• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.6D
• /
• pp.553-560
• /
• 2010

This study examined the factors influencing the number of enforcement cases on traffic signal violation. The study collected enforcement data on traffic signal violation by multi-functional unmanned cameras across the Daegu metropolitan area, and analyzed the data to determine correlations among various factors including physical dimensions and engineering characteristics of the roadway as to how they would influence the number of violations. The resulting analysis provided a general model that assesses applicability for multi-functional unmanned cameras, and further shed helpful insights on efficient utilization of such traffic signal enforcement equipments in terms of installation thresholds and location. By identifying violation-prone features and characteristics and subsequent enforcement considerations, this research also supports safety efforts in reducing the number of traffic accidents as well.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.141-143
• /
• 2022

This paper presented a new technology to identify traffic violations of motorbike riders by detecting the traffic signal using You Only Look Once (YOLO) object detection. The hardware module that is mounted on the front of the motorbike consists of Raspberry Pi with a camera to run the YOLO object detection, a GPS module to acquire the motorcycle's coordinate, and a LoRa communication module to send the data to a cloud DB. The main goal of the software is to determine whether a motorbike has violated a traffic signal. This paper proposes a function to recognize the red traffic signal colour with its movement inside the camera angle and determine that the traffic signal violation happens if the traffic signal is moving to the right direction (the rider turns left) or moving to the top direction (the riders goes straight). Furthermore, if a motorbike rider is violated the signal, the rider's personal information (name, mobile phone number, etc), the snapshot of the violation situation, rider's location, and date/time will be sent to a cloud DB. The violation information will be delivered to the driver's smartphone as a push notification and the local police station to be used for issuing violation tickets, which is expected to prevent motorbike riders from violating traffic signals.

• Korean Journal of Culture and Social Issue
• /
• v.9 no.spc
• /
• pp.15-34
• /
• 2003

The present authors had conducted several researches(parking violation, traffic signal violation, speed violation, drunk-driving) on driving behaviors of the Korean people focused on cultural psychological perspective. This paper was designed to summarize these previous results. Although each research had dealt with different violation behaviors on driving, there were lots of similarities on the basis of violation. The results reveal the following rationale for incurring violation behaviors. First, most people reported that they violated the rule to pursuit short-term benefit. Second, the violators' psychological characteristics are described in terms of self-centered and self-justification. In addition, the respondents have justified their violated behaviors since the outcome is disadvantageous for the drivers. Furthermore, the violators' are found to possess a permissive attitude toward the other violators'. Finally, the implications of these studies were proposed. All of these findings were discussed in relation to the Korean culture.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.1
• /
• pp.424-430
• /
• 2021

Determining the cause of a traffic signal violation is difficult if the drivers' claims are contradictory. In this study, the process of identifying signal violations using a simulation was presented based on cases. First, statements from the driver or witness whose cause of the signal violation is unclear were excluded. Second, the final position, final location, damaged area, steering status, braking status, and road surface traces of the vehicle were collected. The impact point was investigated from the stop line. Third, simulation data were modified and entered until the collision situation of the accident vehicle and the final stop position were met. Fourth, if the simulation results were consistent with the crash situation, the facts were verified by cross-validation to conform to the driver's statement. The results of the simulation showed that the Lexus entered the left turn signal in the intersection at approximately 55 km/h. In comparison, the Sonata driver saw the vehicle straight ahead at the intersection, entered the 72 km/h intersection, and collided with the Lexus. Therefore, the Sonata was identified as a signal violation, and the claims of the Sonata driver, witnesses, and police were contradictory.

• Journal of Korean Society of Transportation
• /
• v.27 no.3
• /
• pp.111-118
• /
• 2009

Factors causing traffic accidents are various and traffic law violations can be among them. The efforts to increase traffic law obedience rates of drivers are common in many other countries to reduce traffic accidents, and one of generally applied methods is to increase the amounts of violation fines. Expensive levels of traffic law violation fines could have drivers choose "obey the law" in their decision-making stages since they are economically better-off by following the law. In this sense, this study has developed an economic model to verify whether the current levels of the traffic violation fines of Korea are effective for drivers to choose "obey-the-law" decisions. Speed violations and traffic signal violations have been selected for the case study to verify the relationships between "expected probabilities of being-caught" and "levels of violations fines".

