• 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.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.1C
• /
• pp.43-50
• /
• 2007

In the paper, we address QRM-MLD (Maximum Likelihood Detection with QR Decomposition and M-algorithm) signal detection method for spatially multiplexed MIMO (Multiple Input Multiple Output) systems. Recently, the QRM-MLD signal detection method which can achieve 1Gbps transmission speed for next generation mobile communication was implemented in a MIMO testbed for the mobile moving at a pedestrian speed. In the paper, we propose a novel signal detection method 'reduced complexity QRM-MLD' that achieves identical error performance as the QRM-MLD while reducing the computational complexity significantly. We rigorously compare the two detection methods in terms of computational complexity to show the complexity reduction of the proposed method. We also perform a set of computer simulations to demonstrate that two detection methods achieve identical error performance.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.405-405
• /
• 2019

최근 기후변화 및 지구온난화의 영향으로 집중호우, 돌발홍수, 가뭄 등 기상 이변이 빈번하게 발생하고 있어 물관리의 불확실성과 복잡성이 매우 높아지고 있다. 대규모 하천의 경우 다목적댐과 다기능보를 이용하여 홍수 및 가뭄에 대응이 비교적 용이하나, 중소하천의 경우 하천길이가 짧고 하천경사가 급해서 홍수파의 이동시간이 짧기 때문에 홍수대비를 위한 시간이 매우 짧다. 또한 중소하천 관리를 담당하는 지자체는 열악한 재정 여건과 전문인력 및 기술력 부족으로 인해 예방보다 사후복구에 집중하는 상황이며, 최근 하천 고수부지를 수변공원, 천변주차장 등으로의 공간적 활용이 증가됨에 따라 홍수발생시 위험성도 증가하고 있어 예방 및 대응 중심의 홍수 모니터링 기준 수립이 시급하다. 이에 K-water는 공익사업의 일환으로 K-water의 홍수 및 하천관리 노하우를 지자체와 공유하고 있다. 해당지자체의 과거 기상 및 수문자료들을 활용하여 홍수분석을 수행하고 지자체 중소하천에 최적화된 우량 및 수위 홍수 모니터링 기준을 수립하여 선제적 홍수대응을 할 수 있는 여건을 조성하였다. 또한 해당지자체의 우량 수위관측소의 분포와 용수전용댐 및 농업용저수지를 반영하여 유역특성을 고려한 홍수분석모형을 구축하였으며, 예상강우에 따른 주요 지점별 예상수위 및 도달시간 분석으로 지자체 담당자의 홍수대응을 지원하고자 한다. 하천 수위국 기준의 우량 알람은 하천 수위 상승 전 예비 알람의 성격으로 수위국의 수위가 상승하기 전 대비할 수 있는 선제적 대응 예방시간 확보에 도움이 될 수 있다. 또한 단계별 수위모니터링 기준에 의거하여 보행자 및 차량 통행제한 등의 조치를 취할 수 있으며, 제방월류 전 사전대응시간을 확보할 수 있어 자자체에서 능동적으며 선제적인 홍수 대응이 가능할 것으로 판단된다. 하지만 하천 수위국의 상황이 홍수에 따라 변화될 수 있으며, 홍수량 재산정 또는 하천기본 계획의 재수립 등 정책적, 현실적인 상황의 변화로 인해 모니터링 기준이 변화되어야 하는 경우에는 지속적인 보완이 필요할 것으로 사료된다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.13 no.4
• /
• pp.12-19
• /
• 2014

A signal plan focused on vehicle traffic could easily overlook vulnerable priority signals, although the importance of vulnerable movements is increasingly recognized in recent years. Especially, the vulnerable are sometimes faced with dangerous situations when crossing roads with a signal plan based on design values of average, non-vulnerable persons. This study is focused on how to minimize the vehicle delay while simultaneously considering traffic flow and providing traffic safety by increasing road crossing time for pedestrians. For this purpose, a priority signal control strategy for the vulnerable, considering vehicle traffic flow, has been tested. Practical implication and a microscopic computer simulation has shown that the proposed method could provide a small decrease (about 6.2%) in pedestrian delay, a small increase (about 8.5~13.3%) in travel speed of passing traffic, and a considerable decrease (16.2~26.9%) in vehicle travel time. These findings suggest that the proposed signal control strategy could increase pedestrian safety and diminish delay of vehicle travel.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.5
• /
• pp.3610-3618
• /
• 2015

The congestion of railway vehicle and station shows up to 220%. Especially, transfer resistance of passenger increase rapidly by the collision of circulation. So increment of travel time, occurrence of safety accidents act as a factor that inhibits the utilization of urban railway station. In this paper, to improve traveling speed and comfort of urban rail passengers, urban transit passenger guidance system using congestion management model is proposed. The congestion management model that can mitigate a recurring/non-recurring congestion is constructed and the preliminary design of the system (middleware system, control system, guidance drive system) is carried out. Passenger Guidance System is configured by step for changing the external data into a form usable by the algorithm, step to perform the congestion management algorithm using the real-time data and historical data, step to control device based on the value that is calculated by congestion management algorithm, step to drive the device based on the information in the control system and circulation guidance devices. In the future, detail design will be performed based on the preliminary design. A prototype of the various devices according to the station structures and locations will be made. The control module of guidance device will be developed.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.1
• /
• pp.100-118
• /
• 2021

