• Journal of KIISE
• /
• v.42 no.10
• /
• pp.1231-1238
• /
• 2015

Traffic light rules are one among the most common and important safety rules as the directly correlate with the safety of pedestrians. Consequently, an algorithm is required to cause an automated (or semi-automated) vehicle to observe traffic light signals. We present a novel, artificial potential function to guide an automated vehicle through traffic lights. Our function consists of three potential function components representing the three traffic light colors: green, yellow, and red. The traffic light potential function smoothly changes an artificial potential field using the elapsed time for the current light and light conversion. Our traffic light potential function is combined with other potential functions to guide vehicles' movement and constructs the final artificial potential field. Using various simulations, we found or method successfully guided the vehicle to observe traffic lights while behaving like human-controlled cars.

• Journal of the Korean Society for Advanced Composite Structures
• /
• v.6 no.3
• /
• pp.62-68
• /
• 2015

As a preparation of a design standard regarding road facilities, such as cantilever columns for traffic lights, street lights on highways is proposed. Currently these minor structures are designed based on guidelines which are mixed with multiple old foreign specifications without any criteria in terms of safety and economy, which could lead irregular safeties and the loss of national properties. In the considered two cases for effective projected area, it is found that following efficient way of design without critical analyses could make significant errors and miscalculations. Therefore, a fundamental research on the minor structures is urgently needed.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2010.03a
• /
• pp.1073-1076
• /
• 2010

Shallow foundations of various columns such as traffic signs, CCTVs, traffic lights, street lights, steel telephone poles and so on are made by cast-in-situ concrete method. However, typical cast-in-situ method has many problems because of the long duration of construction, occupation of sidewalks and low strength of the concrete after curing. In order to solve the problems, field load tests for the prefabricated DSF foundation made by combination of column and foundation was conducted to know load-deformation behavior by torsional tests.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1934-1937
• /
• 2022

The meaning of crosswalks and traffic lights in modern society has changed a lot as the enforcement of traffic signal violations has been strengthened. In this paper, we present a new next-generation traffic light method using radar and Can-bus communication methods suitable for the new traffic signal enforcement system. This method is a system that prevents accidents by transmitting information on the entry of a person and a car to a traffic light in a place where a person and a car passing through a mutually invisible traffic light cannot be seen. Since this system has only been developed for a month, it may be somewhat lacking in experimentation. However, in just one month, there have been no incidents except for a few people where the system has been installed.

• 한국도로학회:학술대회논문집
• /
• 2006.10a
• /
• pp.293-300
• /
• 2006

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.4
• /
• pp.41-48
• /
• 2017

It is necessary to develop an LED traffic light lens having a snow removal function capable of clearly providing a traffic signal to the driver even when a traffic light is blurred due to heavy snow and wind in the winter season. This study is focused on the research and development of the traffic light lens in the process of developing the LED traffic light with the snow removal function. In the developed traffic light lens, instead of attaching the film heater, the coated nichrome wire was wound into a coil shape and inserted directly into the groove in the lens. The developed heater system facilitates the insertion of the heating wire with high elasticity into a curved lens and can provide a sufficient heat without deformation of the PC lens. The proposed traffic lights were tested in various external environments and the test results showed that complete snow removal is possible without tunnel effect.

• Journal of Korea Multimedia Society
• /
• v.21 no.11
• /
• pp.1244-1253
• /
• 2018

The color of traffic light is sensitive to various illumination conditions. Especially it loses the hue information when oversaturation happens on the lighting area. This paper proposes a traffic light recognition method robust to these illumination variations. The method consists of two steps of traffic light detection and recognition. It just uses the intensity and saturation in the first step of traffic light detection. It delays the use of hue information until it reaches to the second step of recognizing the signal of traffic light. We utilized a deep learning technique in the second step. We designed a deep convolutional neural network(DCNN) which is composed of three convolutional networks and two fully connected networks. 12 video clips were used to evaluate the performance of the proposed method. Experimental results show the performance of traffic light detection reporting the precision of 93.9%, the recall of 91.6%, and the recognition accuracy of 89.4%. Considering that the maximum distance between the camera and traffic lights is 70m, the results shows that the proposed method is effective.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1997.04a
• /
• pp.81-85
• /
• 1997

In a virtual environment, agents must demonstrate some degree of realism and interactivity. This paper discusses the algorithm that enables agents to navigate a virtual road network realistically and interactively. The road description files written in this language provide the information of road environments to the navigating agents and the scene visualizer. We call this navigating agent in the road an ambient car. The ambient cars must follow the traffic rules as human does. To do this, the ambient car should continuously check its circumstances, such as, the traffic lights, lanes, road signs, and other ambient cars. Because of the huge scale of road network and the large number of ambient cars, the algorithm considers only the area where the participant is currently located. By this locality, the performance of the whole system does not fluctuate much in different situations. The behavior of ambient cars according to the predefined rules may appear monotonous. We added probability distribution functions to introduce some randomness. We implemented the above idea on silicon Graphics Indigo 2 workstation. The ambient car exhibited its awareness of lanes, traffic lights, and other cars. The participants could hardly distinguish between a human-controlled car and computer-controlled ambient car generated by the algorithm.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.2
• /
• pp.101-108
• /
• 2015

In this paper, a robust traffic light detection method is proposed by using vision sensor and DGPS(Difference Global Positioning System). The conventional vision-based detection methods are very sensitive to illumination change, for instance, low visibility at night time or highly reflection by bright light. To solve these limitations in visual sensor, DGPS is incorporated to determine the location and shape of traffic lights which are available from traffic light database. Furthermore the geometric relationship between traffic light and vision sensor is used to locate the traffic light in the image by using DGPS information. The empirical results show that the proposed method improves by 51% in detection rate for night time with marginal improvement in daytime environment.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.7
• /
• pp.1129-1139
• /
• 2022

Collision accidents happen frequently. The majority of ships involved in collisions in the coastal areas of Korea are middle and small size ships. The proportion of collision accidents is only 9% of all types of marine accidents; however, the number of casualties resulting from collisions is 34.4% of all human life damages. Generally, as reported by the people involved in these collisions, the navigation lights of the opponent ships were poor and invisible when the accident happened even though the weather and visibility were good. Furthermore, there are many insistences for poor navigation light conditions of the opponent ship in the bay or harbor. Therefore, it is necessary to analyze the present conditions and safety of navigation lights. Therefore, in this study, we examined the rules and books of navigation lights and compared it to that of other transportation systems, such as aircraft, trains, and road vehicles. Furthermore, we analyzed the current marine traf ic circumstances and ship collision accidents that happened in the past 5 years. Additionally, a questionnaire was prepared to gather the opinion of ship experts and secure the objectivity for improvement methods of navigation lights. Finally, methods to improve the navigation lights on ships were devised.