• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1911-1923
• /
• 2022

The availability of high-resolution satellite images provides precise information without direct observation of the research target. Korea Multi-Purpose Satellite (KOMPSAT), also known as the Arirang satellite, has been developed and utilized for earth observation. The machine learning model was continuously proven as a good classifier in classifying remotely sensed images. This study aimed to compare the performance of the support vector machine (SVM) model in classifying the land cover of the Delaware River port area on high and medium-resolution images. Three optical images, which are KOMPSAT-2, KOMPSAT-3A, and Sentinel-2B, were classified into six land cover classes, including water, road, vegetation, building, vacant, and shadow. The KOMPSAT images are provided by Korea Aerospace Research Institute (KARI), and the Sentinel-2B image was provided by the European Space Agency (ESA). The training samples were manually digitized for each land cover class and considered the reference image. The predicted images were compared to the actual data to obtain the accuracy assessment using a confusion matrix analysis. In addition, the time-consuming training and classifying were recorded to evaluate the model performance. The results showed that the KOMPSAT-3A image has the highest overall accuracy and followed by KOMPSAT-2 and Sentinel-2B results. On the contrary, the model took a long time to classify the higher-resolution image compared to the lower resolution. For that reason, we can conclude that the SVM model performed better in the higher resolution image with the consequence of the longer time-consuming training and classifying data. Thus, this finding might provide consideration for related researchers when selecting satellite imagery for effective and accurate image classification.

• Journal of Environmental Impact Assessment
• /
• v.22 no.2
• /
• pp.147-156
• /
• 2013

Myanmar(Burma) has been preserved valuable environmental resources because of its political isolation. But recently, Myanmar has moved a capital city(Naypyidaw) at central forest area and it has been urbanized radically since 2005. In this paper, we built multi-temporal land cover map from Landsat images of 1970s to 2012 with ENVI 4.5 software. For a broad approach, administrative district Yamethin which includes Naypyidaw is classified into 3 classes and with only Naypyidaw region is classified with 4-5 classes to analyse specific changes. And with forest cover extracted by Object Oriented Classification, we evaluated forest fragmentation before and after the development using Patch Analyst(FRAGSTATs 3.3) at Yamethin area. For Yamethin area, there were significant forest cover change, 51% in 1999 to 48% in 2012, and for Naypyidaw area, 67% in 1999 to 57% in 2012 respectively. Also landscape indices resulted from Patch Analyst concluded that the total edge, edge density and mean shaped index of forest patches increased and total core area is decreased. It is attributed from land cover change with urbanization and agricultural land expansion.

• Korean Journal of Remote Sensing
• /
• v.35 no.1
• /
• pp.83-92
• /
• 2019

Land cover (LC) is an important factor in socioeconomic and environmental studies. According to various studies, a number of LC maps, including global land cover (GLC) datasets, are made using polar orbit satellite data. Due to the insufficiencies of reference datasets in Northeast Asia, several LC maps display discrepancies in that region. In this paper, we performed a feasibility assessment of LC mapping using Geostationary Ocean Color Imager (GOCI) data over Northeast Asia. To produce the LC map, the GOCI normalized difference vegetation index (NDVI) was used as an input dataset and a level-2 LC map of South Korea was used as a reference dataset to evaluate the LC map. In this paper, 7 LC types(urban, croplands, forest, grasslands, wetlands, barren, and water) were defined to reflect Northeast Asian LC. The LC map was produced via principal component analysis (PCA) with K-means clustering, and a sensitivity analysis was performed. The overall accuracy was calculated to be 77.94%. Furthermore, to assess the accuracy of the LC map not only in South Korea but also in Northeast Asia, 6 GLC datasets (IGBP, UMD, GLC2000, GlobCover2009, MCD12Q1, GlobeLand30) were used as comparison datasets. The accuracy scores for the 6 GLC datasets were calculated to be 59.41%, 56.82%, 60.97%, 51.71%, 70.24%, and 72.80%, respectively. Therefore, the first attempt to produce the LC map using geostationary satellite data is considered to be acceptable.

• Korean Journal of Remote Sensing
• /
• v.39 no.4
• /
• pp.409-423
• /
• 2023

North Korea is carrying out reclamation activities in tidal flat areas distributed throughout the west coast. Previousremote sensing research on North Korean tidal flats either failsto reflect recent trends or focuses on identifying and analyzing tidal flats. Thisstudy aimsto quantify the impact of recent reclamation activitiesin North Korea's coastal areas and contribute knowledge useful for determining the best remote sensing methods for coastal areas with limited accessibility, such as those in North Korea. Using Landsat-8 OLI images from 2014-2022, we analyzed land cover changesin an area on the west coast of Pyeonganbuk-do where reclamation activities are underway. Unsupervised classification using the normalized difference water index and the random forest classification technique were each used to divide the study area into classification groups, and changes in their areas over time were analyzed. The resultsshow a clear decrease in the water area and a tendency to increase cultivated area,supporting the evidence that North Korea'sreclamation isfor agricultural land expansion.Along coasts behind seawalls, the water area decreased by nearly half, and the cultivated area increased by over 2,300%, indicating significant changes and highlighting the anthropogenic nature of the cover changes due to reclamation. Both methods demonstrated high accuracy, making them suitable for detecting cover changes caused by reclamation. It is expected that further quality research will be conducted through the use of high-resolution satellite images and by combining data from multiple satellites in the future.

