• Journal of the Korea Society of Computer and Information
• /
• v.24 no.8
• /
• pp.95-103
• /
• 2019

According to the Statistics Korea in 2017, the 10 leading causes of death contain a cardiac disorder disease, self-injury. In terms of these diseases, urgent assistance is highly required when people do not move for certain period of time. We propose an unusual event detection algorithm to identify abnormal user behaviors using dust, vision and activity sensors in their houses. Vision sensors can detect personalized activity behaviors within the CCTV range in the house in their lives. The pattern algorithm using the dust sensors classifies user movements or dust-generated daily behaviors in indoor areas. The accelerometer sensor in the smartphone is suitable to identify activity behaviors of the mobile users. We evaluated the proposed pattern algorithms and the fusion method in the scenarios.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1547-1550
• /
• 2013

현재 우리나라에서 사용되는 대부분의 교통신호 체계는 교통량의 변화와 상관없이 규칙적인 신호주기를 반복하는 방식으로 교통 패턴이 안정되어 변동량이 적은 경우에는 적합하나, 현장교통상황에 능동적으로 조정되지 못하고, 소방차나 구급차와 같이 긴급을 요하는 차량에 대한 대처가 힘들다는 단점이 존재한다. 따라서 유기적인 현장교통상황에 능동적으로 대처하고, 긴급차량에 대한 합리적인 대처 방법이 필요하다. 따라서, 본 논문에서는 이와 같은 문제점을 해결하고자 기 설치된 신호 후방 CCTV를 이용하여 지능적으로 신호체계를 제어하고, 긴급차량에 대해 신호우선권을 부여함으로써, 위급상황에 유기적으로 대처할 수 있는 지능형 교통신호 제어 시스템을 설계하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1554-1557
• /
• 2013

기존 아날로그 방식의 CCTV는 화질이 좋지 않고, 장시간 사용할 경우 화질이 나빠지는 문제가 발생한다. 이와 같은 문제를 해결하기 위해 아날로그 신호출력을 디지털 방식으로 변환하는 DVR과 IP 네트워크로부터 디지털 신호를 받아 처리하는 NVR이 등장하게 되었다. 이와 같은 영상 보안 이슈가 등장함에도 불구하고 보안 산업 보수성과 새로운 기술을 받아들이는데 있어서의 제약사항 등의 이유로 IP-Suveillance에 대한 이해가 부족한 실정이다. 따라서 본 논문에서는 영상보안 시스템의 동향과 분석을 위해 DVR과 NVR을 투자측면, 비용측면, 유지측면에서 비교 분석하였다.

• Journal of Convergence Society for SMB
• /
• v.5 no.3
• /
• pp.9-13
• /
• 2015

With the advance of ICT, the necessity of user authentication to verify the identity of an opponent online not face to face is increasing. The authentication, the basis of the security, is used in various fields. Because ID-based authentication has weaknesses in terms of stability and losses, two or more than two authentication tools are used in the place in which the security is important. Recently, biometric authentication rather than ID, OTP, SMS authentication has been an issue in terms of credibility and efficiency. As the fields applied to current biometric recognition technologies are increasing, the application of the biometric recognition is being used in various fields such as mobile payment system, intelligent CCTV, immigration inspection, and access control. As the biometric recognition, finger print, iris, retina, vein, and face recognition have been studied actively. This study is to inspect the current state of domestic and foreign standardization including understanding of the face recognition and the trend of technology.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.169-171
• /
• 2021

Image processing through cameras such as self-driving, CCTV, mobile phone security, and parking facilities is being used to solve many real-life problems. Simple classification is solved through image processing, but it is difficult to find images or in-image features of complexly mixed objects. To solve this feature point, we utilize deep learning techniques in classification, detection, and segmentation of image data so that we can think and judge closely. Of course, the results are better than just image processing, but we confirm that the results judged by the method of image segmentation using deep learning have deviations from the real object. In this paper, we study how to perform accuracy improvement through simple image processing just before outputting the output of deep learning image segmentation to increase the precision of image segmentation.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.3
• /
• pp.38-50
• /
• 2023

