• Journal of Broadcast Engineering
• /
• v.25 no.5
• /
• pp.672-684
• /
• 2020

Restoring a low resolution and motion blurred light field has become essential due to the growing works on parallax-based image processing. These tasks are known as light-field enhancement process. Unfortunately, only a few state-of-the-art methods are introduced to solve the multiple problems jointly. In this work, we design a framework that jointly solves light field spatial super-resolution and motion deblurring tasks. Particularly, we generate a straight-forward neural network that is trained under low-resolution and 6-degree-of-freedom (6-DOF) motion-blurred light field dataset. Furthermore, we propose the strategy of local region optimization on the adversarial network to boost the performance. We evaluate our method through both quantitative and qualitative measurements and exhibit superior performance compared to the state-of-the-art methods.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.4
• /
• pp.1942-1950
• /
• 2013

This paper suggests a new method of detecting attacks of network traffic by visualizing original traffic data and applying multi-class SVM (support vector machine). The proposed method first generates 2D images from IP and ports of transmitters and receivers, and extracts linear patterns and high intensity values from the images, representing traffic attacks. It then obtains variance of ports of transmitters and receivers and extracts the number of clusters and entropy features using ISODATA algorithm. Finally, it determines through multi-class SVM if the traffic data contain DDoS, DoS, Internet worm, or port scans. Experimental results show that the suggested multi-class SVM-based algorithm can more effectively detect network traffic attacks.

• Journal of Digital Convergence
• /
• v.18 no.10
• /
• pp.403-408
• /
• 2020

This paper is to evaluate the usability of two representative video meeting services currently used by university for research to improve the quality of university remote lecture. questionnaires based on Kano Model were designed and in-depth interviews were conducted to provide qualitative approaches. Screen-sharing functions, the one-dimensional functions was the most important function. and attractive functions had relatively diverse directions. For essential functions, there was a wide gap in quality due to user-specific equipment. The function in which other platforms exist or business-related was not important. Webex reacted negatively to the aging UI, while Zoom responded negatively to the unilateral mute function. In addition, the development direction was presented in five ways as a result of analysis of these results. under Corona-19 situation, I hope this study will lead to continuous research to make stepping stone for remoted educational development.

• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.252-260
• /
• 2016

The performance of human detection system is affected by camera location and view angle. In 2D image acquired from such camera settings, humans are displayed in different sizes. Detecting all the humans with diverse sizes poses a difficulty in realizing a real-time system. However, if the size of a human in an image can be predicted, the processing time of human detection would be greatly reduced. In this paper, we propose a method that estimates human size by constructing an indoor scene in 3D space. Since the human has constant size everywhere in 3D space, it is possible to estimate accurate human size in 2D image by projecting 3D human into the image space. Experimental results validate that a human size can be predicted from the proposed method and that machine-learning based detection methods can yield the reduction of the processing time.

• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.180-191
• /
• 2016

When up-scaling algorithms for visible light images are applied to infrared (IR) images, they rarely work because IR images are usually blurred. In order to solve such a problem, this paper proposes an up-scaling algorithm for IR images. We employ adaptive dynamic range encoding (ADRC) as a simple classifier based on the observation that IR images have weak details. Also, since human visual systems are more sensitive to edges, our algorithm focuses on edges. Then, we add pre-processing in learning phase. As a result, we can improve visibility of IR images without increasing computational cost. Comparing with Anchored neighborhood regression (A+), the proposed algorithm provides better results. In terms of just noticeable blur, the proposed algorithm shows higher values by 0.0201 than the A+, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.19-26
• /
• 2020

This paper proposes a framework for creating acrobatic scenes such as soccer ball lifting using various users' videos. The proposed method can generate a desired result within a few seconds using a general video of user recorded with a mobile phone. The framework of this paper is largely divided into three parts. The first is to analyze the posture by receiving the user's video. To do this, the user can calculate the pose of the user by analyzing the video using a deep learning technique, and track the movement of a selected body part. The second is to analyze the movement trajectory of the selected body part and calculate the location and time of hitting the object. Finally, the trajectory of the object is generated using the analyzed hitting information. Then, a natural object lifting scenes synchronized with the input user's video can be generated. Physical-based optimization was used to generate a realistic moving object. Using the method of this paper, we can produce various augmented reality applications.

