• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.71-80
• /
• 2024

In this study, a proposed ensemble learning technique aims to enhance the semantic segmentation performance of images captured by Unmanned Aerial Vehicles (UAVs). With the increasing use of UAVs in fields such as urban planning, there has been active development of techniques utilizing deep learning segmentation methods for land cover segmentation. The study suggests a method that utilizes prominent segmentation models, namely U-Net, DeepLabV3, and Fully Convolutional Network (FCN), to improve segmentation prediction performance. The proposed approach integrates training loss, validation accuracy, and class score of the three segmentation models to enhance overall prediction performance. The method was applied and evaluated on a land cover segmentation problem involving seven classes: buildings,roads, parking lots, fields, trees, empty spaces, and areas with unspecified labels, using images captured by UAVs. The performance of the ensemble model was evaluated by mean Intersection over Union (mIoU), and the results of comparing the proposed ensemble model with the three existing segmentation methods showed that mIoU performance was improved. Consequently, the study confirms that the proposed technique can enhance the performance of semantic segmentation models.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.577-587
• /
• 2023

The utilization of crowdsourced spatial data has been actively researched; however, issues stemming from the uncertainty of data quality have been raised. In particular, when low-quality data is mixed into drone imagery datasets, it can degrade the quality of spatial information output. In order to address these problems, the study presents a methodology for automatically validating the geometric quality of crowdsourced imagery. Key quality factors such as spatial resolution, resolution variation, matching point reprojection error, and bundle adjustment results are utilized. To classify imagery suitable for spatial information generation, training and validation datasets are constructed, and machine learning is conducted using a radial basis function (RBF)-based support vector machine (SVM) model. The trained SVM model achieved a classification accuracy of 99.1%. To evaluate the effectiveness of the quality validation model, imagery sets before and after applying the model to drone imagery not used in training and validation are compared by generating orthoimages. The results confirm that the application of the quality validation model reduces various distortions that can be included in orthoimages and enhances object identifiability. The proposed quality validation methodology is expected to increase the utility of crowdsourced data in spatial information generation by automatically selecting high-quality data from the multitude of crowdsourced data with varying qualities.

• Korean Journal of Remote Sensing
• /
• v.39 no.3
• /
• pp.283-295
• /
• 2023

With the development of sensor and satellite technology, numerous high-resolution and multi-spectral satellite images have been available. Due to their wavelength-dependent reflection, transmission, and scattering characteristics, multi-spectral satellite images can provide complementary information for earth observation. In particular, the short-wave infrared (SWIR) band can penetrate certain types of atmospheric aerosols from the benefit of the reduced Rayleigh scattering effect, which allows for a clearer view and more detailed information to be captured from hazed surfaces compared to the visible band. In this study, we proposed a multi-resolution transform-based image fusion method to combine visible and SWIR satellite images. The purpose of the fusion method is to generate a single integrated image that incorporates complementary information such as detailed background information from the visible band and land cover information in the haze region from the SWIR band. For this purpose, this study applied the Laplacian pyramid-based multi-resolution transform method, which is a representative image decomposition approach for image fusion. Additionally, we modified the multiresolution fusion method by combining a haze-guided weight map based on the prior knowledge that SWIR bands contain more information in pixels from the haze region. The proposed method was validated using very high-resolution satellite images from Worldview-3, containing multi-spectral visible and SWIR bands. The experimental data including hazed areas with limited visibility caused by smoke from wildfires was utilized to validate the penetration properties of the proposed fusion method. Both quantitative and visual evaluations were conducted using image quality assessment indices. The results showed that the bright features from the SWIR bands in the hazed areas were successfully fused into the integrated feature maps without any loss of detailed information from the visible bands.

• Journal of Korean Society of Forest Science
• /
• v.100 no.3
• /
• pp.315-326
• /
• 2011

In recent years, domestic and international interests focus on climate change, and importance of forest as carbon sink have been also increased. Particularly REDD+ mechanism expanded from REDD (Reduced Emissions from Deforestation and Degradation) is expected to perform a new mechanism for reducing greenhouse gas in post 2012. To conduct this mechanism, countries which try to get a carbon credit have to certify effectiveness of their activities by MRV (Measuring, Reporting and Verification) system. This study analyzed the approaches for detecting land cover change and estimating carbon stock by remote sensing technology which is considered as the effective method to develop MRV system. The most appropriate remote sensing for detection of land cover change is optical medium resolution sensors and satellite SAR (Synthetic Aperture Radar) according to cost efficiency and uncertainty assessment. In case of estimating carbon stock, integration of low uncertainty techniques, airborne LiDAR (Light Detection and Ranging), SAR, and cost efficient techniques, optical medium resolution sensors and satellite SAR, could be more appropriate. However, due to absence of certificate authority, guideline, and standard of uncertainty, we should pay continuously our attention on international information flow and establish appropriate methods. Moreover, to apply monitoring system to developing countries, close collaboration and monitoring method reflected characteristics of each countries should be considered.

