• Journal of Korean Society for Geospatial Information Science
• /
• v.15 no.3
• /
• pp.33-39
• /
• 2007

Hyperspectral remote sensing data contain plenty of information about objects, which makes object classification more precise. In this paper, we proposed a new spectral similarity measure, called Spectral Mutual Information (SMI) for hyperspectral image classification problem. It is derived from the concept of mutual information arising in information theory and can be used to measure the statistical dependency between spectra. SMI views each pixel spectrum as a random variable and classifies image by measuring the similarity between two spectra form analogy mutual information. The proposed SMI was tested to evaluate its effectiveness. The evaluation was done by comparing the results of preexisting classification method (SAM, SSV). The evaluation results showed the proposed approach has a good potential in the classification of hyperspectral images.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.4
• /
• pp.397-404
• /
• 2012

Jeju where concentrates on agriculture and tourism, conversion of outdoor culture into cultivation under structure happens actively for the purpose of increasing profit so continuous examination on house cultivation area is very important for this region. This paper is to suggest the effective image classification method using high resolution satellite image to detect the greenhouse. We carried out classification of greenhouse using the supervised classification and rule-based classification method about Formosat-2 images. Connecting result of two classification try to find accuracy improvement for greenhouse detection. Results about each classification method were calculated the accuracy by comparing with the result of visual detection. As a result, mahalanobis distance among the supervised methods was resulted in the highest detection. Also, it could be checked that detection accuracy was improved by tying with result of supervised method and result of rule-based classification. Therefore, it was expected that effective detection of greenhouse would be feasible if henceforward further study is performed in the process of connecting supervised classification and rule-based classification.

• Korean Journal of Remote Sensing
• /
• v.33 no.3
• /
• pp.325-331
• /
• 2017

In this study, digital elevation models(DEM) of tidal flat, according to different times, was produced by means of the Drone and commercial software in order to measure seawater change during high tide at water-channel in the Hampyung Bay. To correct the produced DEMs of the tidal flat where is inaccessible to collect control points, the DEM matching method was applied by using the reference DEM, that is previously obtained, instead of the survey. After the ortho-image was made from the corrected DEM, the land cover classified image was produced. The changes of seawater amount according to the times were analyzed by using the classified images and DEMs. As a result, it was confirmed that the amount of water rapidly increased as the time passed during high tide.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.1
• /
• pp.71-79
• /
• 2014

Most researches have created the impervious surface map by using low-spatial-resolution satellite imagery and are inefficient to generate the object-based impervious map with a broad area. In this study, segment-based impervious surface mapping algorithm is proposed using the RapidEye satellite imagery in order to map impervious area. At first, additional bands are generated by using TOA reflectance conversion RapidEye data. And then, shadow and water class are extracted using training data of converted reflectance image. Object-based impervious surface can be generated by spectral mixture analysis based on land cover map of Ministry of Environment with medium scale, in the case of other classes except shadow and water classes. The experiment shows that result by our method represents high classification accuracy compared to reference data, quantitatively.

• Journal of Korea Water Resources Association
• /
• v.35 no.4 s.129
• /
• pp.411-423
• /
• 2002

Accurate and real time forecasting of runoff has a high priority in the drainage basins prone to short, high intensity rainfall events causing flash floods. To take into account the resolution of hydrological variables within a drainage basin, use of distributed system models is preferred. The Landsat Thematic Mapper(TM) observations enable detailed information on distribution of land cover and other related factors within a drainage basin and permit the use of distributed system models. This paper describes monitoring technique of rainfall excess by SCS curve number method. The time series maps of rainfall excess were generated for all the storm events to show the spatiotemporal distribution of rainfall excess within study basin. A combination of the time series maps of rainfall excess with a flow routing technique would simulate the flow hydrograph at the drainage basin outlet.

• Journal of Korea Water Resources Association
• /
• v.36 no.4
• /
• pp.609-621
• /
• 2003

The purpose of this study is to evaluate the hydrological impact due to temporal land cover change by gradual urbanization of upstream watershed of Pyeongtaek gauging station of Anseong -cheon. WMS HEC-1 was adopted, and DEM with 200$\times$200m resolution and hydrologic soil group from 1:50,000 soil map were prepared. Land covers of 1986, 1990, 1994 and 1999 Landsat TM images were classified by maximum likelihood method. The watershed showed a trend that forest ＆ paddy areas decreased and urban/residential area gradually increased for the period of 14 years. The model was calibrated at 2 locations (Pyeongtaek and Gongdo) by comparing observed with simulated discharge results for 5 summer storm events from 1998 to 2001. The watershed average CN values varied from 61.7 to 62.3 for the 4 selected years. To identify the impact of streamflow by temporal area change of a target land use, a simple evaluation method that the CN values of areas except the target land use are unified as one representative CN value was suggested. By applying the method, watershed average CN value was affected in the order of paddy, forest and urban/residential, respectively.

