• 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 HCI Society of Korea
• /
• v.2 no.2
• /
• pp.35-43
• /
• 2007

This paper presents a system for image matching and recognition based on image feature detection and description techniques from artificial satellite photographs. We propose some kind of parameters from the varied environmental elements happen by image handling process. The essential point of this experiment is analyzes that affects match rate and recognition accuracy when to change of state of each parameter. The proposed system is basically inspired by Lowe's SIFT(Scale-Invariant Transform Feature) algorithm. The descriptors extracted from local affine invariant regions are saved into database, which are defined by k-means performed on the 128-dimensional descriptor vectors on an artificial satellite photographs from Google earth. And then, a label is attached to each cluster of the feature database and acts as guidance for an appeared building's information in the scene from camera. This experiment shows the various parameters and compares the affected results by changing parameters for the process of image matching and recognition. Finally, the implementation and the experimental results for several requests are shown.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.196-199
• /
• 2008

Lineament is defined generally as a linear feature or pattern on interpretation of a satellite image and indicates the geological structures such as faults and fractures. For this reason, a lineament extraction and analysis using remote sensing images have been widely used for mapping large areas. The Gyeong-gang Fault is a NNE trending structure located in Gangwon-do and Kyeonggi-do district. However, a few geological researches on that fault have been carried out and its trace or continuity is ambiguous. In this study, we investigate the geologic features at Gyeong-gang Fault Zone using LANDSAT ETM+ satellite image and SRTM digital elevation model. In order to extract the characteristics of geologic features effectively, we transform the LANDSAT ETM+ image using Principal Component Analysis (PCA) and create a shade relief from SRTM data with various illumination angles. The results show that it is possible to identify the dimensions and orientations of the geologic features at Gyeong-gang Fault Zone using remote sensing data. An aerial photograph interpretation and a field work will be future tasks for more accurate analysis in this area.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.10 no.2
• /
• pp.93-103
• /
• 1985

The digital signal processing technique by bandwidth compression has been grown up ragidly owing to integrated circuit developments. In this project, we have proposed the Lee Weighted Hadamard (LWH) transform which retains the main properties of Hadamard matirx. The LWH matrix was weighted in the center of the spatial domain. The human visual of the mid spatial are emphasized more than the low and high spatial frequencies. The fast algorithms of the LWH transform has been studied for hardware realization. The result of this project are availabel to airplane photograph, X-Ray, CATV and the artificial satellite of the digital image processing.

• Journal of Korean Society of Forest Science
• /
• v.78 no.3
• /
• pp.263-273
• /
• 1989

Accurate and cost-effective classification of forest vegetation is the primary goal for forest management and utilization of forest resources. Aerial photograph and remote sensing are the most frequent and effective method in forest resources inventories. TM and MSS are the principal observing instruments on the Landsat-4 and -5 earth observing satellite. Especially TM has considerably greater spatial, spectral, and radiometric resolution power than MSS, that is, the IFOV of TM at a nadir is 30m compared to 80m for MSS. In this study, we used TM data to classify forest types and compared the result with forest type map manufactured by interpretation of B/W infrared photographs. As a result, land use types were well defined with TM data. But classifying forest types was a little difficult and indistinct. However, the spectral signatures of forest in every season and growing stages remained as problems to be solved, and also the most effective selection and combination method of bands for differentiating the spectral plots among classes.

• Journal of the Korean Geophysical Society
• /
• v.9 no.4
• /
• pp.387-395
• /
• 2006

Nowadays, various digital maps on a reduced scale were drawn in Korea including the topographic series of a nation. Though these digital maps are drawn and revised by using aerial photograph or satellite image, there are some problems that it is difficult to revise or renew the topography and natural feature immediately which changes frequently. As the countermeasures of these problems we use GPS accumbency method, which provides user with convenience and accumbency accuracy which is required to revise and renew digital maps. But acquiring correct position by using GPS only may cause not a few errors because of environmental effect of satellite signal errors that GPS obtains. Although accumulated errors which is the major problem of existing method was diminished owing to the position signal received from satellite which is about 20,183km above, the area that can not receives the signal is occur such as woods and high-rise buildings space. And because of the GDOP (Geometry Dilution of Precision) of GPS satellite and the periodically changing orbit of the satellite, the position calculating problems occur. For settlement of these problems and accurate position determination, DGPS (Differential GPS) is indispensably needed. So, in this study, by adapting Radio Beacon Receiver for marine position determination which is the most convenience method of DGPS methods, we elevated accuracy of modification and renewal of digital map and, having wide application in various measurements, proposed the rapid measurement method about widespread area. In this study, wewant to propose the work scheme of rapid modification and renewal of digital map by using Beacon GPS which is comparatively cheap of all the DGPS methods and which makes it possible to measure independently.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.871-884
• /
• 2021

