• The Korean Journal of Applied Statistics
• /
• v.29 no.5
• /
• pp.859-872
• /
• 2016

Land cover classification is an important tool for preventing natural disasters, collecting environmental information, and monitoring natural resources. Hyperspectral imaging is widely used for this task thanks to sufficient spectral information. However, the curse of dimensionality, spatiotemporal variability, and lack of labeled data make it difficult to classify the land cover correctly. We propose a novel classification framework for land cover classification of hyperspectral data based on convolutional neural networks. The proposed framework naturally incorporates full spectral features with the information from neighboring pixels and has advantages over existing methods that require additional feature extraction or pre-processing steps. Empirical evaluation results show that the proposed framework provides good generalization power with classification accuracies better than (or comparable to) the most advanced existing classifiers.

• Journal of Broadcast Engineering
• /
• v.7 no.1
• /
• pp.2-9
• /
• 2002

Recently. VR( Virtual Reality) applications such as virtual studio and virtual character are wifely used In TV programs. and AR( Augmented Reality) applications are also belong taken an interest increasingly. This paper introduces a virtual screen system. which Is a new AR application for broadcasting. The virtual screen system is a real-time video augmentation system by tracking a chroma-patterned moving panel. We haute recently developed a virtual screen system.'K-vision'. Our system enables the user to hold and morse a simple panel on which live video, pictures of 3D graphics images can appear. All the Images seen on the panel change In the correct perspective, according to movements of the camera and the user holding the panel, in real-time. For the purpose of tracking janet. we use some computer vision techniques such as blob analysis and feature tracking. K-vision can work well with any type of camera. requiring no special add-ons. And no need for sensor attachments to the panel. no calibration procedures required. We are using K-vision in some TV programs such as election. documentary and entertainment.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.4
• /
• pp.85-90
• /
• 2001

Recently there are lots of concerning on robot agent system working for itself with the trends of the research of bio-mimetic system and intelligent Therefore it is necessary to develop more humanized interface system from communicating with the robot agent. In this paper a virtual 3D interface system is proposed based on Internet for remote controlling and monitoring of robot agent. The proposed system is constructed as manager-agent model and a man can order a job at the 3D virtual interface environment of the manager located remotely Then the robot agent detects a 3D profile data from a range finder automatically and the robot moves the object to the new position in real space. The proposed system supports a advanced interface displaying virtual 3D graphics and real moving images and which makes it possible one to manage the robot agent more conveniently.

• Journal of Korean Society for Geospatial Information Science
• /
• v.1 no.2 s.2
• /
• pp.167-175
• /
• 1993

This article contains three objectives. First it is to revise unnecessary procedures of a transportation models and transform results of a model into an image. Second objectives is to develop an operational structures which automatically input all data needed from arc-node topology to link-node topology of transportation network. By solving the network discrepancy, time and money for constructing to transportation can be saved. In addition, the rate of errors that my caused during data input process can be reduced. Conclusively, it is found that the integration package may provide user friendliness and reduce the rate of errors. The package can extract informations such as distance between zones and nodes, lane numbers, and hierarchy from arc-node topology for executing SDI. Another advantage of integration is the ability of spatial analysis. The integrated package may provide adequate arrangements of traffic facilities and checking systems of the shortest path. Finally, the database function of GIS package provides various information about study area for transportation analysis.

• The Journal of the Korea Contents Association
• /
• v.8 no.8
• /
• pp.244-252
• /
• 2008

This research differentiate the technique of Jungkwon-jirugi, one of the basic movements of Taekwondo, into two movements stop-jirugi and push-jirugi and gives analysis of the impulse, acceleration and velocity in the point of motor control. For this, we tried graphic analysis using an acceleration sensor and high speed camera which was made from USA in 2005 and took pictures at 250 frames per second. We reached the following conclusions. First, the acceleration wave of push-jirugi was a period longer than stop-jirugi, meaning that the push-jirugi motion asserts force for a longer time. Second, the acceleration and velocity graph shows that the highest velocity occurs on the point when the acceleration begins to decrease right after reaching its maximum. Third, according to the image analysis using the high speed camera, we could find out that the shoulder is pushed a little even in the stop-jirugi motion.

