• Journal of the Korean Society of Industry Convergence
• /
• v.7 no.2
• /
• pp.167-172
• /
• 2004

Neural networks are used in the framework of sensor based tracking control of robot manipulators. They learn by practice movements the relationship between PSD(an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. Furthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple back propagation networks one of which is selected according to which division (Corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.11a
• /
• pp.236-239
• /
• 2014

3차원 영상을 제작하기 위해서는 여러 시점의 색상 영상과 함께 깊이 정보를 필요로 한다. 하지만 깊이 정보를 얻을 때 사용하는 ToF 카메라는 해상도가 낮으며 적외선 신호의 주파수 문제 때문에 최대 3대까지 사용할 수 있다. 따라서 깊이 정보를 색상 영상과 함께 사용하기 위해서 깊이 정보의 업샘플링이 필수적이다. 업샘플링은 깊이 정보를 색상 카메라 위치로 3차원 워핑하고 결합형 양방향 필터(joint bilateral filter, JBF)를 사용하여 빈 영역을 채우는 방법으로 진행된다. 업샘플링은 오랜 시간이 소요되지만 그래픽스 프로세싱 유닛(graphics processing units, GPU)를 이용하여 빠르게 수행될 수 있다. 본 논문에서는 다중 GPU의 병렬 수행을 통하여 빠르게 다시점 깊이맵을 생성할 수 있는 방법을 제안한다. 다중 GPU 병렬 수행은 범용 목적 GPU(general purpose computing on GPU, GPGPU) 중의 하나인 CUDA를 이용하였으며, 본 논문에서 제안된 방법을 이용하여 3개의 GPU 사용한 실험 결과 초당 35 프레임의 다시점 깊이맵을 생성했다.

• ETRI Journal
• /
• v.41 no.2
• /
• pp.207-223
• /
• 2019

Network function virtualization can significantly improve the flexibility and effectiveness of network appliances via a mapping process called service function chaining. However, the failure of any single virtualized network function causes the breakdown of the entire chain, which results in resource wastage, delays, and significant data loss. Redundancy can be used to protect network appliances; however, when failures occur, it may significantly degrade network efficiency. In addition, it is difficult to efficiently map the primary and backups to optimize the management cost and service reliability without violating the capacity, delay, and reliability constraints, which is referred to as the reliability-aware service chaining mapping problem. In this paper, a mixed integer linear programming formulation is provided to address this problem along with a novel online algorithm that adopts the joint protection redundancy model and novel backup selection scheme. The results show that the proposed algorithm can significantly improve the request acceptance ratio and reduce the consumption of physical resources compared to existing backup algorithms.

• Journal of Broadcast Engineering
• /
• v.21 no.6
• /
• pp.957-964
• /
• 2016

Acquisition of reliable depth maps is a critical requirement in many applications such as 3D videos and free-viewpoint TV. Depth information can be obtained from the object directly using physical sensors, such as infrared ray (IR) sensors. Recently, Time-of-Flight (ToF) range camera including KINECT depth camera became popular alternatives for dense depth sensing. Although ToF cameras can capture depth information for object in real time, but are noisy and subject to low resolutions. Recently, filter-based depth up-sampling algorithms such as joint bilateral upsampling (JBU) and noise-aware filter for depth up-sampling (NAFDU) have been proposed to get high quality depth information. However, these methods often lead to texture copying in the upsampled depth map. To overcome this limitation, we formulate a convex optimization problem using higher order regularization for depth map upsampling. We decrease the texture copying problem of the upsampled depth map by using edge weighting term that chosen by the edge information. Experimental results have shown that our scheme produced more reliable depth maps compared with previous methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.2
• /
• pp.438-446
• /
• 2013

Generally, a camera isn't located at the center of display in a tele-presence system and it causes an incorrect eye contact between speakers which reduce the realistic feeling during the conversation. To solve this incorrect eye contact problem, we newly propose an intermediate view reconstruction algorithm using both a color camera and a depth camera and applying for the depth image based rendering (DIBR) algorithm. In the proposed algorithm, an efficient hole filling method using the arithmetic mean value of neighbor pixels and an efficient boundary noise removal method by expanding the edge region of depth image are included. We show that the generated eye-contacted image has good quality through experiments.

• Convergence Security Journal
• /
• v.6 no.4
• /
• pp.113-120
• /
• 2006

C4I system is the centerpiece of the military force. The system is an information based system which facilitates information grid, collection of data and dissemination of the information. The C4I system seeks to assure information dominance by linking warfighting elements in the battlespace to information network which enables sharing of battlespace information and awareness; thereby shifting concept of warfare from platform-centric paradigm to Network Centric Warfare. Although, it is evident that C4I system is a constant target from the adversaries, the issues of vulnerability via cyberspace from attack still remains. Therefore, the protection of C4I system is critical. The roadmap I have constructed in this paper will guide through the direction to protect the system during peace and war time. Moreover, it will propose vision, objectives and necessary supporting framework to secure the system from the threat. In order to fulfill these tasks, enhanced investments and plans from the Joint chief of Staff and Defense of Acquisition and Program Administration (DAPA) is critical; thereby enabling the establishment of rapid and efficient security system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.4C
• /
• pp.277-282
• /
• 2012

In this paper, we present a real-time eye contact system for realistic telepresence using a Kinect depth camera. In order to generate the eye contact image, we capture a pair of color and depth video. Then, the foreground single user is separated from the background. Since the raw depth data includes several types of noises, we perform a joint bilateral filtering method. We apply the discontinuity-adaptive depth filter to the filtered depth map to reduce the disocclusion area. From the color image and the preprocessed depth map, we construct a user mesh model at the virtual viewpoint. The entire system is implemented through GPU-based parallel programming for real-time processing. Experimental results have shown that the proposed eye contact system is efficient in realizing eye contact, providing the realistic telepresence.