• Korean Journal of Remote Sensing
• /
• v.30 no.4
• /
• pp.525-536
• /
• 2014

In this study, a method to assess and monitor hydrological drought using remote sensing was investigated for use in regions with limited observation data, and was applied to the Upper Namhangang basin in South Korea, which was seriously affected by the 2008-2009 drought. Drought information may be obtained more easily from meteorological data based on water balance than hydrological data that are hard to estimate. Air temperature data at 2 m above ground level (AGL) were estimated using remotely sensed data, evapotranspiration was estimated from the air temperature, and the correlations between precipitation minus evapotranspiration (P-PET) and streamflow percentiles were examined. Land Surface Temperature data with $1{\times}1km$ spatial resolution as well as Atmospheric Profile data with $5{\times}5km$ spatial resolution from MODIS sensor on board Aqua satellite were used to estimate monthly maximum and minimum air temperature in South Korea. Evapotranspiration was estimated from the maximum and minimum air temperature using the Hargreaves method and the estimates were compared to existing data of the University of Montana based on Penman-Monteith method showing smaller coefficient of determination values but smaller error values. Precipitation was obtained from TRMM monthly rainfall data, and the correlations of 1-, 3-, 6-, and 12-month P-PET percentiles with streamflow percentiles were analyzed for the Upper Namhan-gang basin in South Korea. The 1-month P-PET percentile during JJA (r = 0.89, tau = 0.71) and SON (r = 0.63, tau = 0.47) in the Upper Namhan-gang basin are highly correlated with the streamflow percentile with 95% confidence level. Since the effect of precipitation in the basin is especially high, the correlation between evapotranspiration percentile and streamflow percentile is positive. These results indicate that remote sensing-based P-PET estimates can be used for the assessment and monitoring of hydrological drought. The high spatial resolution estimates can be used in the decision-making process to minimize the adverse impacts of hydrological drought and to establish differentiated measures coping with drought.

• Korean Journal of Remote Sensing
• /
• v.28 no.5
• /
• pp.489-499
• /
• 2012

In this paper, a classifier ensemble framework for remote sensing data classification is presented that combines classification results generated from both different training sets and different classifiers. A core part of the presented framework is to increase a diversity between classification results by using both different training sets and classifiers to improve classification accuracy. First, different training sets that have different sampling densities are generated and used as inputs for supervised classification using different classifiers that show different discrimination capabilities. Then several preliminary classification results are combined via a majority voting scheme to generate a final classification result. A case study of land-cover classification using multi-temporal ENVISAT ASAR data sets is carried out to illustrate the potential of the presented classification framework. In the case study, nine classification results were combined that were generated by using three different training sets and three different classifiers including maximum likelihood classifier, multi-layer perceptron classifier, and support vector machine. The case study results showed that complementary information on the discrimination of land-cover classes of interest would be extracted within the proposed framework and the best classification accuracy was obtained. When comparing different combinations, to combine any classification results where the diversity of the classifiers is not great didn't show an improvement of classification accuracy. Thus, it is recommended to ensure the greater diversity between classifiers in the design of multiple classifier systems.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_1
• /
• pp.547-557
• /
• 2017

In this paper, a new spectral unmixing based target detection algorithm is proposed which adopted Iterative Error Analysis as a tool for extraction of background endmembers by using the target spectrum to be detected as initial endmember. In the presented method, the number of background endmembers is automatically decided during the IEA by stopping the iteration when the maximum change in abundance of the target is less than a given threshold value. The proposed algorithm does not have the dependence on the selection of image endmembers in the model-based approaches such as Orthogonal Subspace Projection and the target influence on the background statistics in the stochastic approaches such as Matched Filter. The experimental result with hyperspectral image data where various real and simulated targets are implanted shows that the proposed method is very effective for the detection of both rare and non-rare targets. It is expected that the proposed method can be effectively used for mineral detection and mapping as well as target object detection.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2010.06a
• /
• pp.187-187
• /
• 2010