Recent advances in artificial intelligence (AI) technology have enabled the integration of AI technology into image sensors, such as Closed-Circuit Television (CCTV), to detect specific traffic incidents. However, most incident detection methods have been carried out using fixed equipment. Therefore, there have been limitations to incident detection for all roadways. Nevertheless, the development of mobile image collection and analysis technology, such as image sensors and edge-computing, is spreading. The purpose of this study is to estimate the reducing effect of the incident detection time according to the introduction level of mobile image collection and analysis equipment (or connected vehicles). To carry out this purpose, we utilized data on the number of incidents collected by the Suwon branch of the Gyeongbu expressway in 2021. The analysis results showed that if the market penetration rate (MPR) of connected vehicles is 4% or higher for two-lane expressway and 3% or higher for three-lane expressways, the incident detection time was less than one minute. Furthermore, if the MPR is 0.4% or higher for two-lane expressways and 0.2% or higher for three-lane expressways, the incident detection time decreased compared to the average incident detection time announced by the Korea Expressway Corporation for both two-lane and three-lane expressways.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.316-319
• /
• 2008

Most of campus vehicle management systems, so far, have simple functions such as managing vehicle in/out or issuing parking tickets. Recently some of them use RFID tags to count total numbers of cars in the campus, excluding exact parking position management. In this paper we propose a new campus vehicle management system using wireless sensor network location management scheme. This system adopts RSSI based location management method with some performance improvement technique. According to the experimental result, this proposed scheme can be used to implement an effective campus vehicle management system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11b
• /
• pp.995-998
• /
• 2003

인터넷 정보가전 제품의 보급과 편리한 서비스를 요구하는 사용자의 욕구증대로 인하여 홈 오토메이션이라는 기술이 대두 되었다. 초기의 홈 오토메이션은 셋톱박스, CCTV와 같은 장비들이 요구 되어 가정, 사무실과 같은 소규모 공간에서의 도입이 어렵다. 이러한 문제점을 해결하기 위해 언제 어디서나 영상 감시와 제어를 할 수 있고 별도의 장비 없이 소규모 공간에서도 손쉽게 적용 시킬 수 있는 홈 오토메이션 시스템이 요구된다. 홈 오토메이션 시스템의 구현을 위해서는 기반기술인 영상 감시와 제어기술이 구현되어야한다. 본 논문에서는 홈 오토메이션의 기반 기술인 영상 감시기술 구현을 위해 원격 영상 감시 시스템을 설계 및 구현 하였다. 원격 영상 감시 시스템은 클라이언트에서 선택한 웹카메라의 동화상 캡쳐시 버퍼링을 중지함으로써 영상지연을 최소화하였으며, 카메라 선택 모듈의 사용으로 모든 영상이 아닌 선택된 영상만을 전송함으로써 자원 소모를 줄였다. 이러한 원격 영상 감시 시스템은 전력 감시 시스템, 분산 제어 시스템 등의 산업분야 뿐만 아니라 교육 분야 등 여러 분야에서 사용될 수 있다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.4
• /
• pp.999-1004
• /
• 2010

Most of campus vehicle management systems, so far, simply manages coming in or go out of vehicles, issuing a parking tickets. Recently some of them use RFID tags to count total numbers of cars in the campus, excluding exact parking position management. In this paper we propose a new campus vehicle management system using wireless sensor network location management scheme. This system adopts RSSI based location management method with some performance improvement technique. According to the experimental result, this proposed scheme can be used to implement an effective campus vehicle management system.

• The Journal of the Korea Contents Association
• /
• v.12 no.5
• /
• pp.103-112
• /
• 2012

This paper is based on the perspective that the YTN Science, a science channel in Korea which plays a key role in the popularization of science, is suffering from low viewing ratings, insufficient content, and shortage of production. First, this study employs an exploratory method to identify current status of programming and operation of the Korean science channel along with its promotional strategy. Second, it aims to conduct an analysis on the science channels, specifically some major programs, of other nations including the U.S. (Discovery Channel, National Geographic Channel), United Kingdom (BBC Knowledge), Japan (Science Channel), and China (CCTV 10), seeking the possibility to apply and combine them afterward to the Korean TV channels specialized in science. A number of implications are derived from our diagnosis of present situation and analysis of abroad cases, and this helps us suggest the content development and promotional strategies as follows: First, due to the rising need for change in the programming strategy to enhance the value of the content, it is required to rearrange the programming in terms of the target audience and the viewer lifestyle, adopt a new strategy for building up the viewers' watching habit through 'stripping', and place strategic programs in prime-time. Second, as for the specific schemes of content production and application, it is recommended to establish a dual strategy in creating the content (one for conveying knowledge, the other for delivering fun), plan and use a representative character of the program, select scientific and technological topics with more Korean backgrounds, attempt strategic ties with SNS, deepen and diversify the material for programs, and implement a strategy to boost the OSMU. Finally, with regard to the promotional strategy, a constructive proposal may include raising channel awareness through science-related events and live broadcasting, performing promotional strategies by way of expanding to printed media like magazine and book publications, and intensifying online and mobile promotional strategy.