In this study, PM accidents (1,603case) and bicycle accidents (14,672case) that occurred in the last three years were analyzed to determine the characteristics of PM traffic accidents. In particular, PM traffic accidents were divided into perpetrators and victims to determine the characteristics in detail. For PM accidents, the analysis was conducted on the status of each road grade, road type, weather condition, accident type, day and night occurrence, and vehicle type. The number of PM accidents that occurred in 2019 increased by 129%, and deaths increased by more than 200% compared to the previous year. The proportion of pedestrian accidents among PM traffic accidents was higher than that of bicycle accidents. Therefore, regulations on PM traffic are necessary. For the 20 deaths of PM, a detailed analysis was conducted to analyze the factors of traffic accidents. PM fatalities occurred in 50% of vehicle accidents, and 7 out of 10 vehicle accidents occurred at night. This is believed to have been caused by falling or overturning due to an obstacle, such as a depression in the road pavement or a speed bump.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.3
• /
• pp.247-262
• /
• 2022

In domestic tunnels, it is mandatory to install CCTVs in tunnels longer than 200 m which are also recommended by installation of a CCTV-based automatic accident detection system. In general, the CCTVs in the tunnel are installed at a low height as well as near by the moving vehicles due to the spatial limitation of tunnel structure, so a severe perspective effect takes place in the distance of installed CCTV and moving vehicles. Because of this effect, conventional CCTV-based accident detection systems in tunnel are known in general to be very hard to achieve the performance in detection of unexpected accidents such as stop or reversely moving vehicles, person on the road and fires, especially far from 100 m. Therefore, in this study, the region of interest is set up and a new concept of inverse perspective transformation technique is introduced. Since moving vehicles in the transformed image is enlarged proportionally to the distance from CCTV, it is possible to achieve consistency in object detection and identification of actual speed of moving vehicles in distance. To show this aspect, two datasets in the same conditions are composed with the original and the transformed images of CCTV in tunnel, respectively. A comparison of variation of appearance speed and size of moving vehicles in distance are made. Then, the performances of the object detection in distance are compared with respect to the both trained deep-learning models. As a result, the model case with the transformed images are able to achieve consistent performance in object and accident detections in distance even by 200 m.

• Journal of Internet Computing and Services
• /
• v.14 no.6
• /
• pp.33-39
• /
• 2013

When the eldery with limited mobility and disabled use a wheelchairs to move, it can cause decreased exercise ability like decline muscular strength in upper limb and lower extremities. The disabled people suffers with spinal cord injuries or post stroke hemiplegia are easily exposed to secondary problems due to limited mobility. In this paper, We designed intelligent wheelchair robot system for upper limb and lower extremities exercise/rehabilitation considering the characteristics of these severely disabled person. The system consists of an electric wheelchair, biometrics module for Identification characteristics of users, upper limb and lower extremities rehabilitation. In this paper, describes the design and configurations and of developed robot. Also, In order to verify the system function, conduct performance evaluation targeting non-disabled about risk context analysis with biomedical signal change and upper limb and lower extremities rehabilitation over wheelchair robot move. Consequently, it indicate sufficient tracking performance for rehabilitation as at about 86.7% average accuracy for risk context analysis and upper limb angle of 2.5 and lower extremities angle of 2.3 degrees maximum error range of joint angle.

• Journal of Korean Society of Transportation
• /
• v.27 no.2
• /
• pp.179-187
• /
• 2009

Currently, the signalized intersections in Korea are operated without providing an emergency vehicle preemption control strategy. Thus, it might threaten the safety of the pedestrians and drivers on highways when an emergency vehicle faces congested traffic conditions. The existing preemption control is activated when an emergency vehicle is detected along a path. This enables emergency vehicles to progress uninterrupted, but it also increases the delay of other vehicles. In this paper, a revised preemption control strategy considering queue length restrictions is proposed to make both a progressive movement of an emergency vehicle and reduce delay of other vehicles simultaneously. By applying the preemption control strategy through a simulation study, it was shown that delay of an emergency vehicle decreased to 44.3%-96.1% and speed increased to 8.8%-42.0% in all 9 cases as compared with a conventional signal control. The existing preemption control is superior for oversaturated conditions (v/c >1.0) or a link length less than 200m. However, the preemption control considering queue length constraints shows better performance than the existing preemption control when the v/c is less than 0.8 and a link length is longer than 500m.

• Journal of the Korean Wood Science and Technology
• /
• v.41 no.1
• /
• pp.12-18
• /
• 2013

Existing wood decks brings out negligent accident because fastener can be pulled-out by cyclic load of pedestrians. When deck and joist are connected, it also causes the problems, which are cracking of wood decks and rapid decay by material of fastener. In this study, strength property of deck unit using reinforced plastic connector made by domestic A company was evaluated. Southern yellow pine (Pinus palustris Miller) were used for deck material. Bending strength of deck units were implemented for fastener type and joist spacing (400, 600 mm). In the result, carbon steel screw into reinforced plastic connector was the best in average bending strength(Joist spacing : 400, 600 mm). In the result of bending strength for joist-width (40, 50, 70, 80 mm), the average maximum bending strength was measured when the joist spacing was 40 mm.