공간자료를 다루는 일반적인 과정은 연구자의 정의에 따라 달라질 수 있지만, 일반적으로 자료 수집, 자료 구축, 분석 및 결과 도출의 일반적인 과학/공학적 분석 절차와 유사하다. 산업체의 관점에서 볼 때, 1990년대 초기 국가GIS 사업이 시작될때부터 현재까지는 공인된 자료 구축에 많은 주안점을 두어서 기존 아날로그 자료의 디지털화, 자료 가공, 데이터베이스 구축, 자료의 시각화 등의 일반적인 자료 구축 및 도시에 주안점을 두어왔다. 또한 다양한 공간해상도의 원격탐사 자료와 같이 다중 근원 자료의 이용이 빈번해짐에 따라 공간자료의 갱신 또한 중요한 부분을 차지하고 있다. 그러나, 공간자료를 다루는 일련의 과정이 궁극적으로는 특정 분야에서의 의사 결정보조자료의 제공 등을 지향한다고 간주할 때, "from data to information to knowledge"의 중간 혹은 최종 단계의 결과물을 산출하기 위한 적절한 분석 기술의 개발 및 적용 또한 중요한 부분을 차지한다. 공간분석을 별도의 학문분야로 간주하느냐 아니냐의 문제와는 상관없이, 최근 20년간 공간분석은 GIS 및 원격탐사 분야뿐만 아니라 기본적으로 공간자료를 다루는 많은 응용분야에서 공간자료의 이해와 부가정보의 생산을 위한 중요한 기술 분야로 간주되어 왔다. 공간분석의 여러 응용 분야중에서 환경분야에의 적용 연구는 또한 환경과학이라는 별도의 분야 뿐만 아니라, 기존 학문들인 지리학, 생태학, 지구과학, 사회학, 경제학, 도시 계획 등의 하위분야에서 중요한 방법론으로 자리 잡고 있다. 이 기술 세미나에서는 환경분야에 직간접적으로 활용이 가능한 공간정보 분석 기술의 동향을 지구통계학을 중심으로 소개하고자 한다. 국내에서 크리깅으로 대표되어온 지구통계학은 적용하는 학문 분야에 따라 보다 넓은 의미를 가지는 공간 통계학이라는 용어로 사용되고 있지만, 보다 학문적/기술적 의미로 살펴보면 공간분석의 특화된 분야로 간주할 수 있다. 1950년대 알려진 광상의 위치 정보를 이용하여 은둔 광상의 위치를 추정하기 위해 기본 개념이 소개된 이후에 수학적으로 이론이 1960년대 정립된 지구통계학은 많은 발전을 이루어 현재 다양한 분야에서 적용되고 있다. 그러나 외국과 달리 국내에서는 크리깅을 고급 내삽 기법으로만 간주하여 단순 주제도 작성에 제한적으로 사용하고 있다. 이 기술 세미나에서는 특정 학문분야에서 적용되기 보다는 일반적으로 통용될 수 있는 지구통계학의 기본 개념을 우선 소개한 후에, 국내외 학계에서의 환경주제도 제작과 관련된 주요 응용분야를 소개하고자 한다. 이후에 지구통계학이 적용될 수 있으면서, 다학제적 관점에서의 이슈가 될 수 있는 분야를 제시하고자 한다.

• Korean Journal of Remote Sensing
• /
• v.25 no.4
• /
• pp.367-374
• /
• 2009

Recently, new GIS applications such as gee portal and spatial data infrastructure are emerging. These are related to web computing techniques or methodologies based on web 2.0 paradigm, open API of portal, open source GIS, and international GIS standards which are independently on developing. The product of these applications can be realized in the linkage of those components. In this study, a case implementation concerning linkage with Google maps API and open source middleware named Deegree is carried out, and the results are discussed for open source uses in geo portal. Open source middleware supports various levels and types of OGC standards, so that it enables web publishing in the several web standard formats and data exchanges and interoperable uses between external database servers. Also the (unction extensions and the multi tier-based architecture within geo portal for specific purpose are possible.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.317-326
• /
• 2019

Development projects and related environmental impacts take place in space. Therefore, it is important to use spatial information in the environmental impact assessment process. This study proposes to construct spatial information produced by various organizations as an inventory and suggests it to be utilized in environmental impact assessment process. For this purpose, investigate the use of spatial information in the environmental impact assessment process and list of environmental space information provided by public information systems. and applied the methodology derived from previous studies to build an inventory of spatial information using environmental impact assessment. The spatial information utilized in the environmental impact assessment work was 64 items. Based on the data availability, linkage and renewability, the spatial information of the Environment that can be used for the environmental impact assessment was 45 items. Finally 49 items, including 19 new items were presented as an inventory, contributing to the performance of environmental impact assessment based on spatial information.