• Korean Journal of Remote Sensing
• /
• v.17 no.3
• /
• pp.275-284
• /
• 2001

This study was carried out to evaluate high resolution satellite imagery of IKONOS for classifying the land cover, especially forest type. The IKONOS imagery of 11km$\times$11km size was taken on April 24, 2000 in Bong-pyoung Myun Pyungchang-Gun, Kangwon Province. Land cover classes were water, coniferous evergreen, Larix leptolepis, broad-leaved tree, bare land, farm land, grassland, sandy soil and asphalted area. Supervised classification method with algorithm of maximum likelihood was applied for classification. The terrestrial survey was also carried out to collect the reference data in this area. The accuracy of the classification was analyzed with the items of overall accuracy, producer's accuracy, user's accuracy and k for test area through the error matrix. In the accuracy analysis of the test area, overall accuracy was 94.3%, producer's accuracy was 77.0-99.9%, user's accuracy was 71.9-100% and k and 0.93. Classes of bare land, sandy soil and farm land were less clear than other classes, whereas classification result of IKONOS in forest area showed higher performance than that of other resolution(5-30m) satellite data.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.26 no.3
• /
• pp.34-44
• /
• 1998

The purpose of this study is to provide the basic data for land use in the future, which result from analyzing land use, obtained after studying on the natural environment by Geographic Information System and Remote Sensing. The results of this study are as follows : ·According to the classification of land-cover, agricultural land use is relatively prominent except for overall natural covering. According to the average value of Green Vegetation Index class, the average value of GVI is 3.0, and 45% of the regions have relatively good condition of floral state. ·With a view to natural environment, the survey shows that the altitude of 90% of the total areas is below 400m, and most of them are flattened or moderately-inclined area. Therefore, this region has a good condition to be used for development. · The area for the first class in preservation degree of natural scenery of Namcheon-Myun is 2.3% of the total areas. According to the results about unstable areas on all sides, unstable districs are distributed in so small-scale units that they will be safe from some damages drawn by developing activity. But we have to consider every aspects for the future development of them. In this study, the natural environment-variables are regarded firstly, and effective designation of the land with natural environment is researched too. However, to establish more practical developing plan, ecological and human variables should be regarded.

• 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.

• International Journal of Computer Science & Network Security
• /
• v.22 no.2
• /
• pp.214-222
• /
• 2022

Convolutional Neural networks (CNNs) are a category of deep learning networks that have proven very effective in computer vision tasks such as image classification. Notwithstanding, not much has been seen in its use for remote sensing image classification in developing countries. This is majorly due to the scarcity of training data. Recently, transfer learning technique has successfully been used to develop state-of-the art models for remote sensing (RS) image classification tasks using training and testing data from well-known RS data repositories. However, the ability of such model to classify RS test data from a different dataset has not been sufficiently investigated. In this paper, we propose a deep CNN model that can classify RS test data from a dataset different from the training dataset. To achieve our objective, we first, re-trained a ResNet-50 model using EuroSAT, a large-scale RS dataset to develop a base model then we integrated Augmentation and Ensemble learning to improve its generalization ability. We further experimented on the ability of this model to classify a novel dataset (Nig_Images). The final classification results shows that our model achieves a 96% and 80% accuracy on EuroSAT and Nig_Images test data respectively. Adequate knowledge and usage of this framework is expected to encourage research and the usage of deep CNNs for land cover mapping in cases of lack of training data as obtainable in developing countries.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.10 no.4
• /
• pp.41-53
• /
• 2007

The Baekdudaegan Mountain Range is a backbone of the Korean Peninsula which carries special spiritual and sentimental signatures for Koreans as well as significant ecological values for diverse organisms. However, in spite of importance of this region, the forests of Baekdudaegan have been damaged in a variety of human activities by being used as highland vegetable grower, lumber region, grass land, and bare land, and are still undergoing destruction. The existing researches had determined the details of the damage through on-site and recent observations. Such methods cannot provide quantitative and integrated analysis therefore could not be utilized as objective data for the ecological conservation of Baekdudaegan forests. The goal of this study is to quantitatively analyze the forest damage in the Baekdudaegan preservation region through land cover categorization and change detection techniques by using satellite images, which are 1980s, and 1990s Landsat TM, and 2000s Landsat ETM+. The analysis was executed by detecting land cover changed areas from forest to others and analyzing changed areas' spatial patterns. Through the change detection analysis based on land cover classification, we found out that the deforested areas were approximately three times larger after the 1990s than from the 1980s to the 1990s. These areas were related to various topographical and spatial elements, altitude, slope, the distance form road, and water system, etc. This study has the significance as quantitative and integrated analysis about the Baekdudaegan preservation region since 1980s. These results could actually be utilized as basic data for forest conservation policies and the management of the Baekdudaegan preservation region.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.378-381
• /
• 2008

The regulating and relaxing targets in the Land Use Regulation and Total Maximum Daily Loads are influenced by Land cover information. For the providing more accurate land information, this study attempted to generate an impervious surface map using KOMPSAT-2 image which a Korea manufactured high resolution satellite image. The classification progress of this study carried out by tasseled-cap spectral enhancement through each class extraction technique neither existing classification method. KOMPSAT-2 image of this study is enhanced by Soil Brightness Index(SBI), Green vegetation Index(GVI), None-Such wetness Index(NWI). Then ranges of extracted each index in enhanced image are determined. And then, Confidence Interval of classes was determined through the calculating Non-exceedance Probability. Spectral distributions of each class are changed according to changing of Control coefficient(${\alpha}$) at the calculated Non-exceedance Probability. Previously, Land cover classification map was generated based on established ranges of classes, and then, pervious and impervious surface was reclassified. Finally, impervious ratio of reclassified impervious surface map was calculated with blocks in the study area.