• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2018.11a
• /
• pp.27-29
• /
• 2018

ISM Code, CSM 따라 절차 및 문서를 표준화하고 자동화하여 멀티미디어 콘텐츠로 시각화하여 모바일 및 PC등 디지털 디바이스로 제공하고 알림을 통해 선원들에게 좀 더 절차가 단순화되고 편리한 문서 자동화 시스템을 개발 알림을 통해 선원들에게 좀 더 절차가 단순화되고 편리한 문서 자동화 시스템을 개발하고 있으며, 전자해도 기반의 좀 더 정확학고 실용적인 안전관리 방법을 연구.

• Proceedings of the Korean Institute of Industrial Safety Conference
• /
• 2001.11a
• /
• pp.94-98
• /
• 2001

최근 급속한 사무자동화와 함께 컴퓨터의 사용이 보편화되어 가고 있다. 또한, PC보급이 급격하게 증가함에 따라 직장에서뿐만 아니라 가정에서도 누구나 쉽게 컴퓨터 작업을 할 수 있게 되었다. 이에 따라 컴퓨터 등 VDT(Visual Display Terminal)를 장시간 들여다보며 작업을 하는 경우가 늘어나게 되고, VDT작업으로 인한 피로, 시각장애, 경견완장애(목, 어깨 및 손목질환), 요통 등과 같은 새로운 재해를 유발할 가능성이 높아지게 되었다.(중략)

• 방재와보험
• /
• s.135
• /
• pp.29-31
• /
• 2010

소방은 화재진압에서 시작되었다는 것에서 자긍심을 가져야 하지만, 국민에게 오래된 전통에 의해 평가를 받기보다는 국민의 안전을 위한 새로운 시각에서 재조명되어야 한다. 같은 소방업무 중에도 재난관리 단계별로 어느 부분을 더 중요하게 생각하는지 해석이 다를 수 있다, 최근 '예방' 업무의 중요성이 부각되고 있으나 '예방' 단계에서의 소방의 역할에 대해 다시 고민해 보아야 한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.8
• /
• pp.393-400
• /
• 2016

Recently, there have been various researches on efficient and automatic analysis on urban environment methods that utilize the computer vision and machine learning technology. Among many new analyses, urban safety analysis has received a major attention. In order to predict more accurately on safety score and reflect the human visual perception, it is necessary to consider the generic and local information that are most important to human perception. In this paper, we use Double-column Convolutional Neural network consisting of generic and local columns for the prediction of urban safety. The input of generic and local column used re-sized and random cropped images from original images, respectively. In addition, a new learning method is proposed to solve the problem of over-fitting in a particular column in the learning process. For the performance comparison of our Double-column Convolutional Neural Network, we compare two Support Vector Regression and three Convolutional Neural Network models using Root Mean Square Error and correlation analysis. Our experimental results demonstrate that our Double-column Convolutional Neural Network model show the best performance with Root Mean Square Error of 0.7432 and Pearson/Spearman correlation coefficient of 0.853/0.840.

• The Journal of the Korea Contents Association
• /
• v.16 no.8
• /
• pp.202-208
• /
• 2016

The scope of activities of the visually impaired is increasing. But they are not easy to visit the destination safely because the building was complicated and larger than ever. There is a guide system for visually impaired such as GPS and Audio alerts, Braille guide block, Acoustic signaller, etc. But they are not suitable for indoor because most of them are the outdoor guide system. Therefore, in this paper, I propose a system that provides guidance information to the visually impaired using Voice Technology, TTS (Text to Speech) and Haptic Technology, Beacon based on the wireless sensor networks. It informed the visually impaired of guidance information about destination such as distance, height, and obstacle to the destination using the generalized smart phone. The user could be received guide info about searches for the optimal route to the destination using the TTS technology and Haptic technology in test result of the proposed system.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.4
• /
• pp.75-82
• /
• 2010