• The Journal of Advanced Prosthodontics
• /
• v.7 no.6
• /
• pp.460-467
• /
• 2015

PURPOSE. The aim of this study is to evaluate the appropriate impression technique by analyzing the superimposition of 3D digital model for evaluating accuracy of conventional impression technique and digital impression. MATERIALS AND METHODS. Twenty-four patients who had no periodontitis or temporomandibular joint disease were selected for analysis. As a reference model, digital impressions with a digital impression system were performed. As a test models, for conventional impression dual-arch and full-arch, impression techniques utilizing addition type polyvinylsiloxane for fabrication of cast were applied. 3D laser scanner is used for scanning the cast. Each 3 pairs for 25 STL datasets were imported into the inspection software. The three-dimensional differences were illustrated in a color-coded map. For three-dimensional quantitative analysis, 4 specified contact locations(buccal and lingual cusps of second premolar and molar) were established. For two-dimensional quantitative analysis, the sectioning from buccal cusp to lingual cusp of second premolar and molar were acquired depending on the tooth axis. RESULTS. In color-coded map, the biggest difference between intraoral scanning and dual-arch impression was seen (P<.05). In three-dimensional analysis, the biggest difference was seen between intraoral scanning and dual-arch impression and the smallest difference was seen between dual-arch and full-arch impression. CONCLUSION. The two- and three-dimensional deviations between intraoral scanner and dual-arch impression was bigger than full-arch and dual-arch impression (P<.05). The second premolar showed significantly bigger three-dimensional deviations than the second molar in the three-dimensional deviations (P>.05).

• Journal of the Korean Society of Safety
• /
• v.34 no.4
• /
• pp.111-118
• /
• 2019

Accidents occurring due to natural disasters in chemical process facilities where technologies are concentrated can cause secondary damage. The concept of the relationship between natural disasters and highly intensive technologies has evolved into the Natech (Natural Hazards Triggered Technological Disaster) research. Currently, the number of earthquakes is increasing all over the Korean peninsula. To assess the risk of Natech when an earthquake has occurred in South Korea, the Rapid Natech Risk Assessment Tool (RAPID-N) developed by the European Commission's Joint Research Center (EC JRC) was used in the present study. The RAPID-N can be used for Natech risk assessment based on mapping and can be utilized for sufficient preparation for reduction of the effects of Natech accidents. A total of 261 chemical facilities actually existing in Pohang were initially analyzed to select eight facilities and the Pohang earthquake that occurred in 2017 was implemented in the RAPID-N utilizing the shake map. High risk areas were selected through Natech risk assessments for the selected eight work places and countermeasures for the areas were suggested. High risk areas exist depending on the location, since the damage influence ranges could be overlapped and each chemical facility has an independent probability of Natech. Therefore, studies on Natech emergency plans and emergency evacuation routes should be actively conducted considering such high risk areas. The present study was conducted to demonstrate the feasibility of Natech risk assessment in South Korea through the RAPID-N. These findings can be used as a reference material to lay a foundation for Natech risk assessment and related policies in South Korea.

• Journal of muscle and joint health
• /
• v.6 no.1
• /
• pp.51-72
• /
• 1999

The purpose of this study is to compar self-reported fatigue and fatigue-regulating behaviors of rheumatoid arthritic patients and normal persons. This study collected the data from 75 rheumatoid arthritic patents visited the departments of internal medicine or orthopedics of four general hospitals T-city and K-city by means of direct interview and questionnaires. in this study also collected data from 75 normal persons who had not been exposed to any other disease in T-city and K-city by means of direct interviews anti questionnaires which were conducted by two trained nurses. This experiment was conducted from August 1, 1998 to October 15, 1998. This study used both MAP(Multi-Dimentional Assessment of Fatigue) developed by Belza(1995) to measure fatigue and the measurement developed by Kwon, Young-Eun to investigate fatigue regulating behaviors. The collected materials were analyzed by means of descriptive statistics, t-test, and the ANCOVA according to the SPSS PC+ program. The findings are as follows : 1. There was the statistically significant difference(t =5.07, p=.000), between rheumatoid arthritic patients(32.76 points) and normal persons(25.81 points) in t-test comparison by group about fatigue. A fatigue degree of rheumatoid arthritic patient group was high in five kinds of lower realms such as common fatigue degree, fatigue severity to be experienced, distress due to fatigue, daily fatigue degree, and fatigue timing at the last week by dimension. 2. There was the significant difference in the number of fatigue-regulating behaviors between rheumatoid of fatigue arthritic patients(9.37 times) and normal persons (8.15 times), but there wasn't any significant difference in the efficiency between rheumatoid arthritic patients(2.85 points) and normal persons (2.78 points) This research suggests two kinds of things as follows : 1. It is necessary to develop an educational program for improving efficiency of fatigue-regulating behaviors as well as some nursing arbitration measures for reducing fatigue of rheumatoid arthritic patients. 2. It is necessary for the future studies to continuously grasp characteristics of fatigue by gender variable by selecting more rheumatoid arthritic male patients.