• 한국인터넷방송통신학회논문지
• /
• 제16권3호
• /
• pp.115-122
• /
• 2016

본 논문은 차량의 내부 및 외부 정보를 통합하여 운전자의 인지 상태를 측정하고, 안전운전을 보조하여 주는시스템을 제안한다. 구현된 시스템은 운전자의 시선 정보와 외부 영상을 분석하여 얻은 주변정보를 mutual information기반으로 통합하여 구현되며, 차량의 앞부분과 내부 운전자를 검출하는 2개의 카메라를 이용한다. 외부 카메라에서 정보를 얻기 위해 선택적 집중모델을 기반으로 하는 게슈탈트법칙을 제안하고, 이를 기반으로 구현된 saliency map (SM) 모델은 신호등과 같은 중요한 외부 자극을 두드러지게 표현한다. 내부 카메라에서는 얼굴의 특징정보를 이용하여 운전자의 주의가 집중되는 외부 응시 정보를 파악하고 이를 통해 운전자가 응시하고 있는 영역을 검출한다. 이를 위해서 우리는 실시간으로 운전자의 얼굴특징을 검출하는 알고리즘을 사용한다. 운전자의 얼굴을 검출하기 위하여 modified census transform (MCT) 기반의 Adaboost 알고리즘을 사용하였으며, POSIT (POS with ITerations)알고리즘을 통해 3차원 공간에서 머리의 방향과 운전자 응시 정보를 측정하였다. 실험결과를 통하여 제안한 시스템이 실시간으로 운전자의 응시하고 있는 영역과, 신호등과 같은 운전에 도움이 되는 정보를 파악하는데 도움이 되었음을 확인할 수 있으며, 이러한 시스템이 운전보조 시스템에 효과적으로 적용될 것으로 판단된다.

• 한국인터넷방송통신학회논문지
• /
• 제23권3호
• /
• pp.119-125
• /
• 2023

IT 인프라 운영이 고도화하면서 시스템을 관리하는 방식이 널리 보급되어 있으며, 최근에는 Syslog를 활용한 개선방법들이 연구되고 있다. 그러나 이러한 방법으로 수집한 로그 데이터를 활용하여 시스템 관제를 할 경우 다양한 형식으로 추출되는 로그를 전문 인력이 분석해야 하는 어려움이 있다. 본 논문은 엣지 컴퓨팅을 활용하여 Syslog 데이터를 분산 수집하고 중복 데이터를 전처리하여 중앙 데이터베이스에 적재하는 시스템을 구축 방법을 제시하고자 한다. 또한, 데이터사전을 구성하여 실시간으로 데이터를 분류하고 카운팅하는 기능을 제공하며, 데이터사전에 등록된 데이터에 대해서는 중앙 데이터베이스로의 전송을 제한하는 시스템을 구현한다. 이를 통해 데이터 사전의 정의어 패턴을 유지하며, 중복 데이터와 시간 중복을 제어하여 중앙 데이터베이스에 정제된 데이터를 적재함으로써 빅데이터 분석을 위한 기초 자료를 확보할 수 있다. 시뮬레이션결과 제안된 알고리즘과 프로시저를 구체적인 예시와 함께 설명하고, syslog 데이터를 활용하여 그 성능을 검증하였다. syslog 데이터는 실제 로그 데이터에서 추출한 예시를 포함하고 있으며 이를 통해 로그 데이터로부터 필요한 정보를 정확하게 추출하였고, 분류 및 적재 과정에서 정상적인 처리가 이루어지는지를 확인하였다. 이러한 시스템은 엣지 환경에서 로그 데이터를 효율적으로 수집하고 관리하기 위한 솔루션으로 활용하여 기술의 확산 측면에서도 효과를 기대할 수 있다.

