• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.15-16
• /
• 2023

해상교통관제 구역은 항만 시설을 사용하기 위한 입·출항 선박, 연안 해역을 이동하는 선박 등이 서로 복잡하게 운항하는 교통 패턴을 가지고 있다. 이를 안전하고 효과적으로 관리하기 위해 해상교통관제센터(VTS)에서는 선박을 실시간 모니터링하며 관제 업무를 수행하고 있지만, 교통 혼잡 상황에서는 업무 로드의 증가로 인해 관제 공백이 발생하기도 한다. 이에 교통 혼잡도 및 혼잡 구역을 예측한다면보다 효율적인 관제가 가능하지만 현재는 관제사의 경험에 전적으로 의존하고 있는 실정이다. 본 논문에서는 VTS 관점에서의 교통 혼잡을 정의하고, 과거 항적 데이터를 이용하여 항내 선박 교통 혼잡도 및 혼잡 구역을 예측하는 방법을 제안하였다. 또한, 실해역 데이터(대산항 VTS)를 적용하여 제안된 기술이 관제지원 도구로서 활용될 수 있는지 검토하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.379-381
• /
• 2021

비디오 모니터링은 자율주행차뿐만 아니라 농장 내 병든 동물 탐지 등과 같은 스마트팜 분야에서도 사람을 대신하여 24시간 연속 모니터링할 수 있는 중요한 응용 분야이다. 본 논문에서는 비디오 모니터링의 계산양을 줄이면서도 혼잡한 돈방에서 빠르게 움직이는 돼지들을 정확히 탐지하기 위해 CNN 기반 객체 탐지기의 정확도를 고려한 방법을 제안한다. 즉, 연속되는 비디오 영상에서 key frame을 먼저 추출한 후, 비디오의 특성인 움직임 정보가 포함된 영상에서 GMM을 이용하여 움직인 돼지와 움직이지 않은 돼지의 위치를 구분하고, 최종적으로 YOLOv4를 적용하여 움직인 돼지와 움직이지 않은 돼지를 탐지한다. 돈사에서 촬영된 비디오 데이터로 실험한 결과, 제안 방법은 효과적으로 움직인 돼지를 탐지할 수 있음을 확인하였다.

• Journal of Advanced Navigation Technology
• /
• v.14 no.3
• /
• pp.358-366
• /
• 2010

In the wireless network the congestion and delay occurs mainly when there are too many packets for the network to process or the sender transmits more packets than the receiver can accept. The congestion and delay is the reason of packet loss which degrades the performance of multimedia streaming. This paper proposes a novel transmission rate monitoring-based optimization mechanism to optimize packet loss and to improve QoS. The proposed scheme is based on the trade-off relationship between transmission rate monitoring and overhead monitoring. For this purpose this paper processes a source rate control-based optimization which optimizes congestion and delay. Performance evaluated RED, TFRC, and the proposed mechanism. The simulation results show that the proposed mechanism is more efficient than REC(Random Early Detection) mechanism and TFRC(TCP-friendly Rate Control) mechanism in packet loss rate, throughput rate, and average response rate.

• Journal of Korean Society of Transportation
• /
• v.27 no.5
• /
• pp.85-95
• /
• 2009

Congestion on expressways is increasing in spite of continuous road construction. In enlargement of expressway capacity to lessen congestion, a long period is needed and in the case of traffic congestion, it would be impossible to avoid long periods of traffic congestion. So, it is necessary to cope with traffic congestion through continuous traffic condition monitoring, analysis of the causes of congestion and the development of alternatives before traffic conditions worsen. A congestion index that can express traffic operating conditions measurably is needed to monitor those conditions. Thus, in this research, a new congestion index, the Traffic Condition Index (TCI), is developed. TCI is able to evaluate roads that have different grades (or design speeds) and to judge traffic condition as good, fair and poor (congested). In addition, TCI has merits in that it can strengthen the function of existing Freeway Traffic Management Systems (FTMS) and can be applied to congestion management easily: TCI calculates congestion intensity and severity using data obtained from existing FTMS. In order to validate TCI, it was applied to the Kyungbu Expressway and the Seohaean Expressway. As a result, TCI shows a good performance in the aspect of applicability and ability of presentation of traffic conditions compared with travel speed and Travel Time Index (TTI).

• Journal of the Korean Society for Railway
• /
• v.18 no.3
• /
• pp.270-277
• /
• 2015

In some sections of the Seoul Metropolitan Subway, severe congestion can be observed during rush hours and on specific days. The subway operators have been conducting regular surveys to measure the level of congestion on trains: the results are then used to make plans for congestion reduction. However, the survey has so far focused just on train' congestion and has been unable to determine non-recurring congestion due to special events. This study develops an algorithm to estimate the platform congestion rate by time using individual public transportation card data. The algorithm is evaluated by comparison of the estimated congestion rate and the ground truth data that are actually observed at non-transfer subway stations on Seoul subway line 2. The error rates are within ${pm}2%$ and the performance of the algorithm is fairly good. However, varying walking times from gates to platforms, which are applied to both non-peak periods and peak time periods, are needed to improve the algorithm.

