• The Proceeding of the Korean Institute of Electromagnetic Engineering and Science
• /
• v.3 no.2
• /
• pp.66-78
• /
• 1992

Available data for the radar clutter, and the empirical and the theoretical models for the radar clutter have been collected and analyzed. Data sets and models from the remote sensing field have been studied extensively. Although the grazing angles used in remote sensing is larger than the angles normally encountered in radar clutter application, remote sensing field has the merit of abundance of data in much more detailed target classes. The remote sensing model is also superior to the normally used clutter models in the sense that each target class has its own model, rather than being generally characterized by assumed roughness parameters.

• Korean Journal of Remote Sensing
• /
• v.18 no.3
• /
• pp.155-162
• /
• 2002

Neural networks have been focused on as a robust classifier for the remotely sensed imagery due to its statistical independency and teaming ability. Also the artificial neural networks have been reported to be more tolerant to noise and missing data. However, unlike the conventional statistical classifiers which use the statistical parameters for the classification, a neural network classifier uses individual training sample in teaming stage. The training performance of a neural network is know to be very sensitive to the discrepancy of the number of the training samples of each class. In this paper, the effect of the population discrepancy of training samples of each class was analyzed with three layered feed forward network. And a method for reducing the effect was proposed and experimented with Landsat TM image. The results showed that the effect of the training sample size discrepancy should be carefully considered for faster and more accurate training of the network. Also, it was found that the proposed method which makes teaming rate as a function of the number of training samples in each class resulted in faster and more accurate training of the network.

• Review of Korea Contents Association
• /
• v.7 no.4
• /
• pp.23-28
• /
• 2009

• Korean Journal of Remote Sensing
• /
• v.7 no.1
• /
• pp.69-86
• /
• 1991

An unsupervised region based image segmentation algorithm implemented with a pyramid structure has been developed. Rather than depending on thraditional local splitting and merging of regions with a similarity test of region statistics, the algorithm identifies the homogenous and boundary regions at each level of pyramid, then the global parameters of esch class are estimated and updated with values of the homogenous regions represented at the level of the pyramid using the mixture distribution estimation. The image is then classified through the pyramid structure. Classification results obtained for both simulated and SPOT imagery are presented.

• Korean Journal of Remote Sensing
• /
• v.25 no.1
• /
• pp.11-20
• /
• 2009

Due to increasing frequency of yellow dust, not to mention high rate of precipitation and cloud formation in summer season of Korea, atmospheric correction of satellite remote sensing is necessary. This research analyzes the effect of atmospheric correction has on imagery classification by comparing DN distribution before and after atmospheric correction. The image used in the research is LANDSAT-5 TM. As for atmospheric correction module, commercial product ATCOR, FLAASH as well as COST model released on the internet, were used. The result of experiment shows that class separability increased in building areas.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_4
• /
• pp.1351-1361
• /
• 2019

In this study, the annual surface soil erosion amount of before (2007 year) and after (2015 year) the river improvement projects were calculated using RUSLE (Revised Universal Soil Loss Equation) in the Geumgang basin (Daecheong-Dam to Geumgang Estuary-Bank). After the results were classified into five classes, the results were compared and analyzed with the results of the change in the land cover. In order to generate each factor of RUSLE, various spatial information data, such as land cover maps for 2007 and 2015 years, national basic spatial information, soil map, and average annual precipitation data were utilized. The results of the analysis are as follows: 1) annual surface soil erosion in the study area increased the area of class 1 in 2015 years compared to 2007, 2) the area of class 2, 3 and 5 decreased, 3) the area of class 4 increased. It is believed that the average annual amount of surface soil erosion decreased in most areas due to the reduction of annual average precipitation, the formation of ecological parks, the expansion of artificial facilities, and the reduction of illegal farmland.

