• The KIPS Transactions:PartA
• /
• v.16A no.6
• /
• pp.427-436
• /
• 2009

Digital virtual manufacturing is a technology that aims for the rapid development of products and the verification of production-process in ways that are more efficient by integrating digital models within the entire manufacturing process. These digital models utilize various information technologies, such as 3D CAD and simulations. Mixed reality, which represents graphical objects for only needed parts against real scene, can bring a more enriched sense of reality to an existing virtual manufacturing system that is in a pure virtual environment, and it can reduce the time and money needed for modeling the environment. This paper suggests a method for planning virtual factory layouts based on mixed reality using legacy datathat are already constructed in the real field. To do this, we developed the method to acquire simulation data from legacy data and process this acquired data for visualization based on mixed reality. And then we construct display system based on mixed reality, which can simulate virtual factory layout with processed data. Developed system can reduce errors related with factory layout by verifying the location and application of equipments in advance before arrangement of real ones at the practical job site.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06d
• /
• pp.181-183
• /
• 2006

본 논문은 물리 공간의 이벤트를 입력받는 센서 노드들로 이루어진 무선 네트워크 환경에서 네트워크의 전체 에너지를 최소화하기 위한 방법으로, 라우팅, MAC, 어플리케이션 레이어 joint 설계 방식의 크로스 레이어에 기반을 둔 데이터 어그리게이션 알고리즘에 관한 것이다. 시뮬레이션 결과 우리는 제안한 방법을 통해 데이터 어그리게이션을 고려하지 않은 이전의 방법보다 확실한 에너지 감소 효과를 얻을 수 있고, 전체 무선 센서 네트워크의 에너지 사용을 개선 시킬 수 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10c
• /
• pp.674-676
• /
• 2000

인터넷과 같은 이질적인 네트워크환경에서 대용량의 비디오 데이터를 실시간으로 전송하기 위해서 계층적 코딩기법에 관한 연구가 진행되고 있으며, MPEG-2 비디오에서도 Scalability를 제공하고 있다. 하지만 이러한 계층적 코딩기법을 사용한다 하더라도 기본계층의 데이터량이 크기 때문에 실시간 서비스를 위해서는 상당량의 네트워크 자원을 필요로 하게 된다. 이에 네트워크 대여폭 변화에 능동적으로 적응하면서 네트워크 자원을 보다 효율적으로 사용할 수 있는 새로운 계층적 코딩기법과 전송 기법을 제안한다. 제안된 기법은 MPEG 비디오를 픽처층을 이용하여 공간적 계층적 코딩 후 다시 DCT블록에 대한 공간적 계층적 코딩을 수행하여 15개의 레이어로 분할하게 된다. 이렇게 분할된 레이어는 네트워크의 상태에 따라 선별적으로 전송되게 된다.

• Proceedings of the KIEE Conference
• /
• 2005.07c
• /
• pp.2351-2353
• /
• 2005

본 논문은 포장도로의 표면 상태를 고성능의 레이저 변위 센서를 사용하여 정밀하게 측정하고, GPS(Global Positioning System)를 사용하여 측정 위치 데이터를 획득하는 도로 표면 측정 장비 개발에 관한 논문이다. 본 연구에서는 전체 시스템을 설계하고, 차량 주행을 모사한 실험 모형을 제작하여 실내 실험을 실시하였으며, GPS 단말기로부터 실시간으로 위치 신호를 수신하여 도로면 데이터와 연동할 수 있도록 하였다. 그리고 평가 차량의 전면에 레일(rail)을 장착하여 레이저 변위 센서가 좌우로 왕복운동이 가능하도록 하였으며, 레일을 작동시킨 상태에서 도로면을 측정해 보았다. 실험 모형의 측정 곁과는 차량이 80km/h로 주행할 때 도로 표지 타이닝(tinning)의 폭 오차 3.24%, 깊이 오차 5%였다. 차량이 정지된 상태에서 레일을 작동시켜 요철을 측정하였을 경우 레일 방향에 대한 폭 오차는 0.07%였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.335-338
• /
• 2021