• 한국인터넷방송통신학회논문지
• /
• 제24권3호
• /
• pp.77-85
• /
• 2024

본 논문에서는 열화상 카메라, 스피드돔 카메라, PTZ 카메라, 레이더, 라이다 센서와 스마트폰을 통합한 순찰 로봇을 설계하고 구현하였다. 이 로봇은 복잡한 환경에서도 효율적으로 감시하고 대응할 수 있는 능력을 갖추고 있으며, 특히 야간이나 가시성이 낮은 조건에서도 높은 성능을 발휘할 수 있도록 설계되었다. 로봇의 이동성을 위해 궤도 이동체계를 선택하였고, 실시간 데이터 처리와 의사결정을 위해 스마트폰 기반의 제어 시스템을 개발하였다. 다양한 센서의 조합은 로봇이 환경을 포괄적으로 인식하고 위험 요소를 신속하게 감지할 수 있게 해준다. 열화상 카메라는 야간 감시에, 스피드돔과 PTZ 카메라는 광범위한 영역 모니터링에, 레이더와 라이다는 장애물 탐지와 회피에 활용된다. 스마트폰 기반 제어 시스템은 사용자 친화적인 인터페이스를 제공한다. 제안된 로봇 시스템은 보안, 감시, 재난 대응 등 다양한 분야에서 활용 가능하다. 향후 연구에서는 로봇의 자율 순찰 알고리즘 개선, 다중 로봇 협업 시스템 개발, 실제 환경에서의 장기 테스트 등이 수행되어야 할 것이다. 본 연구는 지능형 감시 로봇 분야의 발전에 기여할 것으로 기대된다.

• International journal of advanced smart convergence
• /
• 제4권1호
• /
• pp.18-30
• /
• 2015

As the speed of networks that subscribers can use has greatly increased, demand for high-quality broadcast content, such as from Internet Protocol Television (IPTV) and Video on Demand (VoD), is likewise increasing. Therefore, while broadcasters are increasing content and channels, they are striving to improve consumer quality of experience (QoE) to differentiate themselves from competitors, including by producing higher physical-quality content. Recently, subjective measurement methods have been internationally standardized as the most reliable approach for measuring and evaluating IPTV QoE. However, a majority of these methods are performed in experimental environments and are based on the extremely brief viewing period of approximately ten seconds using original reference videos. It is actually difficult to apply standard evaluation methods based on a ten-second viewing interval to assess real broadcast watching of IPTV or other services that involve a longer time (i.e., more than thirty minutes). In this paper, we therefore propose a method that accommodates actual viewing environments. Using the mean opinion score, we experimentally analyze the effects of evaluation interval changes under actual conditions in which IPTV service is provided. In addition, we propose improvements by applying the results into actual live broadcast IPTV service and by analyzing consumer service QoE.

• ETRI Journal
• /
• 제35권1호
• /
• pp.69-79
• /
• 2013

For real-time interactive multimedia operations, such as video uploading, video play, fast-forward, and fast-rewind, solid state disk (SSD)-based storage systems for video streaming servers are becoming more important. Random access rates in storage systems increase significantly with the number of users; it is thus difficult to simultaneously serve many users with HDD-based storage systems, which have low random access performance. Because there is no mechanical operation in NAND flash-based SSDs, they outperform HDDs in terms of flexible random access operation. In addition, due to the multichannel architecture of SSDs, they perform similarly to HDDs in terms of sequential access. In this paper, we propose a new SSD-based storage system for interactive media servers. Based on the proposed method, it is possible to maximize the channel utilization of the SSD's multichannel architecture. Accordingly, we can improve the performance of SSD-based storage systems for interactive media operations.

• International journal of advanced smart convergence
• /
• 제6권2호
• /
• pp.51-58
• /
• 2017

Recently, rapid advances of Ethernet and IP technology have brought many changes in the sound industry. In addition, due to AoIP-based audio transmission technology, various problems of the acoustic system (sound quality deterioration due to long distance transmission, complicated wiring) have improved dramatically. However, when many distributed audio systems are connected with AoIP equipment, if there is a problem in the equipment, it is impossible to operate the connected system. AoIP equipment only can transmit audio signals but cannot adjust the system for acoustic environment. In this paper, AoIP equipment is to be installed with sound equipment on a one-to-one basis, so that various existing problems can be solved and adjustment of sound quality (reverberation, echo, delay and EQ) can be possible by AoIP-based OAC (On-site Audio Center) with built-in DSP function. As a result, uncompressed real-time transmission by distributed transmission/receipt module in OAC (On-site Audio Center) and high quality sound by adjustment of sound quality with built-in DSP can be acquired. It is expected that OAC based sound system will be the industry standard in ubiquitous environment.

