• Korean Journal of Remote Sensing
• /
• v.29 no.5
• /
• pp.569-579
• /
• 2013

In this study, land-cover classification was implemented using features extracted from multi-temporal SAR data through 3D wavelet transform and the applicability of the 3D wavelet transform as a feature extraction approach was evaluated. The feature extraction stage based on 3D wavelet transform was first carried out before the classification and the extracted features were used as input for land-cover classification. For a comparison purpose, original image data without the feature extraction stage and Principal Component Analysis (PCA) based features were also classified. Multi-temporal Radarsat-1 data acquired at Dangjin, Korea was used for this experiment and five land-cover classes including paddy fields, dry fields, forest, water, and built up areas were considered for classification. According to the discrimination capability analysis, the characteristics of dry field and forest were similar, so it was very difficult to distinguish these two classes. When using wavelet-based features, classification accuracy was generally improved except built-up class. Especially the improvement of accuracy for dry field and forest classes was achieved. This improvement may be attributed to the wavelet transform procedure decomposing multi-temporal data not only temporally but also spatially. This experiment result shows that 3D wavelet transform would be an effective tool for feature extraction from multi-temporal data although this procedure should be tested to other sensors or other areas through extensive experiments.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.589-599
• /
• 2018

The land cover map has been produced by using satellite and aerial images. However, these two images have the limitations in spatial resolution, and it is difficult to acquire images of a area at desired time because of the influence of clouds. In addition, it is costly and time-consuming that mapping land cover map of a small area used by satellite and aerial images. This study used multispectral camera-based drone to acquire multi-temporal images for orthoimages generation. The efficiency of produced land cover map was evaluated using time series analysis. The results indicated that the proposed method can generated RGB orthoimage and multispectral orthoimage with RMSE (Root Mean Square Error) of ${\pm}10mm$, ${\pm}11mm$, ${\pm}26mm$ and ${\pm}28mm$, ${\pm}27mm$, ${\pm}47mm$ on X, Y, H respectively. The accuracy of the pixel-based and object-based land cover map was analyzed and the results showed that the accuracy and Kappa coefficient of object-based classification were higher than that of pixel-based classification, which were 93.75%, 92.42% on July, 92.50%, 91.20% on October, 92.92%, 91.77% on February, respectively. Moreover, the proposed method can accurately capture the quantitative area change of the object. In summary, the suggest study demonstrated the possibility and efficiency of using multispectral camera-based drone in production of land cover map.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.5
• /
• pp.371-379
• /
• 2018

Unlike general VHR (Very-High-Resolution) satellite sensors that are mainly for panchromatic and MS (Multispectral) imaging, Worldview-3 sensor additionally provides eight SWIR (Short Wavelength Infrared) bands in wavelength range from 1198 nm to 2365 nm. This study investigates the effect of informative Worldview-3 SWIR bands for wetland classification performance. Worldview-3 imagery acquired over Sunchon Bay, which is a coastal wetland located in South Korea, is used to implement the classification. Land-cover classes for the scene are determined by referring to national land-cover maps, which are provided by the Ministry of Environment, overlapped with the scene. After that, training data for each determined class are collected. In order to analyze the effect of SWIR bands, classifications with and without SWIR bands are carried out and the results are then compared. In this regard, a SVM (Support Vector Machine) is utilized as their classifier. As a result of the accuracy assessments performed by test data that are independently extracted from training data, it was confirmed that classification performance was improved when the SWIR bands are included as input features for SVM-based classification.

• Korean Journal of Remote Sensing
• /
• v.24 no.5
• /
• pp.507-515
• /
• 2008

Many studies have generally used a large number of pure pixels as an approach to training set design. The training set are used, however, varies between classifiers. In the recent research, it was reported that small mixed pixels between classes are actually more useful than larger pure pixels of each class in Support Vector Machine (SVM) classification. We evaluated a usability of small mixed pixels as a training set for the classification of high-resolution satellite imagery. We presented an advanced approach to obtain a mixed pixel readily, and evaluated the appropriateness with the land cover classification from IKONOS satellite imagery. The results showed that the accuracy of the classification based on small mixed pixels is nearly identical to the accuracy of the classification based on large pure pixels. However, it also showed a limitation that small mixed pixels used may provide insufficient information to separate the classes. Small mixed pixels of the class border region provide cost-effective training sets, but its use with other pixels must be considered in use of high-resolution satellite imagery or relatively complex land cover situations.

• Korean Journal of Remote Sensing
• /
• v.39 no.3
• /
• pp.269-282
• /
• 2023

The purpose of this study was to construct land cover maps using a deep learning model and to select the optimal deep learning model for land cover classification by adjusting the dataset such as input image size and Stride application. Two types of deep learning models, the U-net model and the DeeplabV3+ model with an Encoder-Decoder network, were utilized. Also, the combination of the two deep learning models, which is an Ensemble model, was used in this study. The dataset utilized RapidEye satellite images as input images and the label images used Raster images based on the six categories of the land use of Intergovernmental Panel on Climate Change as true value. This study focused on the problem of the quality improvement of the dataset to enhance the accuracy of deep learning model and constructed twelve land cover maps using the combination of three deep learning models (U-net, DeeplabV3+, and Ensemble), two input image sizes (64 × 64 pixel and 256 × 256 pixel), and two Stride application rates (50% and 100%). The evaluation of the accuracy of the label images and the deep learning-based land cover maps showed that the U-net and DeeplabV3+ models had high accuracy, with overall accuracy values of approximately 87.9% and 89.8%, and kappa coefficients of over 72%. In addition, applying the Ensemble and Stride to the deep learning models resulted in a maximum increase of approximately 3% in accuracy and an improvement in the issue of boundary inconsistency, which is a problem associated with Semantic Segmentation based deep learning models.

