• 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.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.24 no.1
• /
• pp.139-145
• /
• 2006

The advantage of the lidar data is in fast acquisition and process time as well as in high accuracy and high point density. However lidar data itself is difficult to classify the earth surface because lidar data is in the form of irregularly distributed point clouds. In this study, we investigated land cover classification using both lidar data and optical image through a supervised classification method. Firstly, we generated 1m grid DSM and DEM image and then nDSM was produced by using DSM and DEM. In addition, we had made intensity image using the intensity value of lidar data. As for optical images, the red, blue, green band of CCD image are used. Moreover, a NDVI image using a red band of the CCD image and infrared band of IKONOS image is generated. The experimental results showed that land cover classification with lidar data and optical image together could reach to the accuracy of 74.0%. To improve classification accuracy, we further performed re-classification of shadow area and water body as well as forest and building area. The final classification accuracy was 81.8%.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.2 no.1
• /
• pp.32-44
• /
• 1999

Texture features can be incorporated in classification procedure to resolve class confusions. However, there have been few application-oriented studies made to evaluate the relative powers of texture analysis methods in a particular environment. This study evaluates the increases in the land-cover classification accuracy of the SPOT HRV multispectral data of Pusan Metropolitan area from texture processing. Twenty-four texture measures were derived from the SPOT HRV band 3 image. Each of these features were used in combination with the three spectral images in the classification of 10 land-cover classes. Supervised training and a Gaussian maximum likelihood classifier were used in the classification. It was found that while entropy produces the best empirical results in terms of the overall classification, other texture features can also largely improve the classification accuracies obtained by the use of the spectral images only. With the inclusion of texture, the classification for each category improves. Specially, urban built-up areas had much increase in accuracy. The results indicate that texture size 5 by 5 and 7 by 7 may be suitable at land cover classification of Pusan Metropolitan area.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.2
• /
• pp.19-25
• /
• 2013

Recently, the high-resolution satellite images is used the land cover and status data for the natural resources or environment management very helpful. The SVM algorithm of image processing has been used in various field. However, classification accuracy by SVM algorithm can be changed by various kernel functions and parameters. In this paper, the typical kernel function of the SVM algorithm was applied to the KOMPSAT-2 image and than the result of land cover performed the accuracy analysis using the checkpoint. Also, we carried out the analysis for selected the SVM kernel function from the land cover of the target region. As a result, the polynomial kernel function is demonstrated about the highest overall accuracy of classification. And that we know that the polynomial kernel and RBF kernel function is the best kernel function about each classification category accuracy.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1771-1777
• /
• 2023

With the advancements of deep learning, many semantic segmentation-based methods for land cover classification have been proposed. However, existing deep learning-based models only use image information and cannot guarantee spatiotemporal consistency. In this study, we propose a land cover classification model using geographical coordinates. First, the coordinate features are extracted through the Coordinate Hash Encoder, which is an extension of the Multi-resolution Hash Encoder, an implicit neural representation technique, to the longitude-latitude coordinate system. Next, we propose an architecture that combines the extracted coordinate features with different levels of U-net decoder. Experimental results show that the proposed method improves the mean intersection over union by about 32% and improves the spatiotemporal consistency.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.407-408
• /
• 2019

토지 피복과 관련된 지표면 파라미터는 일반적으로 지표에서 감지되어 위성영상에 나타난 많은 물리적 프로세스에 의존하며 계절적 주기성을 갖는 시간적 변화를 보인다. 하모닉 모형은 복잡한 파형을 정현파 성분의 합으로 표시함으로써 레벨, 주기, 진폭 및 위상 요소를 통한 변동을 분석함으로써 표면에서 관찰되는 계절적 변화 패턴을 모델링하는 데 적합한 모형이다. 본 연구에서는 MODIS NDVI (Normalized Difference Vegetation Index) 시계열 자료를 이용하여 하모닉 패턴의 특성에 따라 토지 피복을 분류하는 방법론을 제안하였다.

• The Journal of the Korea Contents Association
• /
• v.16 no.7
• /
• pp.31-41
• /
• 2016

Atmospheric correction as a preprocessing work should be performed to conduct accurately landcover/landuse classification using hyperspectral imagery. Atmospheric correction on airborne hyperspectral images was conducted and then the effect of atmospheric correction by comparing spectral reflectance characteristics before and after atmospheric correction for a few landuse classes was analyzed. In addition, land cover classification was first conducted respectively by the maximum likelihood method and the spectral angle mapper method after atmospheric correction and then the results were compared. Applying the spectral angle mapper method, the sea water area were able to be classified with the minimum of noise at the threshold angle of 4 arc degree. It is considered that object-based classification method, which take into account of scale, spectral information, shape, texture and so forth comprehensively, is more advantageous than pixel-based classification methods in conducting landcover classification of the coastal area with hyperspectral images in which even the same object represents various spectral characteristics.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.3
• /
• pp.65-71
• /
• 2012