• Spatial Information Research
• /
• v.19 no.6
• /
• pp.43-54
• /
• 2011

This study proposes a rule-based image classification method for the time-series analysis of changes in the land surface of the Seongnam-Yongin area using satellite-image data from 2000 to 2009. In order to identify the change patterns during each period, 11 classes were employed in accordance with statistical/mathematic rules. A generalized algorithm was used so that the rules could be applied to the unsupervised-classification method that does not establish any training sites. The results showed that the urban area of the object increased by 145% due to housing-site development. The image data from 2009 had a classification accuracy of 98%. For method verification, the results were compared to land-cover changes through Post-classification comparison. The maximum utilization of the available data within multiple images and the optimized classification allowed for an improvement in the classification accuracy. The proposed rule-based image-classification method is expected to be widely employed for the time-series analysis of images to produce a thematic map for urban development and to monitor urban development and environmental change.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.1909-1913
• /
• 2008

수자원의 공급적인 측면에서 내륙지역에 비하여 불리한 도서지역은 단기간의 가뭄에도 생활용수가 고갈되어 매년 상습적인 식수난을 겪고 있는 상태이다. 전국 3,170개 섬 중 491개 유인도에 831,295명(2003년)이 거주하고 있으나 상수도 보급률은 28.7%에 불과하다(환경부, 2005). 나머지 71.3%의 도서지역 주민들은 간이 급수시설, 우물, 지붕수 등을 생활용수로 이용하고 있다. 이와같이 도서지역은 상수도 보급율이 열악하여 지하수자원에 대한 의존도가 내륙지역에 비하여 높아 지하수자원을 통해 부족한 용수를 공급받아야 할 실정이다. 용수공급을 위한 지하수의 개발을 위해서 무엇보다 선행되어야 할 것은 도서지역의 지하수개발가능량 평가이며 이의 평가를 위해서는 지하수함양량의 파악이 이루어져야 한다. 지하수함양량 산정 기법 중 하나인 NRCS-CN방법은 선행강우조건, 토지피복상태, 수문학적 토양군 등의 인자들에 의해 산정되어진다. 수문학적 토양군의 경우 대부분의 연구에서 정정화 등 (1995)에 의해 분류된 자료가 이용되고 있었으나 최근 정광호 등(2007)에 의하여 수문학적 토양군이 재분류 되었다. 본 연구에서는 NRCS-CN방법을 이용하여 식수난에 어려움을 겪고 있는 우리나라 서남해안의 14개 도서지역에 대하여 수문학적 토양군의 1995년 분류와 2007년 분류를 적용하여 지하수함양량을 산정하고 비교하였다. 1995년 분류와 2007년 분류에서 지하수함양량과 함양률은 개도, 생일도, 보길도를 제외한 도서지역은 1%미만의 차이로 변화가 거의 없는 것으로 나타났다. 개도, 생일도, 보길도는 1995년 분류에 비하여 2007년 분류에서 $2.2%{\sim}2.8%$ 감소하였다. 따라서 대상지역의 수문학적토양군의 재분류에 의한 지하수함양량 및 함양률의 차이가 미미함을 알 수 있었다. 연평균 함양량은 1995년 분류와 2007년 분류에서 수도가 590.8mm, 583.5mm로 최대값을 가지며 가파도가 270.2mm, 270.5mm로 최소값을 가지는 것으로 나타났다. 함양률의 경우 1995년 분류에서는 개도가 29.8%의 최대값을 나타내었고 가파도가 23.3%의 최소값을 가지는 것으로 나타났으며 2007년 분류에서는 사량도 상도가 28.5%의 최대값을 나타내었고 가파도가 23.3%의 최소값으로나타났다.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2005.11a
• /
• pp.17-22
• /
• 2005

Generally, pixel-based classification, utilize the similarity of distances between the pixel values in feature space, is applied to land use mapping using satellite remote sensing data. But this method is Improper to be applied to the very high resolution satellite data (VHRS) due to complexity of the spatial structure and the variety of pixel values. In this paper, we performed the hierarchical classification of VHRS imagery by data fusion, which integrated LiDAR height and intensity information. MLC and ISODATA methods were applied to IKONOS-2 imagery with and without LiDAR data prior to the hierarchical classification, and then results was evaluated. In conclusion, the hierarchical method with LiDAR data was the superior than others in VHRS imagery and both MLC and ISODATA classification with LiDAR data were better than without.

• Korean Journal of Remote Sensing
• /
• v.20 no.6
• /
• pp.383-396
• /
• 2004

The application of spatial statistics to obtain the spatial uncertainty distributions in classification of remote sensing images is investigated in this paper. Two quantitative methods are presented for describing two kinds of uncertainty; one related to class assignment and the other related to the connection of reference samples. Three quantitative indices are addressed for the first category of uncertainty. Geostatistical simulation is applied both to integrate the exhaustive classification results with the sparse reference samples and to obtain the spatial uncertainty or accuracy distributions connected to those reference samples. To illustrate the proposed methods and to discuss the operational issues, the experiment was done on a multi-sensor remote sensing data set for supervised land-cover classification. As an experimental result, the two quantitative methods presented in this paper could provide additional information for interpreting and evaluating the classification results and more experiments should be carried out for verifying the presented methods.