• Korean Journal of Remote Sensing
• /
• v.19 no.4
• /
• pp.329-339
• /
• 2003

In this study, an approach of image fusion in decision level has been proposed for unsupervised image classification using the images acquired from multiple sensors with different characteristics. The proposed method applies separately for each sensor the unsupervised image classification scheme based on spatial region growing segmentation, which makes use of hierarchical clustering, and computes iteratively the maximum likelihood estimates of fuzzy class vectors for the segmented regions by EM(expected maximization) algorithm. The fuzzy class vector is considered as an indicator vector whose elements represent the probabilities that the region belongs to the classes existed. Then, it combines the classification results of each sensor using the fuzzy class vectors. This approach does not require such a high precision in spatial coregistration between the images of different sensors as the image fusion scheme of pixel level does. In this study, the proposed method has been applied to multispectral SPOT and AIRSAR data observed over north-eastern area of Jeollabuk-do, and the experimental results show that it provides more correct information for the classification than the scheme using an augmented vector technique, which is the most conventional approach of image fusion in pixel level.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.6
• /
• pp.628-638
• /
• 2023

Maritime Autonomous Surface ships(MASS) are gradually gaining importance. Until fully autonomous ships are developed, they will likely be controlled by remote operators who are based in a Remote Operations Center. However, there is currently no internationally or domestically established licensing for them. This issue can potentially pose a risk to navigation safety due to operations being handled by unqualified remote operators. We conducted a literature review and proposed criteria for the adoption of a licensing system for remote operators. We have futher offered alternatives to integrate this license into the existing officer licensing system, and analyzed them using Analytic Hierarchy Process(AHP). Subsequently,, theprimary need to enact legislation for remote operators is observed. The most preferred approach is to include the occupation of a remote operator in the Ship Officer Act, Article 4: Occupational Categories and Class of Licenses. Therefore, it would be logical for the organizational structure of the Remote Operation Center to mirror the traditional Bridge Resource Management. This study will contribute to the efficient training of remote operators and the safe navigation of autonomous ships with a focus on human resource management.

• Communications of Mathematical Education
• /
• v.35 no.2
• /
• pp.173-191
• /
• 2021

This study noted that a survey of teachers in a leading study conducted in Korea during the Pandemics period pointed out that the "real-time interactive" classes account for a significantly small portion of the remote class format. Contentually, the study reported cases of developing and applying "real-time interactive" class materials based on "planar decision requirements" of high school mathematics subject geometry. The teacher who participated in the development was a math teacher who worked at a Seoul-based high school with 28 years of high school teaching experience, and a teacher who was in charge of geometry in the math department in 2020. The development teacher decided to develop real-time interactive classes. In particular, the materials were developed by organizing the class guidance plan in four stages: 'Meeting and Class Guidance', 'Giving motivation', 'Suggesting tasks', 'Individual Investigative Activities and Teacher Feedback' and 'Reflection and Evaluation' which were selected through the process of selecting the class contents and selecting online class tools. At this time, the development teacher produced and presented about five minutes of video material using the videooscribe, a whiteboard animation program. And in case of task number 8, it consisted of recording the students' free thoughts after class, which served as a role of assessment by students themselves and providing feedback to their teachers. This study is a case study that introduces a series of courses in which field teachers develop class materials, and in addition to presenting class materials that can be applied directly to classes, is a result of a study that focuses on the role of presenting samples for future class data development. The materials developed were verified as class materials based on the opinions of the students who participated in the class and the results of the evaluation commissioned by the three math teachers.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.570-573
• /
• 2006

College GIS and remote sensing education usually consists of commercial software packages implementations in the classroom. Computer programming is quite important when college graduates work in private or public sectors relevant with GIS and remote sensing implementations. The objective of this paper was to develop a valley management system which implements GIS and remote sensing as the key components for education. The Valley Authority is entitled with water resource protection for sustainable drinking water supply of the second largest city in Taiwan. The test area consists of three different government agencies, Forest Service, EPA, and Water Resource Agency. Materials were provided by the Valley Authority in ArcGIS file format. MapObjects have made the GIS development process much easier. Remote sensing with image manipulation functions were provided by computer programming with Visual Baisc.NET and Visual C#.NET. Attributes inquiry are performed by these two computer languages as well. ArcGIS and ArcPad are also used for simple GIS manipulations of the test area. Comparison between DIY and commercial GIS can be made by college students. Functions provided by the developed valley management system depending on how many map layers have been used and what types of MapObjects components have been used. Computer programming experience is not essential but can be helpful for a college student. The whole process is a step-by-step sequence which college students can modify to depict their capability in GIS and remote sensing. The development process has gone through one semester, three hours every week in 18 weeks. College students enrolled in this class entitled with GIS showed remarkable progresses both in GIS and remote sensing.