• Journal of Cadastre & Land InformatiX
• /
• v.52 no.1
• /
• pp.81-93
• /
• 2022

Recently, there have been many studies on object recognition around the vehicle and recognition of traffic signs and traffic lights in autonomous driving. In particular, such the recognition of traffic lights is one of the core technologies in autonomous driving. Therefore, many studies for such the recognition of traffic lights have been performed, the studies based on various deep learning models have increased significantly in recent. In addition, as a high-quality AI training data set for voice, vision, and autonomous driving is released on AIHub, it makes it possible to develop a recognition model for traffic lights suitable for the domestic environment using the data set. In this study, we developed a recognition model for traffic lights that can be used in Korea using the AIHub's training data set. In particular, in order to improve the recognition performance, we used various models of YOLOv4 and YOLOv5, and performed our recognition experiments by defining various classes for the training data. In conclusion, we could see that YOLOv5 shows better performance in the recognition than YOLOv4 and could confirm the reason from the architecture comparison of the two models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.2875-2893
• /
• 2015

Existing coding aware routing algorithms focused on novel routing metric design that captures the characteristics of network coding. However, in packet coding algorithm, they use opportunistic coding scheme which didn't consider the queue state of the coding node and are equivalent to the conventional store-and-forward method in light traffic load condition because they never delay packets and there are no packets in the output queue of coding node, which results in no coding opportunity. In addition, most of the existing algorithms assume that all flows participating in the network have equal rate. This is unrealistic since multi-rate environments are often appeared. To overcome above problem and expand network coding to light traffic load scenarios, we present an enhanced coding-aware routing algorithm based on queue state and local topology (OQMCAR), which consider the queue state of coding node in packet coding algorithm where the control policy is of threshold-type. OQMCAR is a unified framework to merge single rate case and multiple rate case, including the light traffic load scenarios. Simulations results show that our scheme can achieve higher throughput and lower end-to-end delay than the current mechanisms using COPE-type opportunistic coding policy in different cases.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.3
• /
• pp.41-46
• /
• 2021

The number of big traffic accident cases of pedestrian death appeared to be minor, however compared to death rate in car to car accidents is very high and quite a few of the pedestrian death rates among all traffic accidents are counted to be almost 40%. Previous pedestrian safety studies were mostly aimed at reducing the degree of pedestrian injuries from a vehicle to pedestrian collision, and less at preventing a collision itself. This research was conducted with a method of using road facilities to prevent vehicles from rushing into the sidewalk. This research used one of the collision analyzing programs, called PC-Crash to simulate the vehicle rushing into the sidewalk. Based on the program, it could derive an optimal safe zone location where the pedestrian can wait for the pedestrian light safely. Also, changing road facilities such as pedestrian light pillars or signal controllers can widen 440% compared to the present safe zone. Accordingly, researchers have to consider a method to analyze and apply pedestrian safe zones along with road facilities location when designing a road.

• Journal of Korean Society of Transportation
• /
• v.8 no.1
• /
• pp.73-88
• /
• 1990

This study aims to develop a traffic accident forecasting model using the data, which are based on the past accidents in Korea. The regression analysis was used in conjuction with the variables of the traffic accidents and social behaviours. The objectives of this study are as follows; 1. The number of behicles has given a strong affect to increase the traffic accidents in Korea since a factor of vehicles has shown 86% over of total accidents. 2. The forecasting model regarding the traffic accidents, deaths and injuries, which was formulated for this study, proved to be useful in light of the results of the regression diagnostics. 3. It is expected that the traffic accidents in Korea in 1991 may take place as follows on condition that the traffic environment would worsen ; 274,000 cases of accidents with 13,600 deaths and 367,000 injuries, in 1994, 451,000 cases with 24,900 deaths and 71,500 injuries respectively.

