• Proceedings of the KAIS Fall Conference
• /
• 2009.12a
• /
• pp.594-596
• /
• 2009

본 연구에서는 영상센서를 이용한 상황인식 기반의 컴퓨팅 기술이 혼합된, 스쿨존 안전 관리 시스템을 제안한다. 영상센서를 통한 객체 추출과 상황 인식 기술의 조합을 통하여, 초등학교 주위에서 발생할 수 있는 여러 상황 중 초등학생의 유괴나 사고 등을 인식할 경우 모니터링 장치로 전송하여 응급 상황을 관리할 수 있다. 또한 제안된 시스템은 인간의 시각을 필요로 하는 철도 건널목이나, 교통량 통계조사, 공장 자동화 시스템 등 다양한 응용분야에 활용할 수 있는 최적의 선택이라 할 수 있다.

• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.23-31
• /
• 2020

This study was carried out to generate various images of railroad surfaces with random defects as training data to be better at the detection of defects. Defects on the surface of railroads are caused by various factors such as friction between track binding devices and adjacent tracks and can cause accidents such as broken rails, so railroad maintenance for defects is necessary. Therefore, various researches on defect detection and inspection using image processing or machine learning on railway surface images have been conducted to automate railroad inspection and to reduce railroad maintenance costs. In general, the performance of the image processing analysis method and machine learning technology is affected by the quantity and quality of data. For this reason, some researches require specific devices or vehicles to acquire images of the track surface at regular intervals to obtain a database of various railway surface images. On the contrary, in this study, in order to reduce and improve the operating cost of image acquisition, we constructed the 'Defective Railroad Surface Regeneration Model' by applying the methods presented in the related studies of the Generative Adversarial Network (GAN). Thus, we aimed to detect defects on railroad surface even without a dedicated database. This constructed model is designed to learn to generate the railroad surface combining the different railroad surface textures and the original surface, considering the ground truth of the railroad defects. The generated images of the railroad surface were used as training data in defect detection network, which is based on Fully Convolutional Network (FCN). To validate its performance, we clustered and divided the railroad data into three subsets, one subset as original railroad texture images and the remaining two subsets as another railroad surface texture images. In the first experiment, we used only original texture images for training sets in the defect detection model. And in the second experiment, we trained the generated images that were generated by combining the original images with a few railroad textures of the other images. Each defect detection model was evaluated in terms of 'intersection of union(IoU)' and F1-score measures with ground truths. As a result, the scores increased by about 10~15% when the generated images were used, compared to the case that only the original images were used. This proves that it is possible to detect defects by using the existing data and a few different texture images, even for the railroad surface images in which dedicated training database is not constructed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.1
• /
• pp.579-584
• /
• 2017

The damper oil seal of a high-speed railway vehicle is made from nitrile butadiene rubber (NBR) in order to prevent lubricant from leaking into the damper and to stop harmful contaminants from entering the external environment while in service. Oil leakage through the seal primarily occurs from fatigue failure of the damper. Cumulative damage of the seal occurs due to the contact force between the rod and the rubber during movement due to track irregularities and cants, among other factors. Thus, the design of the oil seal should minimize the maximum principal strain at weak points. In this study, the optimal cross section of the damper oil seal was found using the multi-island genetic algorithm method to improve the durability of the damper. The optimal shape of the oil seal was derived using process automation and design optimization software. Nonlinear material properties for finite element analysis (FEA) of the rubber were determined by Marlow's model. The nonlinear FEA confirmed that the maximum principal strain at the oil leakage point was decreased 24% between the initial design and the optimum design.

• Journal of the Korean Society for Railway
• /
• v.11 no.2
• /
• pp.139-144
• /
• 2008

Recent advances in embedded system technology have brought more dependence on automating train control. While much efforts have been reported to improve electronic hardware's safety, not so much systematic approaches to evaluate software's safety, especially for the vital software running on board train controllers. In this paper, we propose a new software tool to evaluate software safety for the train controller. We have reviewed requirements in the international standards and surveyed available tools in the market. From that, we identified necessary tests to meet the standards and proposed a tool that can be used during the whole software life cycle. We show the functional architecture and internal components of the tool. Our tool is unique in that it is a comprehensive tool specifically designed for software safety evaluation while other tools are not.

• Convergence Security Journal
• /
• v.9 no.1
• /
• pp.11-17
• /
• 2009

The object of this paper is to design a school-zone safety management system based on context-aware, integrated with computing technology. When it occurs to kidnap of elementary school students, the monitoring device creates context information through a combination object extraction and context-aware technology and alarm administrator about an emergency situation. In addition, the proposed system that requires a human perspective, a railroad crossing, statistics research of traffic, and a variety of applications such as factory automation systems can be used to be the best choice.