• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.32-33
• /
• 2020

쿠버네티스는 컨테이너를 사용하는 분산 클라우드에서 컨테이너화를 쉽고 빠르게 배포/확장할 수 있어 유용한 플랫폼이다. 쿠버네티스에서 다양한 애플리케이션들이 동작하며 서비스를 제공하고 있다. 서비스의 원활한 제공을 위하여 고객과 서비스수준에 대한 약속인 SLA와 SLA의 기준이 되는 SLO에 필요한 지표를 확인하는 것은 중요하다. 본 논문은 쿠버네티스 클러스터로 구성된 분산 클라우드 DECENTER를 소개하고 DECENTER에서 분산 AI 애플리케이션의 효율적인 SLO를 지원하는 모니터링 시스템을 제안한다.

• Journal of Information Processing Systems
• /
• v.7 no.2
• /
• pp.221-240
• /
• 2011

Vehicular networks are a promising application of mobile ad hoc networks. In this paper, we introduce an efficient broadcast technique, called CB-S (Cell Broadcast for Streets), for vehicular networks with occlusions such as skyscrapers. In this environment, the road network is fragmented into cells such that nodes in a cell can communicate with any node within a two cell distance. Each mobile node is equipped with a GPS (Global Positioning System) unit and a map of the cells. The cell map has information about the cells including their identifier and the coordinates of the upper-right and lower-left corner of each cell. CB-S has the following desirable property. Broadcast of a message is performed by rebroadcasting the message from every other cell in the terrain. This characteristic allows CB-S to achieve an efficient performance. Our simulation results indicate that messages always reach all nodes in the wireless network. This perfect coverage is achieved with minimal overhead. That is, CB-S uses a low number of nodes to disseminate the data packets as quickly as probabilistically possible. This efficiency gives it the advantage of low delay. To show these benefits, we give simulations results to compare CB-S with four other broadcast techniques. In practice, CB-S can be used for information dissemination, or to reduce the high cost of destination discovery in routing protocols. By also specify the radius of affected zone, CB-S is also more efficient when broadcast to a subset of the nodes is desirable.

• Journal of Broadcast Engineering
• /
• v.24 no.7
• /
• pp.1266-1275
• /
• 2019

With increasing criminal rates and number of CCTVs, much attention has been paid to intelligent surveillance system on the horizon. Object detection and tracking algorithms have been developed to reduce false alarms and accurately help security agents immediately response to undesirable changes in video clips such as crimes and accidents. Many studies have proposed a variety of algorithms to improve accuracy of detecting and tracking objects outside tunnels. The proposed methods might not work well in a tunnel because of low illuminance significantly susceptible to tail and warning lights of driving vehicles. The detection performance has rarely been tested against the tunnel environment. This study investigated a feasibility of object detection and tracking in an actual tunnel environment by utilizing YOLOv3 and Kernelized Correlation Filter. We tested 40 actual video clips to differentiate pedestrians and motorcycles to evaluate the performance of our algorithm. The experimental results showed significant difference in detection between pedestrians and motorcycles without false positive rates. Our findings are expected to provide a stepping stone of developing efficient detection algorithms suitable for tunnel environment and encouraging other researchers to glean reliable tracking data for smarter and safer City.

• Journal of Broadcast Engineering
• /
• v.17 no.6
• /
• pp.1106-1109
• /
• 2012

The stability of object tracking in non-stationary camera environment, such as intelligent surveillance system using a pan/tilt camera, is less stable compared with stationary camera environment. This is due to the fact that it is difficult to model a background image in non-stationary environment. In this letter, we propose a non-stationay pan/tilt camera surveillance system which uses a stop/go procedure together with a real-time active contour. The proposed system can track the object stable even in an environment where only a few difference frames can be obtained.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.390-395
• /
• 2009

The robustness of audio fingerprinting system in a noisy environment is a principal challenge in the area of content-based audio retrieval. The selected feature for the audio fingerprints must be robust in a noisy environment and the computational complexity of the searching algorithm must be low enough to be executed in real-time. The audio fingerprint proposed by Philips uses expanded hash table lookup to compensate errors introduced by noise. The expanded hash table lookup increases the searching complexity by a factor of 33 times the degree of expansion defined by the hamming distance. We propose a new method to improve noise robustness of audio fingerprinting in noise environment using predominant pitch which reduces the bit error of created hash values. The sub-fingerprint of our approach method is computed in each time frames of audio. The time frame is transformed into the frequency domain using FFT. The obtained audio spectrum is divided into 33 critical bands. Finally, the 32-bit hash value is computed by difference of each bands of energy. And only store bits near predominant pitch. Predominant pitches are extracted in each time frames of audio. The extraction process consists of harmonic enhancement, harmonic summation and selecting a band among critical bands.