• International Journal of Highway Engineering
• /
• v.10 no.3
• /
• pp.119-128
• /
• 2008

On the many highways, severe traffic congestions happen chronically and make traffic problems like reduction of mobility because of rapid increase of vehicles though road construction has been last. In order to solve these traffic problems, it is needed to find the trend and the symptom of traffic congestion and to analyze the cause of congestion and the(spatial) range affected by congestion. To develop the traffic condition monitoring index prior to doing all those things is most important. With this reason, many countries including U.S. had been developed the congestion criteria and indices. In this paper, applicability and characteristics of existing traffic congestion indices were considered and the direction for development of a new traffic condition index was suggested to achieve an effective traffic management.

• Journal of Digital Convergence
• /
• v.14 no.11
• /
• pp.289-295
• /
• 2016

Subway is a future-oriented means of transportation that can be safely and quickly mass transport many passengers than buses and taxis. Congestion growth due to the increase of the metro users is one of the factors that hinder citizens' rights to comfortably use the subway. Accordingly, congestion prediction in the subway is one of the ways to maximize the use of passenger convenience and comfort. In this paper, we monitor the level of congestion in real time via the existing congestion on the metro using multiple regression analysis and big data processing, as well as their departure station and arrival station information More information about the transfer stations offer a personalized congestion prediction system. The accuracy of the predicted congestion shows about 81% accuracy, which is compared to the real congestion. In this paper, the proposed prediction and recommendation application will be a help to prediction of subway congestion and user convenience.

• Journal of Korean Society of Transportation
• /
• v.17 no.3
• /
• pp.61-70
• /
• 1999

The Purpose of this study is to test whether Braess Paradox (BP) can be revealed in a real world network. Fer the study, Namsan 2nd tunnel case is chosen, which was shut down for 3 years for repair works. The revelation of BP is determined by analyzing network-wise traffic impacts followed by the tunnel closure. The analysis is conducted using a network simulation model called SECOMM developed for the congestion management of the Seoul metropolitan area. Also, the existence of BP is further identified by a before-after traffic survey result of the major arterials nearby the Namsan 2nd tunnel. The model estimation expected that the closure of Namsan 2nd tunnel improve the network-wise average traffic speed from 21.95km/h to 22.21km/h when the travel demand in the study area and congestion Pricing scheme on Namsan 1st & 3rd tunnels remain unchanged. In addition, the real world monitoring results of the corridors surrounding Namsan 2nd tunnel show that the average speed increases from 29.53km/h to 30.37km/h after the closure. These findings clearly identify the BP Phenomenon is revealed in this case.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.80-82
• /
• 2019

드론은 좁은 장소나, 도로 위에서도 자유롭게 운용할 수 있다는 등의 장점으로 인해 점차 교통 모니터링 분야에 서도 널리 쓰이고 있다. 교통 모니터링을 통해 교통관제가 가능하며, 교통혼잡 해소에 활용할 수 있다. 교통량 확인을 위하여 기존에는 hand-crafted 기반의 방법들이 사용되었는데, 이러한 방법들은 조명이나 촬영위치에 취약하다. 따라서 이러한 문제를 해결하기 위해 본 논문에서는 딥러닝 기반의 교통량 확인 알고리즘을 제안하였다. 본 논문에서는 드론의 촬영 환경과 비슷한 환경의 도로 데이터를 수집하였다. 정확도를 좀 더 높이기 위해, 데이터 augmentation 을 하였다. 생성된 데이터를 이용하여 학습을 진행하였고, 학습 결과 97%의 정확도가 나옴을 확인하였다. 테스트 데이터에 대한 정확도 측정은 [250 pixel 이상] X [250 pixel 이상] 크기의 객체에 대해서 IOU 0.3 기준으로 측정되었다.

• Journal of Korean Society of Transportation
• /
• v.30 no.1
• /
• pp.149-159
• /
• 2012

The evaluation of public transit service quality is more complicated than evaluating other aspects of transportation service. Although various measures of effectiveness [MOEs] for transit service have been studied and applied, a more comprehensive and accurate MOE is still required. In the past, either data from user surveys or the experience of bus agency administrators and/or engineers used to measure the quality of service. However, recently, with reliable and accurate real time data from BMS(Bus Management System) and BIS(Bus Information System), more reliable and accurate MOEs are available. This study develops a service evaluation model from users' perspectives, which is based on user' cost models that consider passenger access time, riding time, waiting time, and discomfort due to in-vehicle overcrowding, violation of traffic laws, and accident rate. For validating proposed model, data from the BMS and transit-fare cards (T-Money Card) for Seoul's No. 472 main bus line were used. Models developed in this study provided reliable results.