• Hwankyungkyoyuk
• /
• v.23 no.1
• /
• pp.99-111
• /
• 2010

The purpose of this study was to investigate high school students' perceptions of biotechnology. Participants in this study were 9th and 10th grade students who were enrolled in high schools in Gyeonggi Province. The survey instrument used in this study was a 26-item questionnaire that was designed to measure students' perceptions regarding biotechnology. The study revealed that students' perceptions were positive toward the use of biotechnology on biological objects such as plant, grain and microbes. However, their perceptions were negative toward the use of biotechnology on humans and animals. Male students' perceptions were more positive than female students and there were significant differences between male and female students(p<.01). The study also revealed that male and female students had positive perceptions about the use of biotechnology in the development of beneficial products. However, male students' perceptions were more positive than female students(p<.01). Female students' perceptions were slightly more negative than males and they indicated a measure of caution in the development of beneficial products using biotechnology. Regarding the reliability of biotechnological information acquired from food companies, TV broadcasters, and entertainers, male and female students tended to be highly negative. Students perceived that environmental, religious and ethical issues did not affect the use of biotechnology when asked the effect of these factors on the use of biotechnology. They perceived that food safety and genetic factors of microbes did affect the use of biotechnology. Thus, the study findings suggest that teaching and learning strategies based on the differences of perceptions between male and female students of this study be established and the use of media, development of teaching method and materials be promoted in order to enhance student's performance in environmental education.

• The Journal of Korean Association of Computer Education
• /
• v.12 no.3
• /
• pp.75-83
• /
• 2009

Moving picture has become the important media in education with expanded e-learning paradigm, but Korea Educational Metadata has limitation about representing information of lots of events and objects in moving picture. Announcing the MPEG-7 specification the information of lots of events and objects in it can be presented in terms of semantic and structural description of moving pictures. In this paper moving picture searching system model that integrates two metadata specifications, such as KEM and MPEG-7, is proposed. In this model one ontology to combine two metadata specifications is designed, and the other ontology about knowledge of a subject matter is added to search efficiently in searching system. As some moving picture data from Edunet were selected and stored in our server, our prototype of searching system using MPEG-7 and KEM shows the results that we are expected.

• Journal of Digital Convergence
• /
• v.18 no.9
• /
• pp.317-322
• /
• 2020

The purpose of this study is to lay the groundwork for the operation method for correctly operating remote lectures at universities. Among the universities that started non-face-to-face classes due to 'COVID-19', college students and graduate students from some universities who conducted remote lectures through Cisco's Webex meeting were studied on how to operate the remote lecture platform. First, the requirements for lectures for remote lectures were established through the literature survey, and effective operation measures were proposed through the survey. The research method was conducted on a total of 45 college and graduate students from April 21 to May 15, 2020. The results of the study showed that the operation plan for the basic and meeting elements. Based on this study, we expect it to be used in disaster situations or classes that may occur after COVID-19. In the future, the usability evaluation of the remote class platform and the direction in which the domestic remote lecture platform should move should be presented.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.2
• /
• pp.349-356
• /
• 2020

This paper introduces the implementation of a driver's condition warning system using eye aspect ratio to prevent a car accident. The proposed driver's condition warning system using eye aspect ratio consists of a camera, that is required to detect eyes, the Raspberrypie that processes information on eyes from the camera, buzzer and vibrator, that are required to warn the driver. In order to detect and recognize driver's eyes, the histogram of oriented gradients and face landmark estimation based on deep-learning are used. Initially the system calculates the eye aspect ratio of the driver from 6 coordinates around the eye and then gets each eye aspect ratio values when the eyes are opened and closed. These two different eye aspect ratio values are used to calculate the threshold value that is necessary to determine the eye state. Because the threshold value is adaptively determined according to the driver's eye aspect ratio, the system can use the optimal threshold value to determine the driver's condition. In addition, the system synthesizes an input image from the gray-scaled and LAB model images to operate in low lighting conditions.