• Journal of Broadcast Engineering
• /
• v.18 no.2
• /
• pp.237-248
• /
• 2013

Hybrid broadcasting environment is convergence of broadcasting and communication environment. In hybrid broadcasting environment, a number of media can be delivered using both broadcasting channel and other network unlike traditional broadcast environment that is able to deliver a couple of media by the limited bandwidth. Now, starting with smart TV, hybrid broadcasting environment combining broadcasting channel and IP network is established, and a variety of services are appearing. Moreover, the services using hybrid broadcasting environment are expected to appear soon for the other smart terminals such as smart phone and tablet PC. Scene composition is one of the methods that can consume effectively a number of media delivered from hybrid broadcasting environment. Using scene composition, multiple media can be consumed through the specified presentation time and space. Therefore, in this paper, it proposes the scene composition technology that is suitable for hybrid broadcasting environment and smart terminals. However, the spatial composition and temporal composition of media using script language and style language of HTML5 might increase the complexity of processing, and cause limitation of avaliable terminals. Also, a document of HTML5 can describe only one scene. By these reason, the proposed scene composition technology extends HTML5 in order to provide the spatial and temporal composition of media and description of multiple scene through markup language. In addition, it includes the extension of HTML5 in terms of utilization in hybrid broadcasting environment. For this proposal, this paper describes the technology of HTML5 and proposed scene composition. Also, it verifies the scene composition with both implementations and experiments.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1999.11b
• /
• pp.249-254
• /
• 1999

In this paper we analyze the bit error rate of an in-band DAB(Digital Audio Broadcasting) system which is based upon orthogonal frequency division multiplexing(OFDM) and uses M-PSK and M-QAM modulation schemes in the interference environment of an analog FM signal. Results are derived which take into account the influence of the frequency non- selective Rician fading channel, but they are valid for Rayleigh fading channel and AWGN channel as well. Theoretical bit error rates and simulation results are given for system parameters for DAB proposed by ETRI(Electronics and Telecommunications Research Institute).

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06d
• /
• pp.291-296
• /
• 2008

Wireless network technologies are becoming more widely used in industrial environment. The industrial communication system requires a real-time delivery of messages. The sensors periodically senses the physical environment and wants to deliver the data in real-time to the sink. This paper proposes a real-time protocol for periodic messages on wireless sensor and actor networks to be used in industrial communications. The proposed protocol delivers the data message using the shortest path from the source and the nearest actor. The protocol considers the energy consumption by reducing the number of broadcast messages during flooding. We have evaluated the performance of the proposed protocol using QualNet simulator. The simulation results show that the data messages have been delivered in real-time and the number of broadcast messages is reduced from 90% to 35% compared the existing protocols.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.525-528
• /
• 2009

Recently, image classification has been an important task in various fields. Generally, the performance of image classification is not good without the adjustment of image features. Therefore, it is desired that the way of automatic feature extraction. In this paper, we propose an image classification method which adjusts image features automatically. We assume that texture features are useful in image classification tasks because natural images are composed of several types of texture. Thus, the classification accuracy rate is improved by using distribution of texture features. We obtain texture features by calculating image features from a current considering pixel and its neighborhood pixels. And we calculate image features from distribution of textures feature. Those image features are adjusted to image classification tasks using Genetic Algorithm. We apply proposed method to classifying images into "head" or "non-head" and "male" or "female".

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2004.11a
• /
• pp.27-30
• /
• 2004

본 논문에서는 사용자의 다양한 이질적인 사용 환경(단말기기, 네트웨크 품질 등)에 최적화된 멀티미디어 컨텐츠를 제공하는 시스템에 대해 제안한다. 제안된 시스템은 MPEG-21 멀티미디어 프레임워크를 기반으로 한다. 시스템은 클라이언트, 미디어 서버, 적응 변환 서버, 그리고 툴 서버로 구성된다. 또한 제안된 시스템은 사용자의 사용 환경 정보를 분석하고, 생성하는 사용 환경 정보에이전트 모듈과, 이를 받아 분석하는 정책 결정 엔진 모듈, 그리고 이를 제어하고 관리하는 제어모듈도 제공된다. 구성된 시스템에 대해 MPEG-2 교육 방송 컨텐츠에 대해 다양한 사용환경에 대해 적용하여 제안된 MPEGB-21 기반 서비스 시스템이 유효함을 확인하였다.