At this time, our country's social welfare system for the handicapped is switching to increase independence, education is the most important. This study increases the quality of Visual handicapped people's life which have limit to learn and reduces their inconvenience which may occur during their independent school life through the development of the system which helps them safely to reach their destination by themselves using IT technologies in an educational institute which helps their ability to get information and be independent. This study supports Visual handicapped people to move safely by using cell phone which is necessary items for most modern people, RFID tags and white canes with antenna and reader which read the information installed in the raised blocks outside of school buildings and in the hall or aisle inside of buildings and inform the path by voice and vibration.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.1
• /
• pp.94-102
• /
• 2012

Recently entered into an aging socity as the number of elderly drivers is increasing. Traffic accidents of elderly drivers are caused by driver inattentions such as poor vehicle control due to aging, visual information retrieval problems caused by presbyopia, and objects identifying problems caused by low contrast sensitivity. In this paper, detection method of ROIs on the road is proposed. The proposed method creates the saliency map to detect the candidate ROIs from the input image. And, the input image is segmented to obtain the ROIs boundary. Finally, selective visual attention regions are detected according to the presence or absence of a segmented region with saliency pixels. Experimental results from a variety of outdoor environmental conditions, the proposed method presented a fast object detection and a high detection rate.

• Journal of the Korea Institute of Building Construction
• /
• v.22 no.2
• /
• pp.171-182
• /
• 2022

The regular assessment of a building is important to understand structural safety and latent risk in the early stages of building life cycle. However, methods of traditional assessment are subjective, atypical, labor-intensive, and time-consuming and as such the reliability of these results has been questioned. This study proposed a method to bring accurate results using a 3D laser scanner and integrate them in Building Information Modeling (BIM) to visualize defective condition. The specific process for this study was as follows: (1) semi-automated data acquisition using 3D laser scanner and python script, (2) scan-to-BIM process, (3) integrating and visualizing defective conditions data using dynamo. The method proposed in this study improved efficiency and productivity in a building assessment through omitting the additional process of measurement and documentation. The visualized 3D model allows building facility managers to make more effective decisions. Ultimately, this is expected to improve the efficiency of building maintenance works.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.377-378
• /
• 2008

본 논문은 시각 장애인들의 보행 시 앞을 볼 수 없는 점을 바탕으로 시각을 음성으로 대체하여 장애 물체가 발생하였을 경우 안전을 위하여 위험 요소를 사전에 경보하여 알려주도록 구현하였다. 시각 장애인들이 보행 시 장애 물체가 나타났을 경우 이를 입체 변위 센서인 초음파 센서로 장애물의 위치를 측정하고 측정된 거리 데이터를 근거리 무선통신인 블루투스를 동하여 송 수신하여 사용자인 시각 장애인에게 소형 스피커를 통하여 음성으로 알려주고 경고함으로써 위험 요소를 사전에 대처할 수 있도록 설계를 하였다. 초음파 입체 변위 센서를 이용하여 측정된 거리를 실시간 자동 거리 측정이 가능하도록 시스템을 구현하고 이 데이터를 근거리 무선 통신으로 송 수신하며 수신 모듈이 데이터를 음성으로 전환하여 실시간 자동 경보 시스템을 구축함으로써 보행 장애 위험물 감지가 보다 효율적으로 이루어지고 디지털화되게 시스템을 개선하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.11a
• /
• pp.383-386
• /
• 2009

대부분의 시각 장애인은 보행을 위해 흰 지팡이 및 안내견의 도움을 받는다. 일반적으로 사용되는 흰 지팡이는 주변 정보의 수집에 한계가 있으며 안내견은 고도의 훈련비용에 따른 비용의 문제점이 있어 그 수가 매우 제한적이다. 따라서 본 논문에서는 시각 장애인의 보행을 위한 시스템을 제한하고자 한다. 제안하는 시스템은 다음과 같다. 먼저 카메라를 이용하여 보행에 필요한 점자유도블럭을 검출한 후 검출된 점자유도블럭의 상태를 HRTF를 이용한 입체음향으로 소리를 전달하여 시각장애인이 안전한 보행을 할 수 있도록 하였다.