• The Journal of the Korea Contents Association
• /
• v.10 no.1
• /
• pp.147-159
• /
• 2010

The touch screen phone launched domestically in Korea, unlike the existing plane UI, it applied a cubic shape of 3D UI which provides three dimensional solid graphic. This study proposes to examine the correlation between the users' experience of 3D GUI, which were made by two different companies, and the brand. From this point of view, this study sets up a hypothesis about intimate correlation between individual differentiated brand and the user experience. Base on that, a model was designed. This study measured the satisfaction of user experience through the disclosure and non-disclosure of brand, focusing on 3D GUI cases which were launched so far, and it demonstrated that there was a clear difference in the degree of satisfaction. Through this examine, a brand was confirmed as one of the important element of user experience in using the 3D GUI that was launched competitively by companies. Therefore, the result of this study suggest that the designers need to establish strategies that make the brand as the core subject of design during the process of manufacturing product and service.

• The Journal of the Korea Contents Association
• /
• v.6 no.11
• /
• pp.110-117
• /
• 2006

With the New media of present age we are living at, strongly entice consumers through various sensible technology and give influences on our life. They are visually formed but make us feel them as if formed tactile. The masses of today are meeting media through all the senses in daily life according to the spread of on-line media and in such course they want momentary and tactile share. Since appearance of mass society and cinema following such current, art has appealed to dispersive and tactile perception, and such public way of perception makes it possible to experience 'visual tactility' in daily life in accordance with the development of on-line game culture among others. The shock effects, given by editing of game animations which are produced for epic experience of on-line game, arouse tactility in addition to visibility. Under this assumption and on the basis of visual tactility theory as well as montage theory of image by Walter Benjamin, the research intends to explain that public tactile shock does not result from simple graphic effect but from montage effect and dispersive acceptance.

• Journal of Radiation Protection and Research
• /
• v.34 no.2
• /
• pp.69-75
• /
• 2009

To obtain precise information about characteristics of gamma ray detector system responses, we developed new GUI computer program to analize full-energy absorption peak using our developed Delphi computer code for educational purpose. By use of the well known 4 nonlinear peak shaping functions, peaks were fitted with least square fit method in this code. In this paper, we described the methods to search for 12 coefficients in above 4 nonlinear peak shaping functions by use of our developed code in details. The computer code was tested for 1 $\mu$Ci $^{137)Cs$ 661 keV gamma ray peak spectrum detected by 25 % relative efficiency HPGe detector with 5.35 cm (D) $\times$ 5.5 cm (L) size.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.6
• /
• pp.796-801
• /
• 2009

In medical practice, the diagnosis or prediction models requiring complicated computations are not widely recognized due to difficulty in interpreting the course of reasoning and the complexity of computations. Medical personnel have used the nomograms which are a graphical representation for numerical relationships that enables to easily compute a complicated function without help of computation machines. It has been widely paid attention in diagnosing diseases or predicting the progress of diseases. A nomogram is constructed from a set of clinical data which contain various attributes such as symptoms, lab experiment results, therapy history, progress of diseases or identification of diseases. It is of importance to select effective ones from available attributes, sometimes along with parameters accompanying the attributes. This paper introduces a nomogram construction method that uses a naive Bayesian technique to construct a nomogram as well as a genetic algorithm to select effective attributes and parameters. The proposed method has been applied to the construction of a nomogram for a real clinical data set.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.1
• /
• pp.273-285
• /
• 2000

While page segmentation is an important step in document recognition, there haven's been many researches on it. More improvement is still needed on the segmentation of document elements in complicated or color documents. In this paper, I present a new page segmentation method which can segment pages with multiple columns, dotted lines, graphics, and photographs. I extract all connected components using contour following and combine them depending on the size and positional information of them. Separate text location is done for non-text color regions to extract possible text lines. To see the performance of the proposed method, experiments are done for 180 documents. Four commercial OCR programs are also tested and the proposed method showed the best result.