also forest area in more detailed spatial scale. Especially South Korea is largely consist of mixed forest, so the spectral mixture analysis is suitable as a classification method. For the successful classification using spectral mixture analysis, extraction of optimal endmembers is prerequisite process. Though geometric endmember selection has been widely used, it is barely suitable for forest area. Therefore, in this study, we modified Iterative Error Analysis (IEA), one of the most famous algorithms of image endmember selection which extracts pure pixel directly from the image. The endmembers which represent deciduous and coniferous trees are automatically extracted. The experiments were implemented on two sites of Compact Airborne Spectrographic Imager (CASI) and classified forest area into two types. Accuracies of each classification results were 86% and 90%, which mean proposed algorithm effectively extracted proper endmembers. For the more accurate classification, another substances like forest gap should be considered.

• Korean Journal of Plant Resources
• /
• v.18 no.2
• /
• pp.325-336
• /
• 2005

The life form, the origin and the time of introduction of those naturalized plants grown in Jeju-Do, korea were grasped by conducting the documentary survey, and the field survey thereof. The naturalized plants were total 199 taxa including 185 species, 12 varieties and 2 cultivar, which belong to 115 genera, 32 families. The classification of families, there were 43 taxa of Compositae ($21.6\%$), 32 taxa of Gramineae ($16.8\%$), 17 taxa of Legumlinosae ($8.5\%$), and 13 taxa of Cruciferae ($6.5\%$). As the life forms of the naturalized plants in Jeju Island were there 91 taxa of annual plants, 31 taxa of biennial plants, 16 taxa of annual or biennial plants, 57 taxa of perennial plants, and 4 taxa of trees. The distribution of the naturalized plants, the were 29 taxa thereof were located in Jeju Island, 20 taxa in Jeju Island as well as in the southern part of Korean Peninsula, 33 taxa in Jeju Island as well as in the central part of Korean Peninsula, and 117 taxa in the entire area of South Korea. As 89 taxa thereof were originated from America, 69 taxa from Europe, 2 taxa from Africa, 22 taxa from Asia, 1 taxa from Oceania, and 16 taxa from other provinces. As 38 taxa thereof had been introduced into Jeju Island before 1921, 23 taxa from 1922 to 1963, and 138 taxa since 1964.

• Proceedings of the KSRS Conference
• /
• 2006.03a
• /
• pp.257-260
• /
• 2006

본 연구에서는 SIR-C MLC 영상자료와 환경부에서 제공하는 중분류 토지피복도 자료를 참조하여 식생피복지역으로 예상되는 논, 밭 지역으로 분류된 농업지역과 활엽수림, 침엽수림, 혼효림 지역으로 분류된 산림지역에 대한 산란특성을 고찰하기 위해 편광 반응특성을 측정하였다. 편광반응특성분석결과 농업지역과 산림지역의 거동형태는 구형 산란체나 편평한 면에서의 거동특성을 나타냈으며, 측정된 HH, VV, HV 편광매개변수의 후방산란계수 값들은 각각의 지역에서 다른 경향을 보였다.

• Korean Journal of Plant Resources
• /
• v.32 no.5
• /
• pp.565-588
• /
• 2019

This study aimed to understand current flora of Western Civilian Control Zone (CCZ) in Korea. Some areas that located at Paju-si and Yeoncheon-gun were selected as representative survey area (Jangdan-myeon, Deokjin mountain fortress, Ilwol peak of Mt. Seokbyeong, Imjinriver, Sunaecheon stream, Sewolcheon stream in Paju and Banjeong-ri in Yeoncheon). Through this survey, 461 vascular plant specimens were collected from April 2012 to September 2014, twice a month and from October 2014 to October 2018, once a month. These were finally classified into 96 families 305 genera 413 species 4 subspecies 41 varieties 6 forms totally 464 taxa. There are remarkable plants such as 6 taxa of Korean endemic species, 44 taxa of specified species on a floristics aspect, and 35 taxa of alien and naturalized plants (7.5%). Meanwhile, it has not been observed any endangered plant species during the activities in this area.

• Proceedings of the Plant Resources Society of Korea Conference
• /
• 2022.09a
• /
• pp.44-44
• /
• 2022

본 연구는 산림 생물다양성 특정 지역인 풍혈지 25개소를 대상으로 기후변화에 취약한 북방계식물 등의 현지내·외 보전 대책 수립과 풍혈지의 산림유전자원보호지역 지정을 위한 기초자료로 활용하기 위하여 조사를 수행하였다. 조사는 풍혈의 바람이 나오는 핵심지역 10m 를 중심으로 동서남북으로 각각 50m 범위에서 실시하였고, 2016년 4월부터 2021년 11월까지 계절별로 각 1~2회씩 수행하였다. 한국의 25개소 풍혈지의 관속식물상은 125과 486속 947종 23아종 75변종 7품종 총 1,052분류군으로 확인되었다. 조사 면적은 최대 0.09km²로 우리나라 산림면적 62,860km²의 0.00014%에 불과하지만, 우리나라 관속식물의 4,724종 중에서 22.27%가 출현하였다. 이는 풍혈지역이 산림생물다양성의 가치가 매우 높은 지역임을 확인해 볼 수 있다. 특기할만한 식물은 멸종위기야생생물이 산작약, 으름난초 등 6분류군, 희귀식물과 적색목록은 월귤, 개병풍 등 67분류군, 한반도 특산식물과 고유종이 병꽃나무 등 58분류군, 식물구계학적 특정식물은 개느삼 등 총 317분류군이 조사되었다. 북방계식물은 토끼고사리 등 181분류군, 석회암지대 식물은 덕우기름나물 등 32분류군이 확인되었다. 외래식물은 개망초, 달맞이꽃 등 75분류군이 확인되었고, 귀화율 7.13%와 도시화율 12.12%로 산출되었다. 본 연구대상지인 풍혈지 25개소의 식물지리학적 특정식물은 월귤, 흰인가목, 꽃개회나무, 각시괴불나무, 산솜방망이 등으로 파악되었다.

• Korean Journal of Remote Sensing
• /
• v.17 no.1
• /
• pp.57-69
• /
• 2001

This study propose a image processing system of unsupervised analysis. This system integrates low-level segmentation and high-level classification. The segmentation and classification are conducted respectively with and without spatial constraints on merging by a hierarchical clustering procedure. The clustering utilizes the local mutually closest neighbors and multi-window operation of a pyramid-like structure. The proposed system has been evaluated using simulated images and applied for the LANDSATETM+ image collected from Youngin-Nungpyung area on the Korean Peninsula.