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.115.5-115
• /
• 2002

In this paper, we introduce a system that detects all kinds of violations at a street intersection such as red light running, speed violation, stop line violation and lane violation by tracking individual vehicles. Two cameras are used for defecting violations. One is an analog camera for real-time tracking and the other is a digital camera for license plate reading. This system is connected to the traffic signal system controller and monitors the red, arrow, yellow and green phases of an approach. Two loops in the road are used to detect vehicle approach and speed. The system takes pictures of all vehicles passing a second loop and tracks the vehicles until they go out a street intersection...

• Journal of the Korean Society of Safety
• /
• v.23 no.6
• /
• pp.164-170
• /
• 2008

This research was verified detection way of intercept vehicles and performance evaluation after system installation using image detector as detection way of ground installation. By image recognition algorithm was on the trace of moving orbit of violation vehicles for detection way of intercept vehicles. When moving orbit is located special site, utilized geometric image calibration and DC-notch filter. These are cognitive system of license plate by making signal. Then, Bright Evidence Detection and Dark Evidence Detection were applied to after mixing. It is applied to way of Backward tracking for detection way of intercept vehicles. After the field evaluation of developed system, it should be analyzed the more high than recognition rate of minimum standards 80%. It should rise in the estimation of the site applicability is highly from now.

• Journal of Korean Society of Transportation
• /
• v.33 no.5
• /
• pp.441-448
• /
• 2015

This study aims to suggest a reasonable signal operation method for right-turn traffic management. It was found that the right-turn vehicle supplementary signal is currently operated without clear regulations or criteria. It was also analyzed that right-turn supplementary signals are used without consistency, there is a risk of traffic accidents due to the discordance between supplementary signals and traffic signals of forward vehicles, there is a lack of basis for prohibition of a right turn when right-turn vehicle's supplementary signal is red and the flashing red signal is used in a different sense from the law. In order to see the effect of the installed right-turn vehicle supplementary signals on traffic signal violation, a field investigation was conducted. As the result, there was a high proportion of signal violation on the approach lane with right-turn supplementary signals and this means that right-turn supplementary signals hardly influenced the reduction in proportion of signal violation during a right turn. Additionally, a survey was carried out to see if there were differences in driver's interpretation of traffic signals depending on the installation of right-turn supplementary signals. As the result of the survey, there were no differences in interpretation of traffic signals depending on the installation of right-turn supplementary signals or the types of right-turn supplementary signals. A right turn when the signal was red did not lead to serious traffic accidents, so it is thought that there should be a careful consideration of a total ban on a right turn when the signal is red, in order to prevent driver's confusion due to the change of the signal system. Unless there is a disturbance to cars and pedestrians after a temporary stop when the signal is red, there is a need to specify that vehicles must stop temporarily in the Road Traffic Act to facilitate a right turn. What this study finally suggested is to use tri-colored arrow signals for right-turn car supplementary signals to convey a signal to a driver clearly.

• Proceedings of the IEEK Conference
• /
• 2001.06e
• /
• pp.147-150
• /
• 2001

This paver has presented the architecture and function of the traffic signal enforcement system to detect and capture a image of the violating car in the street intersection. Also in the paper, the algorithm and method of detecting the violation car have been presented and the microwave detection method has been explained. And then this paper has showed the operation software interface for system and presented the experiment data carried out in the field.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.5
• /
• pp.444-450
• /
• 2013

For intelligent vehicle technology, it is very important to recognize the states of around vehicles and assess the collision risk for safety driving of the vehicle. Specifically, it is very fatal the collision with the vehicle coming from opposite direction. In this paper, a centerlane violation prediction method is proposed. Only radar signal based prediction makes lots of false alarm cause of measurement noise and the false alarm can make more danger situation than the non-prediction situation. We proposed the novel prediction method using IMM algorithm and fuzzy logic to increase accuracy and get rid of false positive. Fuzzy logic adjusts the radar signal and the IMM algorithm appropriately. It is verified by the computer simulation that shows stable prediction result and fewer number of false alarm.