• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.317-318
• /
• 2023

본 논문에서는 CNN(Convolutional Neural Network)을 활용하여 자율주행 자동차가 각 국가별 교통 규칙 및 도로 표시를 이해하고 정확한 주행을 할 수 있도록, Deep Neural Network 시스템을 설계하고 구현하는 방법을 제안한다. 연구 방법으로는 한국도로교통공단(koroad)에서 제공하는 교통안전표지 일람표 이미지를 학습하여, 차량이 자율주행을 하기 위해 요구되는 표지판을 인식할 수 있도록 하였다. 본 논문에서 설계한 학습 시스템으로 도로교통표지판의 인식에 성공했으며, 이를 통해 자율주행차량이 표지판을 인식할 수 있으며, 시각장애인 및 고령운전자를 위한 지원 역시 가능하다고 사료된다.

• Journal of the Korean Society of Safety
• /
• v.33 no.3
• /
• pp.71-76
• /
• 2018

The purpose of this study is to analyze the factors affecting the roundabout accidents near schools. This study gives particular attentions discussing characteristics by pedestrian accident severity using the ordered logit models. In pursuing the above, 63 roundabouts installed before 2014 are surveyed for modeling. the traffic accident data from 2014 to 2016 are collected from TAAS data set of Road Traffic Authority. Such 35variables explaining the accidents as environment, human, geometries, school and roundabout factor are selected from literature reviews. The main results are as follows. First, the ordered logit models (${\rho}^2$ of 0.272, $x^2$ of 24.723) which is statistically significant have been developed. Second, environment factor variable is analyzed to be day or night ($X_1$ ), human factor variables are evaluated to be driver gender($X_4$), older driver($X_5$), pedestrian gender($X_7$) and children pedestrian($X_8$ ). Third, geometries factor variable are analyzed to be speed limit sign($X_{16}$) and median barrier($X_{21}$), school factor variables are evaluated to be hump-type crosswalk($X_{25}$), CCTV($X_{26}$) and school zone sign($X_{27}$), roundabout factor are analyzed to be roundabout sign($X_{30}$) and number of circulatory roadway lane($X_{32}$). Finally, this study could give some implications to decreasing the accidents severity at roundabout near schools.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.24 no.5
• /
• pp.898-902
• /
• 2010

This study is performed to report that oriental medical treatment was effective to the patient with piriformis syndrome after traffic accident. The patient was diagnosed as piriformis syndrome by considering clinical symptom, clinical history, physical examination, radiologic study and NCV EMG study. We applied acupuncture, herbal medicine, cupping, Chuna manipulation and exercise to the patient. After treatment, VAS decreased, and physical examination sign was disappeared. This result suggest that oriental medical treatment can be effective to piriformis syndrome.

• International Journal of Internet, Broadcasting and Communication
• /
• v.6 no.2
• /
• pp.20-24
• /
• 2014

These days the large-scale car accidents have often been occurred by overspeeding in disregard of sharp curve, foggy and freezing regions. This paper has proposed the algorithm to calculate the safety speed in real time that can protect the car accidents under these weather and road conditions using Fuzzy reasoning theory. Under raining and snowing, drivers have to slow down the traffic safety speed by 1/3 of the traffic safety speed indicated on the existing speed sign plate based on their decision. So it is difficult to calculate and then observe the safety speed. This paper has performed the simulation that provides the deivers with the optimal safety speed considering the road and weather conditions in real time to improve these problems. We have proved this method can improve more 25% than the existing one.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05b
• /
• pp.587-590
• /
• 2004

In this paper proposed a HMM(Hidden Martov Model)-based segmentation method which is able to model shadows as well as foreground and background regions. Shadow of moving objects often obstruct visual tracking. We propose an HMM-based segmentation method which classifies in real time oath objects. In the case of traffic monitoring movies, the effectiveness of the proposed method has been proven through experimental results

