• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.12
• /
• pp.1122-1129
• /
• 2015

This paper suggests a method of detecting traffic lights for vehicles by combining the HSV(hue saturation value) color model, morphometric characteristics, and location information appearing on consecutive images in daytime. In order to detect the traffic light, the color corresponding to the signal lights should be explored. It is difficult to detect traffic lights among colors of lights from buildings, taillight of cars, leaves, placards, etc. The proposed algorithm searches for the traffic lights from many candidates using morphometric characteristics and location information in consecutive images. The recognition process is divided into three steps. The first step is to detect candidates after converting RGB channel into HSV color model. The second step is to extract the boundaries between the housing of traffic lights and background by exploiting the assumption that the housing has lower brightness than the surrounding background. The last step is to recognize the signal light after eliminating the false candidates using morphometric characteristics and location information appearing on consecutive images. This paper demonstrates successful detection results of traffic lights from various images captured on the city roads.

• Journal of Radiation Protection and Research
• /
• v.32 no.2
• /
• pp.79-88
• /
• 2007

When an accident occurs at nuclear power plant and radionuclide material is released to the area around the plant, public evacuation is considered as a measure to protect the safety of the residents nearby. This study draws factors required to estimate evacuation time and make estimation of the time to evacuate all residents from the EPZ of Wolsong site in consideration of traffic condition in the neighborhood and on the basis of field data around the site for each factor. The traffic capacity and the traffic volume by season were investigated for the traffic analysis and simulation within EPZ of Wolsong site. As a result, the background traffic volume by season were established. To estimate TGT(Trip Generation Time), the questionnaire surveys were carried out for resident and transient. The TSIS code was applied to traffic analysis in the events of daytime/night and normal/adverse weather under normal day/summer peak traffic condition. The results showed that the evacuation time required for total vehicles to move out from EPZ took generally from 118 to 150 minutes. The evacuation time took longer maximum 17 minutes at night than daytime during summer peak traffic.

• Journal of Environmental Science International
• /
• v.16 no.10
• /
• pp.1179-1187
• /
• 2007

This paper represents the statistical characteristics of sources and receptors for road traffic noise in apartment complex. Also we suggested that the site-specific characteristics of vertical and horizontal distributions in the complex apartment have been derived using a different analysis for evaluating levels of Leq1h by the apartment floor at a given distance from a road in terms of the flow rate, the mean speed of the traffic, and the percentage of the type vehicles in the day and night periods. As a result, the contribution orders of traffic quantity by the type of vehicles showed as followed: light vehicle>medium vehicle>heavy vehicle>motorcycle. Especially, the mixing ratio of entering the road on the heavy vehicle in the daytime was two times higher than that of in the night. The speed in all types of vehicle is in the range of 41 and 81 km/hr and noise level was not significantly different in day and night-time. The sources of road traffic noise had different variations and uncertainties using a random variable and probability distribution. The sound distribution to receptors by the apartment floor showed S curve between 1st floor and $15^{th}$ floor With the normality test, the normal distributions using Anderson-Darling Test followed $1^{st},\;3^{th},\;13^{th}$ and $15^{th}$, floor in the daytime and all floors except $7^{th}$ floor in the night (p>0.05). And also, the value of the pearson correlation coefficient (r) obtained in this study have significantly different at the range of floor. In conclusion, the results suggested that the distribution characteristics of levels of $Leq_{1h}$ on the sources and receptors of road traffic noise in apartment complex must be improved and developed on the guideline of regulation of road traffic noise.

• Journal of Environmental Health Sciences
• /
• v.21 no.4
• /
• pp.56-62
• /
• 1995

Recently, the traffic noise around residences and schools has become a serious social problem with the increase of the amount of transportation. This study was performed to investigate the sound proof efficiency of windows for traffic noise. The results were as follows 1) The traffic noise in 19 sites among 22 sampling sites was higher value than 65 dB(A) being roadside environment standard level in the daytime when all windows were opened, while the noise in 22 sampling sites was transmitted below standard level when all windows were closed. 2) The transmission loss of sound level at single window and double windows were 10~25 dB(A) and 11~29 dB(A) respectively. 3) The transmission loss of sound level at sampled school with sound proof pannel was 7~8 dB (A), which was lower 2~7 dB(A) than the theoretical value of the influence assessment . 4) The construction cost of double windows was lower 28% even if include the cost of setting up air conditioner for the summer season and the power consuming cost for its operation than that of sound proof pannel for traffic noise. 5) The effect of transmission loss of windows was more influenced by airtight than materials of windows.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.237-250
• /
• 2015

This paper describes a hardware-oriented algorithm and its conceptual implementation in a real-time speed limit traffic sign detection system on an automotive-oriented field-programmable gate array (FPGA). It solves the training and color dependence problems found in other research, which saw reduced recognition accuracy under unlearned conditions when color has changed. The algorithm is applicable to various platforms, such as color or grayscale cameras, high-resolution (4K) or low-resolution (VGA) cameras, and high-end or low-end FPGAs. It is also robust under various conditions, such as daytime, night time, and on rainy nights, and is adaptable to various countries' speed limit traffic sign systems. The speed limit traffic sign candidates on each grayscale video frame are detected through two simple computational stages using global luminosity and local pixel direction. Pipeline implementation using results-sharing on overlap, application of a RAM-based shift register, and optimization of scan window sizes results in a small but high-performance implementation. The proposed system matches the processing speed requirement for a 60 fps system. The speed limit traffic sign recognition system achieves better than 98% accuracy in detection and recognition, even under difficult conditions such as rainy nights, and is implementable on the low-end, low-cost Xilinx Zynq automotive Z7020 FPGA.

