• Journal of Korean Society of Forest Science
• /
• v.81 no.4
• /
• pp.346-356
• /
• 1992

The extensive Snake River floodplain in Northwest United States has experienced major changes in water channels and vegetation types due to floodings. To detect the change of wetland cover-types for the period of 1985 and 1988, post-classification comparison and image differencing change detection techniques were evaluated using Landsat-5 TM digital data. Differenced infrared-band images indicated better accuracy indices than any visible-band images. A thresholding technique was applied to identify the change and no change categories from the transformed images produced by image differencing. The problems in using different accuracy indices, including the Kappa coefficient of agreement, overall accuracy, producer's accuracy, user's accuracy, and average accuracy(based on both the producer's and user's accuracy approaches) in determining an optimal threshold level, were examined.

• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.319-326
• /
• 2002

In this paper, we have designed and implemented cluttering classification systems- unsupervised classifiers-for the processing of satellite remote sensing images. Implemented systems adopt various design patterns which include a factory pattern and a strategy pattern to support various satellite images'formats and to design compatible systems. The clustering systems consist of sequential clustering, K-Means clustering, ISODATA clustering and Fuzzy C-Means clustering classifiers. The systems are tested by using a Landsat TM satellite image for the classification input. As results, these clustering systems are well designed to extract sample data for the classification of satellite images of which there is no previous knowledge. The systems can be provided with real-time base clustering tools, compatibilities and components' reusabilities as well.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.1-4
• /
• 2001

The classification performance of Artificial Neural Network (ANN) and RBF-NN was compared for Landsat TM image. The RBF-NN was validated for three unique landuse types (e.g. Mixed landuse area, Cultivated area, Urban area), different input band combinations and classification class. The bootstrap resampling technique was employed to estimate the confidence intervals and distribution for unit load, The pollutant generation was varied significantly according to the classification accuracy and percentile unit load applied. Especially in urban area, where mixed landuse is dominant, the difference of estimated pollutant load is largely varied.

• Environmental Sciences Bulletin of The Korean Environmental Sciences Society
• /
• v.4 no.3
• /
• pp.149-156
• /
• 2000

This study presents an investigation of the changes that have occurred in the coastal ocean area of Kwangyang Bay located in the South Coastal region of Korea using remote sensing data based on Landsat Thematic Mapper (TM) multispectral digital data from 1988 and 1996. The coastal changes were detected using the digital histogram method and vector trace method. All the images were preprocessed, i.e. geometrically corrected, before the training set selection. when comparing the histograms of 7-band TM data, it was found that the band 5 image exhibited two critical Digital Number(DN) peaks, thereby indicating new coastal water and coastal land data. Based on this information, the coastal ocean area of the band 5 image was calculated using the vector tracing method supported by a CAD program. The result shows that the coastal ocean area decreased by about 5 % between 1988 to 1994. Accordingly, this gives a strong indication that the continuing land development will have a serious impact on the ecosystem of Kwangyang Bay.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.21 no.3
• /
• pp.261-267
• /
• 2003

We are able to simultaneously extract the land surface change information, as we input each information extracted from images classified during the two periods, as the attribute information of geographic information, and then use it a parameter of GIS. Hence, this research sought to present basic data far efficient management and development of land surface, together with land use trends, by using the remote-sensing technique enabling the acquisition of the land surface covering information, as well as the benefits of GIS. The research conducted a study on the extraction of land surface change information, and made it possible to treat image information easily compared to the existing image classification methods, thereby making it easy to know the land surface change process for each pixel.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.3
• /
• pp.34-43
• /
• 2005

We will catch the spatio-temporal changes that analyse the unknown topography of Go-Gunsan Islands using Landsat TM satellite images into an unsupervised ISODATA classification and a supervised nearest likelihood classification. Each sedimental topography has the different characteristics according to building the Saemangeum embarkment. We will deal with the distribution of sedimental shapes using ERDAS Imagine 8. 6. The result that classifies specifically topographic properties of our research area be considered to get use of establishing the reclaiming program and predicating the reclaimed sedimental topography. The research area can be classified into tidal flats and sea level using band 4 among 7 bands of Landsat TM. Also band 5 can be used to classify the special unknown shapes of tidal flats. We will clarify the efficiency that spatio-temporal sedimental changes can be extracted through processing satellite images. Therefore, the spatio-temporal unknown topography change monitoring using satellite images is expected to be very useful to clarify whether the tidal flat is generated or not in the Go-Gunsan Islands at the outer side of the embarkment after constructing completely the Saemangeum tidal embarkment.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2004.05b
• /
• pp.1300-1304
• /
• 2004

This study is to present a method of flood damaged area detection by the typhoon RUSA (August 31 - September 1, 2002) using Landsat 7 ETM+ and Landsat 5 TM images. Two images of Sept. 29, 2000 and Sept. 11, 2002 (path 115, row 34) were prepared for Gangreung, To identify the damaged areas, firstly, the NDVI (Normalized Difference Vegetation Index) of each image was computed, secondly, the NDVI values were reclassified as two categories that the negative index values including zero are the one and the positive index values are the other, thirdly the reclassified image before typhoon is subtracted from the reclassified image after typhoon to get DNDVI (Differential NDVI). Some part of urban and agricultural were classified into damaged area due to typhoon RUSA in Gangreung, $18.8km^2$ and $17.7km^2$ respectively.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.249-255
• /
• 1999

Water pollution is becoming a serious problem in the populous cities and coastal areas near industrial complex. Sometimes, phytoplankton is considered as the most important element in the coastal environment. Phytoplankton is easily estimated by measuring chlorophyll content in the laboratory. In this study, to build up estimating algorithm of the chlorophyll amount related to the monitoring of coastal environments in Kwangyang bay, the correlationship the respective in situ observed data with Landsat TM and SeaWiFS satellite Image was analyzed. It showed that Landsat TM band 3 image has the highest correlationship with observed data, and based upon this result the monitoring algorithm of chlorophyll in coastal area was extracted. This algorithm will be an important for extracting and controlling environment elements in coastal areas in the future. And it has a significant meaning that it has established a spatial data construction in which satellite image alone could monitor the coastal environment.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.3
• /
• pp.16-25
• /
• 1998

In this paper, we propose features extraction method using Rough sets theory for efficient data classifications in hyperspectral environment. First, analyze the properties of multispectral image data, then select the most efficient bands using discemibility of Rough sets theory based on analysis results. The proposed method is applied Landsat TM image data, from this, we verify the equivalence of traditional bands selection method by band features and bands selection method using Rough sets theory that pmposed in this paper. Finally, we present theoretical basis to features extraction in hyperspectral environment.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.2
• /
• pp.143-150
• /
• 2013

Recently, environmental issues such as climate warming, ozone layer depletion, reduction of tropical forests and desertification are emerging as global environmental problems beyond national problems. And international attention and effort have been carried out in many ways to solve these problems. In this study, the growth of green was calculated quantitatively using the technique of remote sensing and temperature change was figured out through temperature extraction in the city. The land-cover changes and thermal changes for research areas were analyzed using Landsat TM images on May 2002 and May 2009. Surface temperature distribution was calculated using spectral degree of brightness of Band 6 that was Landsat TM thermal infrared sensor to extract the ground surface temperature in the city. As a result of research, the area of urban green belt was increased by $2.87km^2$ and the ground surface temperature decreased by $0.6^{\circ}C{\sim}0.8^{\circ}C$ before and after tree planting projects. Henceforth, if the additional study about temperature of downtown is performed based on remote sensing and measurement data, it will contribute to solve the problems about the urban environment.