The purpose of this study was to determine ways to increase efficiency in constructing and verifying artificial intelligence learning data on land cover using aerial and satellite images, and in applying the data to AI learning algorithms. To this end, multi-resolution datasets of 0.51 m and 10 m each for 8 categories of land cover were constructed using high-resolution aerial images and satellite images obtained from Sentinel-2 satellites. Furthermore, fine data (a total of 17,000 pieces) and coarse data (a total of 33,000 pieces) were simultaneously constructed to achieve the following two goals: precise detection of land cover changes and the establishment of large-scale learning datasets. To secure the accuracy of the learning data, the verification was performed in three steps, which included data refining, annotation, and sampling. The learning data that wasfinally verified was applied to the semantic segmentation algorithms U-Net and DeeplabV3+, and the results were analyzed. Based on the analysis, the average accuracy for land cover based on aerial imagery was 77.8% for U-Net and 76.3% for Deeplab V3+, while for land cover based on satellite imagery it was 91.4% for U-Net and 85.8% for Deeplab V3+. The artificial intelligence learning datasets on land cover constructed using high-resolution aerial and satellite images in this study can be used as reference data to help classify land cover and identify relevant changes. Therefore, it is expected that this study's findings can be used in the future in various fields of artificial intelligence studying land cover in constructing an artificial intelligence learning dataset on land cover of the whole of Korea.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.22 no.6
• /
• pp.63-76
• /
• 2019

UAVs are unmanned, autonomous or remotely piloted aircraft. As UAVs become smaller, lighter and more economical, their applications continue to expand. Researches on UAVs in the field of remote sensing show development methods and purposes similar to those on satellite images, and they are widely used in studies such as 3D image composition and monitoring. In the field of environmental impact assessment(EIA), satellite information and data are mainly used. However, only low-resolution images covering long distances and large-scale data allowing for rough examination are being provided, so their uses are seriously limited. Therefore, in this paper, we construct spatial information of forest area by using unmanned aerial vehicle and seek efficient utilization and policy improvement in the field of environmental impact assessment. As a result, high-resolution images and data from UAVs can be used to identify the location status of SEIA, EIA, and small scale EIA project plans and to evaluate detailed environmental impact analysis. In addition, when provided together with infographics about Post-environmental impact investigation, it was confirmed that the possibility of periodic spatial information construction and evaluation can be used throughout the entire project contents and project post-process.In order to provide sophisticated infographics for the EIA, drone photography and GCP surveying methods were derived.The results of this study will be used as a basis for improving high-resolution monitoring and environmental impact assessment in the forest sector.

• Korean Journal of Geomatics
• /
• v.3 no.2
• /
• pp.81-86
• /
• 2004

In recent years, the importance of geospatial data have been emphasized not only for the national GIS programs and but also in the value added commercial and industry markets. There is no doubt that GIS, GPS, aerial and satellite imagery data were provided powerful tools to support national information infrastructure for geospatial database. While great emphasis has been laid on the geospatial data, there has been little analysis or evaluation of how to maximize the benefits of using these information sources. Also, with the proliferation of geographic data and information sources such as satellite imagery, digital aerial photograph, digital topographic and vector data, there is a great need to inform professionals from all disciplines as to the benefits of these information sources and how to best put them to use within any given application. From the first publication of KSGPC(Korean Society of Geodesy, Photogrammetry and Cartography) papers in 1981, our objective was, and is, to help develop the wider spectrum of GIS in the academy and industry by exposing new users to the benefits of GIS, remote sensing, mapping, GPS and photogrammetry. In this presentation, we will introduce KSGPC works and will evaluate GIS-related governmental policies and programs in Korea for the past and the future to present different status between Korea and Russia. It is now important to investigate lessons learnt from two countries' experiences and developed an empirical framework to combine outcome from GIS-related researches in Korea and Russia. This may enable GIS professionals to gain a wider range of experiences in the international context, and consequently, help them to develop new markets for GIS. Therefore, we arranged the possible action items and interesting points to corporate and to promote the academic growth in the practice of GIS.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.395-409
• /
• 2022

The purpose of this study is to evaluate the classification performance and applicability when land cover datasets constructed for AI training are cross validation to other areas. For study areas, Gyeongsang-do and Jeolla-do in South Korea were selected as cross validation areas, and training datasets were obtained from AI-Hub. The obtained datasets were applied to the U-Net algorithm, a semantic segmentation algorithm, for each region, and the accuracy was evaluated by applying them to the same and other test areas. There was a difference of about 13-15% in overall classification accuracy between the same and other areas. For rice field, fields and buildings, higher accuracy was shown in the Jeolla-do test areas. For roads, higher accuracy was shown in the Gyeongsang-do test areas. In terms of the difference in accuracy by weight, the result of applying the weights of Gyeongsang-do showed high accuracy for forests, while that of applying the weights of Jeolla-do showed high accuracy for dry fields. The result of land cover classification, it was found that there is a difference in classification performance of existing datasets depending on area. When constructing land cover map for AI training, it is expected that higher quality datasets can be constructed by reflecting the characteristics of various areas. This study is highly scalable from two perspectives. First, it is to apply satellite images to AI study and to the field of land cover. Second, it is expanded based on satellite images and it is possible to use a large scale area and difficult to access.