• Journal of Korean Society of Transportation
• /
• v.14 no.3
• /
• pp.91-125
• /
• 1996

The purpose of this paper is comparatively to evaluate the confidence of Vehicle-Detector informations for various detectors in order to test to be possible the application of these to real time traffic signal control. The detectors which are tested for this study are Circle-Shaped Loop, Ultrasonic, Microwave and Image detector. The tested items for each detectors are traffic volume, degree of saturation for through and left turn movement, speed and queue length, etc. These items for each are tested at the field according to several situations, such as dry day, raining day, night and daytime. The result of these tests are performed comparative analysis and statistical examination in order to increase the confidence of the experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.11
• /
• pp.2078-2082
• /
• 2007

Recently, according to traffic accident statistics, traffic accidents occurring at night are as frequent as those during daytime, but their death rate is 1.5 times higher than that of daytime traffic accidents. This problem originates that the insufficient range of vision security of a driver causes the inappropriate accident confrontation. Therefore, in this paper, a microcontroller-based digital control method for the superior performance in headlight system is presented for optimal control that can adapt complex transient state, steady state and various environments. Specially in vehicles# headlight, its fundamental purpose is to implement the artificial headlight system which automatically controls the lighting patterns most adaptive to driving, road and weather conditions. Therefore we aimed at the development of headlight system, focused on the implementation of an artificial vehicle, of more advanced convenience and safety for drivers.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.18 no.4
• /
• pp.323-330
• /
• 2012

Manila Bay is home to the Port of Manila with three harbors: North Harbor, South Harbor and MICT(Manila International container Terminal). There is an adjacent fishing port to the north and another port across the Bay, the Limao Port. This study focuses on the volume of traffic movement in the Bay area taken from Manila VTMS raw data of the arrival and departure movements only. It is a two-year period of study of 2010 and 2011 traffic volume. It divides the data according to their numbers; to their sizes measured in gross tons; to the time of vessels' movements, whether daytime or night-time; and to each voyage trade: domestic or foreign. Quantitative values are calculated from the raw data based on the whole population of the two-year period. The results are illustrated by tables and graphs. Statistical measures are applied to determine the spread and frequencies of the data and test any significance from the hypotheses. These are shown in the tabulated form and interpreted to give a better picture of the frequency and volume of traffic. In the end, a summary is offered where it is hoped that this paper will propel further studies of improving the safety behavior in the premier port of the country.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.6
• /
• pp.697-702
• /
• 2018

Recently, the number of private cars has increased sharply due to the increase in national income. The sudden increase in the number of vehicles in limited territory has caused serious traffic congestion and the traffic congestion cost wasted on the road due to such traffic congestion is increasing every year. To solve this problem, we propose a traffic signal control system using image processing. In this paper, we use the camera installed at the intersection to measure the amount of traffic flowing in and out of each road simultaneously. We propose a traffic signal control system that can prevent traffic congestion before it happens. In the case of applying the traffic signal control system proposed in this paper to the daytime, the traffic volume could be measured accurately. However, the result of the experiment with the night-time general camera and the headlight with the infrared camera at the night-time of 72.8% was 86.6%.

• Journal of the Korean Society of Safety
• /
• v.23 no.6
• /
• pp.171-177
• /
• 2008

As the risk of traffic accidents caused by mists emerged as a social problem, recently safety facilities to be prepared for mists are being actively installed when designing roads. But in some part, the facilities are being installed imprudently without analyzing the extent of occurrences of mists that would increase the risk of traffic accidents and appropriate countermeasures against the occurrences of mists are not being suggested. For that reason, in this study, first questionnaire surveys were executed on road users in order to draw the factors affecting the traffic accidents caused by mists, a mist traffic accident predicting model was developed and an accident seriousness determining model that can determine accident seriousness was developed. In this way, by extracting major factors affecting mist traffic accidents to grasp risk factors in roads to be caused by mists, safety of roads can be enhanced and traffic accidents in road operations can be decreased. As the affecting factors influencing mist traffic accidents, were extracted sightable distances, durations of mists and whether daytime or nighttime as major factors and the plan to install the facilities for the prevention of mist traffic accidents was suggested to prevent the traffic accidents to be caused by those factors and also the plan to operate roads considering sightable distances was suggested to solve the problem of insufficient sightable distances to be caused by mists was suggested. It is judged that the road safety in the areas where mists occur can be improved through foregoing methods.