• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.07a
• /
• pp.218-219
• /
• 2015

본 논문에서는 스마트폰으로 촬영한 비디오 영상이나 일반 캠코더로 촬영한 비디오 영상을 4K 고화질 콘텐츠로 제작하는 것을 제안한다. 대화면 디스플레이와 고해상도 디스플레이가 점차 확대되면서 고화질 콘텐츠의 필요가 증대됨으로 이에 일반적으로 촬영된 영상을 비디오 편집기법을 이용하여 4K 고화질 해상도의 영상 제작을 제안하다. 하지만 일반 비디오카메라로 촬영한 영상을 4K 콘텐츠로 완전히 적용하기 위해서는 촬영에서 4K 카메라로 촬영하고 편집하면 4K 콘텐츠로 보다 해상도가 높은 콘텐츠를 제작할 수 있다고 사료한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.08a
• /
• pp.165-168
• /
• 2008

이 논문에서는 멀티미디어 컴퓨터에 연결된 미디키보드를 사용하여 피아노 연주를 혼자서 배우고 연습할 수 있도록 하기 위한 지능형 교습 시스템을 개발하기 위하여, 시스템 구조 및 모듈별 기능과 기본적인 사용자 인터페이스를 설계하였다. 시스템의 구조는 미디 키보드의 실시간 연주 샘플링 모듈, 미디 데이타의 시퀀싱 모듈, 사운드 합성 모듈과 연결된 지능형 교습 시스템이 된다. 세분화된 모듈별 기능에서는 학습 콘텐츠, 학습자 모델, 진단 평가 모듈, 진도 관리 모듈, 등의 세부적인 기능 설계가 필요하다. 학습자 모델을 기반으로 진단 편가 및 진도 관리를 지능적으로 처리하기 위해서 CLIPS를 사용한 전문가시스템 접근을 사용한다. 컴퓨터 화면상의 악보 디스플레이, 실시간 연주 화면, 진단 평가 디스플레이를 위한 GUI 설계가 필요하다. 그리고, 향후 콘텐츠 구축 및 시스템 구현 시에 예상되는 문제점과 해결 방안을 논의한다.

• Journal of the Semiconductor & Display Technology
• /
• v.18 no.2
• /
• pp.1-5
• /
• 2019

As the number of IOT devices is growing rapidly, various 'see-thru connection' techniques have been reported for efficient communication with them. In this paper, we propose a deep learning based IOT device recognition system for interaction with these devices. The overall system consists of a TensorFlow based deep learning server and two Android apps for data collection and recognition purposes. As the basic neural network model, we adopted Google's inception-v3, and modified the output stage to classify 20 types of IOT devices. After creating a data set consisting of 1000 images of 20 categories, we trained our deep learning network using a transfer learning technology. As a result of the experiment, we achieve 94.5% top-1 accuracy and 98.1% top-2 accuracy.

• Journal of the Semiconductor & Display Technology
• /
• v.17 no.3
• /
• pp.1-9
• /
• 2018

The drone has the restrictions on the controls, the battery and the surrounding environment in performing missions such as fire extinguishing. This restriction can improve the limitations that leave the leader can be monitored. The existing method of constructing the leader based on the GPS is highly dependent on the signal and is vulnerable to hardware defects. In this paper, we solve these problems with dynamic leaders decision. Drones can use their leader drones rather than remote controls. Information about the drones changes depending on the surrounding environment by replacing the leader with a dead battery or electing leader by the drones themselves without human intervention. This suggests that the leader monitors the community through a framework for continuing the drones collaboration and that the community can collaborate to overcome the limitations and continue the mission. The analysis of the proposed system through simulation experiments confirm that it has a better task performance. By using this system, it is possible to continue the mission and solve problems that are vulnerable to hardware defects.