• Korean Journal of Remote Sensing
• /
• v.18 no.3
• /
• pp.163-169
• /
• 2002

The land uses of Korean peninsula are very complicated and high-density. Therefore, the image classification using coarse resolution satellite images may not provide good results for the land cover classification. The purpose of this paper is to compare the classification accuracy of visual interpretation with that of digital image classification of satellite remote sensing data such as 20m SPOT and 30m TM. In this study, hybrid classification was used. Classification accuracy was assessed by comparing each classification result with reference data obtained from KOMPSAT-1 EOC imagery, air photos, and field surveys.

• Korean Journal of Remote Sensing
• /
• v.32 no.4
• /
• pp.353-364
• /
• 2016

Yangon city is experienced a rapid urban expansion over the last two decades due to accelerate with the socioeconomic development. This research work studied an investigation into the application of the integration of the Remote Sensing (RS) and Geographic Information System (GIS) for observing Land Use and Land Cover (LULC) patterns and evaluate its impact on Land Surface Temperature (LST) of the downtown, suburban 1 and suburban 2 of Yangon city. The main purpose of this paper was to examine and analyze the variation of the spatial distribution property of the LULC of urban spatial information related with the LST and Normalized Difference Vegetation Index (NDVI) using RS and GIS. This paper was observed on image processing of LULC classification, LST and NDVI were extracted from Landsat 8 Operational Land Imager (OLI) image data. Then, LULC pattern was linked with the variation of LST data of the Yangon area for the further connection of the correlation between surface temperature and urban structure. As a result, NDVI values were used to examine the relation between thermal behavior and condition of land cover categories. The spatial distribution of LST has been found mixed pattern and higher LST was located with the scatter pattern, which was related to certain LULC types within downtown, suburban 1 and 2. The result of this paper, LST and NDVI analysis exhibited a strong negative correlation without water bodies for all three portions of Yangon area. The strongest coefficient correlation was found downtown area (-0.8707) and followed suburban 1 (-0.7526) and suburban 2(-0.6923).

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.3 no.3
• /
• pp.163-170
• /
• 2001

The objective of this study was to evaluate land cover classification of PyeongTaeg area by Landsat Thematic Mapper Data June, 1997. This study was also to make more correct reference data using DGPS, aerophoto, and topographical chart etc.. The result of the area of paddy and upland were estimated 4,949 $\textrm{km}^2$ and 16,157 $\textrm{km}^2$, respectively. Correctness of estimation by using DGPS, aerophoto, topographical chart were shown over 90% correct in case of rice paddy field, water, and sea, while upland, vinyl house, forest, grassland, village were shown low correctness. Total average accuracy was shown to be 85.8%. Correctness of paddy field showed high value of 92%, showing that use of remote sensing data was proved to be effective methods to estimate spatial distribution and cultivation status of paddy field. Classification result of sea, water area, downtown had higher correctness, while upland, vinyl-house, grassland were proved to be relatively low correctness because of it's small area and mixed distribution.

• Proceedings of the KSRS Conference
• /
• 2009.03a
• /
• pp.354-359
• /
• 2009

Land cover types of Hustai National Park (HNP) in Mongolia, a hotspot area with rare species, were classified and their temporal changes were evaluated using Landsat MSS TM/ETM data between 1994 and 2000. Maximum likelihood classification analysis showed an overall accuracy of 88.0% and 85.0% for the 1994 and 2000 images, respectively. Kappa coefficients associated with the classification were resulted to 0.85 for 1994 and 0.82 for 2000 image. Land cover types revealed significant temporal changes in the classification maps between 1994 and 2000. The area has increased considerably by $166.5km^2$ for mountain steppe. By contrast, agricultural areas and degraded areas affected by human being activity were decreased by $46.1km^2$ and $194.8km^2$ over the six year span, respectively. These areas were replaced by mountain steppe area. Specifically, forest area was noticeably fragmented, accompanied by the decrease of $\sim400$ ha. The forest area revealed a pattern with systematic gain and loss associated with the specific phenomenon called as forest free-south slope. We discussed the potential environmental conditions responsible for the systematic pattern and addressed other biological impacts by outbreaks of forest pests and ungulates.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.2
• /
• pp.44-55
• /
• 2018

The importance of establishing a greenhouse gas inventory is emerging for policymaking and its implementation to cope with climate change. Thus, it is needed to establish Approach 3 level Land Use, Land-Use Change and Forestry (LULUCF) matrix that is spatially explicit regarding land use classifications and changes. In this study, four types of spatial information suitable for establishing the LULUCF matrix were analyzed - Cadastral Map, Land Cover Map, Forest Map, and Biotope Map. This research analyzed the classification properties of each type of spatial information and compared the quantitative and qualitative characteristics of the maps in Boryeong city. Drawn from the conclusions of the quantitative comparison, the forest area showed the maximum difference of 50.42% ($303.79km^2$) in the forest map and 46.09%($276.65km^2$) in the cadastral map. The qualitative comparison drew five qualitative characteristics: data construction scope difference, data construction purpose difference, classification standard difference, and classification item difference. As a result of the study, it was evident that the biotope map was the most appropriate spatial information for the establishment of the LULUCF matrix. In addition, if the LULUCF matrix is made by integrating the biotope, the forest map, and the land cover map, the limitations of each spatial information would be improved. The accuracy of the LULUCF matrix is expected to be improved when the map of the level-3 land cover map and the biotope map of 1:5,000 covering the whole country are completed.