• International journal of advanced smart convergence
• /
• 제8권4호
• /
• pp.40-46
• /
• 2019

The current education is becoming more extensive with the application of various teaching methods. This is a problem that is so distributed that it is difficult for users to find the data and it takes a long time to find the information they need. Currently, various educational services, materials, and instruments are developed and scattered. Therefore, it is important to raise students' awareness of aptitude and career path with customized education tailored to students. Conventional education platforms have very difficult to choose the right materials for students because of the spread of educational programs and institution materials. To solve this, we propose a customized recommendation approach to recommend customized educational service materials and institution for students to teachers, which helps teachers conveniently choose materials suitable for their respective environments. On this new platform, the CNN algorithm provides recommended content for classes and students. For real service on the educational service platform, we implement this system for Jeil edus business. Through this mechanism, we expect to improve the quality of education by helping to select the right service.

• International journal of advanced smart convergence
• /
• 제8권4호
• /
• pp.104-112
• /
• 2019

This study proposed a robust detection algorithm. It detects face more stably with respect to changes in light and rotation forthe identification of a face shape. The proposed algorithm uses face shape asinput information in a single camera environment and divides only face area through preprocessing process. However, it is not easy to accurately recognize the face area that is sensitive to lighting changes and has a large degree of freedom, and the error range is large. In this paper, we separated the background and face area using the brightness difference of the two images to increase the recognition rate. The brightness difference between the two images means the difference between the images taken under the bright light and the images taken under the dark light. After separating only the face region, the face shape is recognized by using the self-organization feature map (SOFM) algorithm. SOFM first selects the first top neuron through the learning process. Second, the highest neuron is renewed by competing again between the highest neuron and neighboring neurons through the competition process. Third, the final top neuron is selected by repeating the learning process and the competition process. In addition, the competition will go through a three-step learning process to ensure that the top neurons are updated well among neurons. By using these SOFM neural network algorithms, we intend to implement a stable and robust real-time face shape recognition system in face shape recognition.

• International journal of advanced smart convergence
• /
• 제8권4호
• /
• pp.16-25
• /
• 2019

The Internet of things (IOT) is remodeling the agribusiness empowering the agriculturists through the extensive range of strategies, for example, accuracy as well as practical farming to deal with challenges in the field. The paper aims making use of evolving technology i.e. IoT and smart agriculture using automation. The objective of this research paper to present tools and best practices for understanding the role of information and communication technologies in agriculture sector, motivate and make the illiterate farmers to understand the best insights given by the big data analytics using machine learning. The methodology used in this system can monitor the humidity, moisture level and can even detect motions. According to the data received from all the sensors the water pump, cutter and sprayer get automatically activated or deactivated. we investigate a remote monitoring system using Wi-Fi. These nodes send data wirelessly to a central server, which collects the data, stores it and will allow it to be analyzed then displayed as needed and can also be sent to the client mobile.

• ETRI Journal
• /
• 제36권2호
• /
• pp.253-263
• /
• 2014

In the near future, traditional narrow and fixed viewpoint video services will be replaced by high-quality panorama video services. This paper proposes a visual-attention-aware progressive region of interest (RoI) trick mode streaming service (VA-PRTS) that prioritizes video data to transmit according to the visual attention and transmits prioritized video data progressively. VA-PRTS enables the receiver to speed up the time to display without degrading the perceptual quality. For the proposed VA-PRTS, this paper defines a cutoff visual attention metric algorithm to determine the quality of the encoded video slice based on the capability of visual attention and the progressive streaming method based on the priority of RoI video data. Compared to conventional methods, VA-PRTS increases the bitrate saving by over 57% and decreases the interactive delay by over 66%, while maintaining a level of perceptual video quality. The experiment results show that the proposed VA-PRTS improves the quality of the viewer experience for interactive panoramic video streaming services. The development results show that the VA-PRTS has highly practical real-field feasibility.