본 논문에서는 기존 AHDRNet에 channel attention 기법을 적용했을 때 성능에 어떠한 변화가 있는지를 평가하였다. 기존 모델의 병합 망에 존재하는 DRDB(Dilated Residual Dense Block) 사이, 그리고 DRDB 내의 확장된 합성곱 레이어 (dilated convolutional layer) 뒤에 또다른 합성곱 레이어를 추가하는 방식으로 channel attention 기법을 적용하였다. 데이터셋은 Kalantari의 데이터셋을 사용하였으며, PSNR(Peak Signal-to-Noise Ratio)로 비교해본 결과 기존의 AHDRNet의 PSNR은 42.1656이며, 제안된 모델의 PSNR은 42.8135로 더 높아진 것을 확인하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.397-399
• /
• 2022

Digit recognition is one of the applications of deep learning, which appears in many fields. CNN network enables us to recognize handwritten digits. Also, It can process various types of data. As we stack more layers in CNN network, we expect more performance improvements. In this paper, we added a convolution layer. as a result, we achieved an accuracy improvement from 76.96% to 98.87%, which is a nearly 21.81% increase.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.1
• /
• pp.19-30
• /
• 2007

Modeling 3D buildings is an essential process to revive the real world into a computer. There are two ways to create a 3D building model. The first method is to use the building layer of 1:1000 digital maps based on high density point data gained from airborne laser surveying. The second method is to use LiDAR point data with digital images achieved with LiDAR. In this research we tested one sheet area of 1:1000 digital map with both methods to process a 3D building model. We have developed a process, analyzed quantitatively and evaluated the efficiency, accuracy, and reality. The resulted differed depending on the buildings shape. The first method was effective on simple buildings, and the second method was effective on complicated buildings. Also, we evaluated the accuracy of the produced model. Comparing the 3D building based on LiDAR data and digital image with digital maps, the horizontal accuracy was within ${\pm}50cm$. From the above we derived a conclusion that 3D building modeling is more effective when it is based on LiDAR data and digital maps. Using produced 3D building modeling data, we will be utilized as digital contents in various fields like 3D GIS, U-City, telematics, navigation, virtual reality and games etc.

• Spatial Information Research
• /
• v.9 no.1
• /
• pp.1-13
• /
• 2001

Nowadays, SAR Interferometry is actively being studied as a new technique in topographic mapping using satellite imagery. It extracts height values using phase information derived by two SAR imageries covering same areas. Unlike when using SPOT imagery, it is not affected by atmospheric conditions and time. So to speak, we can say that SAR Interferometry is flexible in imagery acquisitions and can get height data economically over wide area. So, it is expected that SAR Interferometry will be widely using in GIS applications. But, in some area occurring geometric distortion, height data are misjudged or not extracted depending on phase unwrapping algorithms. IN the case of ERS tandem data, the accuracy of height data was worst in mountain area. It is the because of the short incidence angle resulted in layover effect. Of the phase unwrapping algorithms, path-following was better in height accuracy but could not get data in layover area. In this area, we could get height data using Height Sensitivity. In concludion, we could get DEM that maintained the accuracy of path-following method and have overall data across imagery.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.5
• /
• pp.430-437
• /
• 2021

In this paper, we propose a robust face recognition method against soft errors with a deep convolutional generative adversarial network(DCGAN) based compensation method by a cross-layer approach. When soft-errors occur in block data of JPEG files, these blocks can be decoded inappropriately. In previous results, these blocks have been replaced using a mean face, thereby improving recognition ratio to a certain degree. This paper uses a DCGAN-based compensation approach to extend the previous results. When soft errors are detected in an embedded system layer using parity bit checkers, they are compensated in the application layer using compensated block data by a DCGAN-based compensation method. Regarding soft errors and block data loss in facial images, a DCGAN architecture is redesigned to compensate for the block data loss. Simulation results show that the proposed method effectively compensates for performance degradation due to soft errors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.5
• /
• pp.619-627
• /
• 2021

Recent advance in low cost and light-weight drones has extended their application areas in both military and private sectors. Accordingly surveillance program against unfriendly drones has become an important issue. Drone detection and classification technique has long been emphasized in order to prevent attacks or accidents by commercial drones in urban areas. Most commercial drones have small sizes and low reflection and hence typical sensors that use acoustic, infrared, or radar signals exhibit limited performances. Recently, artificial intelligence algorithm has been actively exploited to enhance radar image identification performance. In this paper, we adopt machined learning algorithm for high resolution radar imaging in drone detection and classification applications. For this purpose, simulation is carried out against commercial drone models and compared with experimental data obtained through high resolution radar field test.