• Journal of the Semiconductor & Display Technology
• /
• v.16 no.3
• /
• pp.127-130
• /
• 2017

In this research, we present a path planning method for an autonomous flight of unmanned aerial vehicles (UAVs) through reinforcement learning under simulated environment. We design the simulator for reinforcement learning of uav. Also we implement interface for compatibility of Deep Q-Network(DQN) and simulator. In this paper, we perform reinforcement learning through the simulator and DQN, and use Q-learning algorithm, which is a kind of reinforcement learning algorithms. Through experimentation, we verify performance of DQN-simulator. Finally, we evaluated the learning results and suggest path planning strategy using reinforcement learning.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.1
• /
• pp.104-107
• /
• 2021

Unity programs are largely recognized as game development tools. However, it has many functions built in, so it can be applied to various fields as well as game development. Therefore, in this paper, we propose a smart farm environmental control program using Unity and Photon. The proposed program has vast compatibility that is not limited to specific devices, and it is very easy to build network systems for remote control. In addition, the proposed programs were installed on various devices such as pc and smartphones, making it easy to control the smart farm environment system. Through experiments, it was confirmed that data transmission and reception between Windows and Android, other operating system environments, and that smart farm systems were operating normally.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.17-21
• /
• 2022

A variety of techniques have been proposed in the literature for depth improvement in depth from focus method. Unfortunately, these techniques over-smooth the depth maps over the regions of depth discontinuities. In this paper, we propose a robust technique for improving the depth map by employing a nonconvex smoothness function that preserves the depth edges. In addition, the proposed technique exploits the mutual structures between the depth map and a guidance map. This guidance map is designed by taking the mean of image intensities in the image sequence. The depth map is updated iteratively till the nonconvex objective function converges. Experiments performed on real complex image sequences revealed the effectiveness of the proposed technique.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.77-80
• /
• 2023

Since fires in uncontrolled environments pose serious risks to society and individuals, many researchers have been investigating technologies for early detection of fires that occur in everyday life. Recently, with the development of deep learning vision technology, research on fire detection models using neural network backbones such as Transformer and Convolution Natural Network has been actively conducted. Vision-based fire detection systems can solve many problems with physical sensor-based fire detection systems. This paper proposes a fire detection method using the latest YOLOv8, which improves the existing fire detection method. The proposed method develops a system that detects sparks and smoke from input images by training the Yolov8 model using a universal fire detection dataset. We also demonstrate the superiority of the proposed method through experiments by comparing it with existing methods.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.453-454
• /
• 2023

현재 선천적인 청각장애인이나 언어 장애가 있는 사람은 다른 사람과의 대화에 많은 불편을 겪고 있다. 매장을 이용하기 어려움은 물론 언어전달 능력이 떨어지기 때문에 간단한 의사소통을 통한 서로 간의 교류 또한 불편함을 감수해야 한다. 현재는 따로 디스플레이가 내장된 장치를 이용하여 지정된 장소에서 수화를 번역해야 하는 불편함을 해당 문제 해결을 위해 본 연구에서는 딥러닝을 적용하여 수화를 인식하고 번역하여 디스플레이에 텍스트를 출력해주는 시스템을 개발하였다. AI 프레임워크 MediaPipe와 SVM 알고리즘을 라즈베리파이에 적용하여 구현하였다. 개발한 시스템은 제스처에 대한 번역 결과를 제공한다. 기존의 지정된 장소가 아닌 대화가 필요한 모든 장소에서 번역이 가능하도록 개선하여 청각장애인과 언어장애가 있는 사람들과 소통의 불편함을 줄일 수 있을 것으로 기대할 수 있다.

• Annual Conference of KIPS
• /
• 2008.05a
• /
• pp.163-165
• /
• 2008

본 논문은 공간적인 제약을 벗어난 협업을 위하여 사용자가 서로의 모습을 확인할 수 있고, 직접적인 터치에 공간적인 터치(손 형상 및 제스처 인식)를 통하여 보다 자유롭고 직관적인 시스템 제어를 추구 하는 테이블 탑 디스플레이를 제안한다. 테이블 탑 디스플레이는 FTIR(Frustrated Total Internal Reflection : 내부 전반사 장애 현상) 방식이 아닌 TouchLight방식과 HoloWall방식을 조합하여 손 형상 및 제스처 인식을 할 수 있도록 설계하였다.