• Journal of IKEEE
• /
• v.18 no.4
• /
• pp.485-494
• /
• 2014

Traffic Sign Recognition(TSR) is an important element in an Advanced Driver Assistance System(ADAS). However, many studies related to TSR approaches only in normal daytime environment because a sign's unique color doesn't appear in poor environment such as night time, snow, rain or fog. In this paper, we propose a new TSR algorithm based on machine learning for daytime as well as poor environment. In poor environment, traditional methods which use RGB color region doesn't show good performance. So we extracted sign characteristics using HoG extraction, and detected signs using a Support Vector Machine(SVM). The detected sign is recognized by a decision tree based on 25 reference points in a Normalized RGB system. The detection rate of the proposed system is 96.4% and the recognition rate is 94% when applied in poor environment. The testing was performed on an Intel i5 processor at 3.4 GHz using Full HD resolution images. As a result, the proposed algorithm shows that machine learning based detection and recognition methods can efficiently be used for TSR algorithm even in poor driving environment.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.4
• /
• pp.699-708
• /
• 2021

In this paper, a steering control and speed control algorithm was presented for autonomous driving based on two vision sensors and road speed sign board. A car speed control algorithm was developed to recognize the speed sign by using TensorFlow, a deep learning program provided by Google to the road speed sign image provided from vision sensor B, and then let the car follows the recognized speed. At the same time, a steering angle control algorithm that detects lanes by analyzing road images transmitted from vision sensor A in real time, calculates steering angles, controls the front axle through PWM control, and allows the vehicle to track the lane. To verify the effectiveness of the proposed algorithm's steering and speed control algorithms, a car's prototype based on the Python language, Raspberry Pi and OpenCV was made. In addition, accuracy could be confirmed by verifying various scenarios related to steering and speed control on the test produced track.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.1
• /
• pp.251-259
• /
• 2013

This paper is aimed to introduce to a moving bollard (i.e., smart bollard) to improve the pedestrian safety along the crosswalk in the school zone as a means to physically separate pedestrians and approaching vehicles, to propose the appropriate criteria for its installation and implementation from the traffic engineering perspective, and to evaluate its effectiveness with the microscopic simulation model. The simulation results indicate that implementing the smart bollard results in the decrease of average approaching speed and traffic throughput and the most critical factors affecting its effectiveness are yellow time of the traffic signal directly associated with the location of the advance warning sign and its operation time, 5~6 seconds and 2~3 seconds, respectively.

• Journal of Korean Society of Transportation
• /
• v.26 no.1
• /
• pp.155-164
• /
• 2008

Variable Message Signs (VMS) is one of the major components for Intelligent Transport Systems (ITS) services that provides real-time traffic and incident information to drivers. The objective of this research was to develop a method determining the optimal location of VMS considering safety and driving characteristics of various drivers. A driving simulator was utilized to evaluate how drivers can safely exit to off-ramp depending on various VMS locations while information relating route diversion was provided. The binary logistic regression and factor analysis were applied in developing a probability model that predicts the success of safe off-ramp exiting. Based on the developed probability model, a method to estimate the spacing between VMS and off-ramp is suggested. It is expected that the products of this study would be utilized as a tool in determining VMS locations for ITS planners and designers.

• Journal of Korean Port Research
• /
• v.13 no.1
• /
• pp.113-122
• /
• 1999

Congestion and traffic accidents occur on the merge and diverge sections in the interchange of the freeway. Studies have been conducted to reduce the traffic delay and accidents on the merge section in the freeway since 1960s. but a study was not conducted to estimate the speed variation on the merge section construct models estimated for the speed variation and suggest the appropriate measures. The purpose of this study was to identify the traffic flow characteristics on the merge section in the freeway construct the models estimated for the speed variation on the merge section in the freeway and finally establish the appropriate measure for reduction of traffic delay and accidents on the merge section in the freeway. The following results were obtained: I) Speed variations in the urban freeway appeared to be about 3.2mph, 6.5mph and 7.4mph based on the morning peak period, afternoon peak period and 24-hours period but those in the suburban freeway appeared to be about 8.0mph, 11.1mph and 10.1mph based on the same periods respectively. So different speed reduction signs need be installed to reduce delay and accidents on the merge section in the freeway based on the areas and periods as the freeway traffic management system(FTMS). ii) These models estimated for speed variation need to be studied with the changeable message sign(CMS) technique based on the real-time data so that the traffic flow could be maximized and the traffic delay and accidents be on the merge section in the freeway as more efficient freeway traffic management system(FTMS) in the near future.