• Journal of Korean Society for Atmospheric Environment
• /
• v.9 no.E
• /
• pp.364-372
• /
• 1993

The purpose of this study is to analyze traffic patterns by use of TRANSYT-7F Model, and to choose the optimum traffic-light cycle length and cycle splite to improve traffic flow and air quality at Samsung Intersection in Seoul. Emission rates of air pollutants are calculated for three time segments 0700-0900, 0900-1800 and 1800-2000. The traffic volume correlated reasonably well with air pollutants emitted ; however, the phasing and timing of traffic signals was found to equally be important. The results of performance with optimal setting indicate that the best cycle length were 80sec(0700-0900), 95sec(0900-1800) and 90sec(1800-2000), res-pectively. As expected the highest emissions of air pollutants were observed during the evening rush hours (1800-2000). A properly designed signalized intersection can help reduce traffic delay, driver discomfort, fuel consumption, and air pollution by efficiently the capacity of existing intersection.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.8 no.5
• /
• pp.114-120
• /
• 2009

In outdoor visible light communication channels and LED road illumination communications for the intelligent transport systems (ITS), inter symbol interference (ISI) due to multipath propagation prevents high data rate transmission. Indoor wireless optical communication systems utilizing white LED lights and on the road illumination have been studying about it. Generally, plural lights are installed in room and considered to the traffic information system using existing LED traffic lights. Therefore, their optical path difference must be considered. In this paper, the influence of an optical path difference has been investigated and two approaches against this problem are introduced. One uses on-off keying, return-to-zero (OOK-RZ) coding and the other uses optical orthogonal frequency division multiplexing(OFDM).

• Journal of applied mathematics & informatics
• /
• v.8 no.3
• /
• pp.1035-1045
• /
• 2001

We present two decomposition approximations for the mean sojourn times in open single class queing networks. If there is a single bottleneck station, the approximations are asymptotically exact in both light and heavy traffic. When applied to a Jackson network or an M/G/1 queue, these approximations are exact for all values of the traffic intensity.

• Journal of Korean Society of Transportation
• /
• v.30 no.6
• /
• pp.93-102
• /
• 2012

The frequency and severity of traffic accidents related to signalized intersections in urban areas have been more serious than those in both arterial segments and crosswalks. Especially, traffic accidents involved with injuries and fatalities have caused by traffic signal violations within intersections. Therefore, many countries including Korea have installed the red light enforcement camera (RLE) to reduce traffic accidents associated with the traffic signal violation. Meanwhile, many methodologies have been studied in terms of safety impacts estimation of red light enforcement, which, however, cannot be easy to conduct. In this study, safety impacts was estimated for intersections of Chicago downtown area using SPF models and EB approach. As a result, for all crash types and target traffic accident types such as "angle", "rear end", "sideswipe in the same and other directions", "turn", and "head on", fatal crashes were reduced by 26% and 38%. However, RLE may increase property-demage-only-crashes by 3.23% and 1.16%, respectively.

• Journal of Korean Society of Transportation
• /
• v.14 no.1
• /
• pp.101-116
• /
• 1996

Increased attention has been paid in recent years to the need of traffic management for alleviating urban traffic congestion. This paper presents a discrete event modeling and simulation framework for analyzing the traffic flow. Traffic simulation models can be classified as being either microscopic and macroscopic models. The discrete event modeling and simulation technique can be basically employed to describe the macroscopic traffic simulation model. To do this, we have employed the System Entity Structure/Model Base (SES/MB) framework which integrates the dynamic-based formalism of simulation with the symbolic formalism of AI. The SES/MB framework supports to hierarchical, modular discrete event modeling and simulation environment. We also adopt the Symbolic DEVS (Discrete Event System Specification) to developed the automated analysis methodology for generating optimal signal light policy. Several simulation tests will demonstrates the techniques.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.11
• /
• pp.5334-5337
• /
• 2013

In this paper, the structure of traffic lights removed the wire for the completion of urban aesthetics is analyzed. The finite element model consists of shell elements from three-dimensional CAD model of actual traffic signal. Traffic light pole, horizontal stand shape, thickness, stiffeners, etc. are considered in this study. Analysis of stress and deformation is performed by applying wind load. When the wind load is applied, the result on traffic signal is analyzed. This study is to perform the basic tasks for improving the design.