• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.23.4-23
• /
• 2001

This paper proposes a new approach to unsupervised classification of remotely sensed images. Fusion of optic images (Landsat TM) and radar data (SAR) has beer used to increase the accuracy of classification. Number of clusters is estimated using generalized Dunns measure. Performance of the proposed method is best observed comparing the classified images with classified aerial images.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.422-425
• /
• 2007

Traditionally, surface energy fluxes are obtained by model simulations or empirical equations with auxiliary meteorological data. These methods may not effectively represent the surface heat fluxes in a regional scale due to scene variability. On the other hand, remote sensing has the advantage to acquire data of a large area in an instantaneous view. The remotely sensed data can be further used to retrieve surface radiation and heat fluxes over a large area. In this study, the airborne and satellite images in conjunction with meteorological data and ground observations were used to estimate the surface heat fluxes over Taiwan's Chaiyi Plain. The results indicate that surface heat fluxes can be properly determined from both airborne and satellite images. The correlation coefficient of surface heat fluxes with in situ corresponding observations is over 0.60. We also observe that the remotely sensed data can efficiently provide a long term monitoring of surface heat fluxes over Taiwan's Chaiyi Plain.

• Journal of Environmental Impact Assessment
• /
• v.10 no.3
• /
• pp.167-174
• /
• 2001

National Parks in Korea occupy about four percents of South Korean land. This paper aims to prove the potentiality of the application of remotely sensed data for the effective management of National Parks. Different satellite images such as Landsat TM, IRS-1C, Alternative image, and IKONOS image are analyzed for the detection of changes, the extraction of degraded areas, and the comparison of Normalized Difference Vegetation Index (NDVI) in Bukhansan National Park. The artificial structures such as buildings and paved areas are overvalued in relatively higher resolution data. The result showed that the choice of images should be determined according to specific purposes and the combination of different resolution data may be the solution for the effective management of National Park.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.17 no.2
• /
• pp.189-196
• /
• 1999

Until now, Many approach to use the layer or attribute items in GIS the classification results of remotely sensed images is going on, but It was rarely ever tried to use the results of fuzzy classification in GIS. The fuzzy classification can be accurate than any other classification methods of remotely sensed images and can separately extract the result for each classification items. In this study, We applied to GIS database implementation with fuzzy classification result. In the process of this study, We convert the fuzzy classification image into the grid of GIS database, and Membership Grade Value files transformed to table database into the GIS. And then Membership Grade Values related to each grid-cell of database be able to verify with pointer layer. Finally, we can use the fuzzy classification images in GIS database.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.3
• /
• pp.150-158
• /
• 1998

This paper describes the classification of remotely sensed image data using fuzzy neural network, whose algorithm was obtained by replacing real numbers used for inputs and outputs in the standard back propagation algorithm with fuzzy numbers. In the proposed method, fuzzy patterns, generated based on the histogram ofeach category for the training data, are put into the fuzzy neural network with real numbers. The results show that the generalization and appoximation are better than that ofthe conventional network in determining the complex boundary of patterns.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.530-535
• /
• 2002

An approach for quickly updating GIS building data using high resolution remotely sensed data is proposed in this paper. High resolution remotely sensed data could be aerial photographs, satellite images and airborne laser scanning data. Data from different types of sensors are integrated in building extraction. Based on the extracted buildings and the outdated GIS database, the change-detection-template can be automatically created. Then, GIS building data can be fast updated by semiautomatically processing the change-detection-temp late. It is demonstrated that this approach is quick, effective and applicable.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.272-275
• /
• 2005

The digital map expresses natural topographies and artificial things with 3D position coordinates in the computer such as the road, railway, building, river, mountain, paddy and dryland. Therefore, the digital map is regarded as an important factor in the information-oriented society. However, it is difficult to maintain the most recent topographic information all the times because of restricted budget and time. For that, the efficient method corresponded with the digital map should be presented. This study aims to suggest the way to make an estimate of updating cost for 1:5,000 scale digital map by using remotely sensed data. To predict updating area of the digital map, the screen digitizing method was applied to the overlapped images and digital maps.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1284-1286
• /
• 2003

There is a growing demand on remotely sensed and GIS data services in modern society. However, conventional WEB applications based on client/server pattern can not meet the criteria in the future . Grid computing provides a promising resolution for establishing spatial information system toward future applications. Here, a new architecture of the distributed environment for remotely sensed data processing based on the middleware technology was proposed. In addition, in order to utilize the new environment, a problem had to be algorithmically expressed as comprising a set of concurrently executing sub-problems or tasks. Experiment of the algorithm was implemented, and the results show that the new environmental can achieve high speedups for applications compared with conventional implementation.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.6_2
• /
• pp.559-565
• /
• 2013

Spatial resolution of land covers from remotely sensed images can be increased using super-resolution mapping techniques for soft-classified land cover proportions. A further development of super-resolution mapping technique is downscaling the original remotely sensed image using super-resolution mapping techniques with a forward model. In this paper, the model for increasing spatial resolution of remote sensing multispectral image is tested with real SPOT 5 imagery at 10m spatial resolution for an area in Bac Giang Province, Vietnam in order to evaluate the feasibility of application of this model to the real imagery. The soft-classified land cover proportions obtained using a fuzzy c-means classification are then used as input data for a Hopfield neural network (HNN) to predict the multispectral images at sub-pixel spatial resolution. The 10m SPOT multispectral image was improved to 5m, 3,3m and 2.5m and compared with SPOT Panchromatic image at 2.5m resolution for assessment.Visually, the resulted image is compared with a SPOT 5 panchromatic image acquired at the same time with the multispectral data. The predicted image is apparently sharper than the original coarse spatial resolution image.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1326-1328
• /
• 2003

An elliptical basis function (EBF) network is proposed in this study for the classification of remotely sensed images. Though similar in structure, the EBF network differs from the well-known radial basis function (RBF) network by incorporating full covariance matrices and uses the expectation-maximization (EM) algorithm to estimate the basis functions. Since remotely sensed data often take on mixture -density distributions in the feature space, the proposed network not only possesses the advantage of the RBF mechanism but also utilizes the EM algorithm to compute the maximum likelihood estimates of the mean vectors and covariance matrices of a Gaussian mixture distribution in the training phase. Experimental results show that the EM-based EBF network is faster in training, more accurate, and simpler in structure.