Recently the high-resolution satellite images are helpfully using the land cover, status data for the natural resources or environment management. The effective satellite analysis process for these satellite images that require high investment can be increase the effectiveness has become increasingly important. In this Study, the statistical value of the training data is calculated and analyzed during the preprocessing. Also, that is explained about the maximum likelihood classification of traditional classification method, artificial neural network (ANN) classification method and Support Vector Machines(SVM) classification method and then the IKONOS high-resolution satellite imagery was produced the land cover map using each classification method. Each result data had to analyze the accuracy through the error matrix. The results of this study prove that SVM classification method can be good alternative of the total accuracy of about 86% than other classification method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.141-141
• /
• 2012

비점오염물질은 강우 시 유출되기 때문에 일간, 계절 간 유출량 변화가 대단히 크게 나타나며, 기후, 지형, 토지이용, 토양 등과 지역적인 특성과 유역 형상에 따라 변화되므로 비점오염원 유출량에 대한 정량화를 위해서는 강우지속시간동안 정확한 수질과 유량에 대한 측정 자료가 요구된다. 따라서 본 연구에서는 비점오염물질에 대해 현장 모니터링 및 현장 실측 관련 기존 연구자료 수집을 통해 중분류 토지피복분류별 원단위를 산정하였다. 또한 특정 유역에 중분류 토지피복 분류별 산정된 원단위를 적용하여 유역기반의 비점오염부하량을 산정 하였다. 대상 유역에 해당하는 하천 말단에서의 실측 자료를 활용하여 유역모형을 구축하고, 강우를 입력 자료로 하여 비점오염 물질별 부하량을 모의 산정하였다. 유역모형으로 HSPF(Hydrologic Simulation Program - Fortran)을 실제 대상유역에 적용하였고, 이에 따른 모의 결과를 실측치와 비교하여 부하량을 산정하였다. 이렇게 모의 산정된 부하량은 실측자료를 기반으로 산정된 원단위의 적용에 따른 부하량과 비교 검토하여 유역에 대한 비점오염원 부하량 산정 시 모형의 적용 가능성을 평가하였다. 본 연구에 적용된 대상유역은 동천유역으로 병성천의 주요 지류로서 유역의 상단에 위치하고 있다. 중분류 토지피복 중 공업지역, 교통지역, 과수원재배지, 비닐하우스재배지, 기타재배지에 대해서는 2008년부터 2010년까지 모니터링을 실시하였고, 이외의 중분류 토지피복에 대한 결과는 수계별 현재까지 진행되고 있는 환경기초조사사업 중 '주요 비점오염원 유출 장기 모니터링'사업의 자료를 활용하였다. 동천유역의 비점오염원 발생부하량을 산정한 결과, BOD 부하량은 대지의 경우 391.4 kg/day로서 중분류 군으로 구분한 결과에 비해 높게 산정되었다. T-N, T-P 발생부하량도 토지피복군이 대분류에서 중분류로 변화됨에 따라 부하량의 차이가 발생 하였다. 또한 동천유역에 대해 구축된 HSPF 모형의 적합도를 시기별 4개의 Case로 구분하여 평가해 보았는데 그 결과, 모형 모의치의 실측치에 대한 적합도가 높게 평가 되었다. 현재 특정 지역에 편중되어 조사되고 있는 중분류 토지피복을 조사 기관간의 교차 조사를 통해 지역적 제한성을 낮추고, 중분류에 속하는 세부피복지점을 확대하여 모니터링 지점의 다양성을 확보하여야 할 것으로 판단된다. 이와 동시에 한시적인 조사가 아닌, 장기간에 걸쳐 연구가 진행 될 경우 원단위에 대한 현재의 불확실성 및 제한성을 줄일 수 있을 것으로 판단되므로, 이러한 기초 자료 확보에 대한 장기적인 투자와 노력이 수반될 시 우리나라에 대표적으로 적용할 수 있는 비점오염원 원단위가 산정될 것으로 생각되며, 이러한 기틀이 마련되어야 비점오염원에 대한 적절한 유역관리방안을 수립할 수 있을 것으로 생각된다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.4
• /
• pp.25-33
• /
• 2015

The study of ecosystem assessment(ES) is based on land cover information, and primarily it is performed at the global scale. However, these results as data for decision making have a limitation at the aspects of range and scale to solve the regional issue. Although the Ministry of Environment provides available land cover data at the regional scale, it is also restricted in use due to the intrinsic limitation of on screen digitizing method and temporal and spatial difference. This study of objective is to generate UAV land cover map. In order to classify the imagery, we have performed resampling at 5m resolution using UAV imagery. The results of object-based image segmentation showed that scale 20 and merge 34 were the optimum weight values for UAV imagery. In the case of RapidEye imagery;we found that the weight values;scale 30 and merge 30 were the most appropriate at the level of land cover classes for sub-category. We generated land cover imagery using example-based classification method and analyzed the accuracy using stratified random sampling. The results show that the overall accuracies of RapidEye and UAV classification imagery are each 90% and 91%.