• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.273-275
• /
• 2011

최근 교통량이 증가함에 따라 자동차 사고피해도 비례하여 증가하고 있으며, 이로 인해 CCTV 등과 같이 교통사고 예방에 소모되는 비용이 막대하게 지출되고 있다. 단일시점 카메라의 시스템은 객체들의 겹침, 카메라각도에 의한 인식오류 등으로 오차율이 높은 단점이 있다. 이를 보완하기 위해 다중시점의 협업기반 자동 상황인지 시스템을 제안한다. 제안하는 방법은먼저 영상데이터로부터 차량, 사람 등의 객체를 추출하고 이들 객체 쌍의 특징 정보를 계산한다. 이를 바탕으로 각 카메라 센서노드의 규칙기반 시스템을 이용하여 객체간의 사고여부를 가려낸다. 각 센서노드의 사고여부 정보는 메인서버로 수집되고, 수집된 정보는 상위 규칙에 의해 최종 사고 여부가 판단된다. 본 논문에서는 실제 교차로에 설치된세대의 카메라를 이용한 실험을 통해 제안하는 시스템의 성능을 검증하였다.

• Spatial Information Research
• /
• v.21 no.3
• /
• pp.11-19
• /
• 2013

Compared with traditional video monitoring systems that provide a video-recording function as a main service, an intelligent video monitoring system is capable of extracting/tracking objects and detecting events such as car accidents, traffic congestion, pedestrian detection, and so on. Thus, the object tracking is an essential function for various intelligent video monitoring and surveillance systems. In this paper, we propose a background and local histogram-based object tracking approach for intelligent video monitoring systems. For robust object tracking in a live situation, the result of optical flow and local histogram verification are combined with the result of background subtraction. In the proposed approach, local histogram verification allows the system to track target objects more reliably when the local histogram of LK position is not similar to the previous histogram. Experimental results are provided to show the proposed tracking algorithm is robust in object occlusion and scale change situation.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.10
• /
• pp.162-170
• /
• 2013

In recent years, the interests and needs of the Pedestrian Protection System (PPS), which is mounted on the vehicle for the purpose of traffic safety improvement is increasing. In this paper, we propose a pedestrian candidate window extraction and unit cell histogram based HOG descriptor calculation methods. At pedestrian detection candidate windows extraction stage, the bright ratio of pedestrian and its circumference region, vertical edge projection, edge factor, and PCA reconstruction image are used. Dalal's HOG requires pixel based histogram calculation by Gaussian weights and trilinear interpolation on overlapping blocks, But our method performs Gaussian down-weight and computes histogram on a per-cell basis, and then the histogram is combined with the adjacent cell, so our method can be calculated faster than Dalal's method. Our PCA reconstruction error based pedestrian detection candidate window extraction method efficiently classifies background based on the difference between pedestrian's head and shoulder area. The proposed method improves detection speed compared to the conventional HOG just using image without any prior information from camera calibration or depth map obtained from stereo cameras.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.3
• /
• pp.319-325
• /
• 2015

High-strength steel has replaced mild steel as the material of choice for truck decks or frames, owing to the growing demand for lightweight vehicles. Although studies on the weld fatigue characteristics of mild steel are available, studies on high-strength steels have been seldom conducted. In this study, firstly, we surveyed a chosen number of approaches and selected the Radaj method, which uses the notch factor approach, as the one suitable for evaluating the fatigue life of commercial vehicles. Secondly, we obtained the S-N curves of HARDOX and ATOS60 steel welds, and the F-N curves of the T-weld and overlapped-weld structures. Thirdly, we acquired a general S-N curve of welded structures made of high-strength steel from the F-N curve, using the notch factor approach. Fourthly, we extracted the weld fatigue characteristics of high-strength steel and incorporated the results in the database of a commercial fatigue program. Finally, we compared the results of the fatigue test and the CAE prediction of the example case, which demonstrated sufficiently good agreement.

• Journal of the Korean Applied Science and Technology
• /
• v.32 no.2
• /
• pp.348-361
• /
• 2015

To reduce the effects of greenhouse gas (GHG) emissions, the government has announced the special platform of technologies as parts of an effort to minimize global climate change, and the government distributed biodiesel since 2006 as the further efforts. Although there are some debates about some quality specifications and unbalanced of source (44% from palm oil), more than 400kton/year of biodiesel was produced in 2013. Moreover the amounts will be increased when the RFS is activated. To solve the unbalanced situation and to achieve the diversity of feeds, it is essential that many researches should be considered. Especially, free and bond glycerines are one of the important properties seriously affected to the combustion system in vehicle & cold properties. Previous method (KS M 2412) couldn't cover the biodiesel derived from lauric oil($C_{12:0}$) such as PKO (Palm Kernel Oil), Coconut oil because those compositions are lighter than other conventional biodiesel sources. In this study, we review the existed method and figure out the factors should improve to analysis the glycerine from PKO and Coconut oil biodiesel. Modifying the analysis conditions to enhance the resolution and change the internal standards to avoid the overlapped- peaks between Capric acid ME ($C_{10:0}$) and standard#1(1,2,4-butantriol). From this revised method, we could solve the restrictions of previous methods. And check the possibility of new method to analyze the glycerine in biodiesel regardless of sources.

• Journal of Intelligence and Information Systems
• /
• v.11 no.3
• /
• pp.25-43
• /
• 2005

In modern automated container terminals, automated guided vehicle (AGV) systems are considered a viable option for the horizontal tansportation of containers between the stacking yard and the quayside cranes. AGVs in a container terminal move rather freely and do not follow fixed guide paths. For an efficient operation of such AGVs, however, a sophisticated traffic management system is required. Although the flexible routing scheme allows us to find the shortest possible routes for each of the AGVs, it may incur many coincidental encounters and path intersections of the AGVs, leading to collisions or deadlocks. However, the computational cost of perfect prediction and avoidance of deadlocks is prohibitively expensive for a real time application. In this paper, we propose a traffic control method that predicts and avoids some simple, but at the same time the most frequently occurring, cases of deadlocks between two AGVs. More complicated deadlock situations are not predicted ahead of time but detected and resolved after they occur. Our method is computationally cheap and readily applicable to real time applications. The efficiency and effectiveness of our proposed methods have been validated by simulation.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.6
• /
• pp.915-936
• /
• 2017

In this study, current status of Korean hazard mitigation guideline for tunnel operation is summarized. It shows that requirement for CCTV installation has been gradually stricted and needs for tunnel incident detection system in conjunction with the CCTV in tunnels have been highly increased. Despite of this, it is noticed that mathematical algorithm based incident detection system, which are commonly applied in current tunnel operation, show very low detectable rates by less than 50%. The putative major reasons seem to be (1) very weak intensity of illumination (2) dust in tunnel (3) low installation height of CCTV to about 3.5 m, etc. Therefore, an attempt in this study is made to develop an deep-learning based tunnel incident detection system, which is relatively insensitive to very poor visibility conditions. Its theoretical background is given and validating investigation are undertaken focused on the moving vehicles and person out of vehicle in tunnel, which are the official major objects to be detected. Two scenarios are set up: (1) training and prediction in the same tunnel (2) training in a tunnel and prediction in the other tunnel. From the both cases, targeted object detection in prediction mode are achieved to detectable rate to higher than 80% in case of similar time period between training and prediction but it shows a bit low detectable rate to 40% when the prediction times are far from the training time without further training taking place. However, it is believed that the AI based system would be enhanced in its predictability automatically as further training are followed with accumulated CCTV BigData without any revision or calibration of the incident detection system.