• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.610-630
• /
• 2020

A large number of people suffered from traffic accidents each year, so people pay more attention to traffic safety. However, the traditional methods use laser sensors to calculate the vehicle distance at a very high cost. In this paper, we propose a method based on deep learning to calculate the vehicle distance with a monocular camera. Our method is inexpensive and quite convenient to deploy on the mobile platforms. This paper makes two contributions. First, based on Light-Head RCNN, we propose a new vehicle detection framework called Light-Car Detection which can be used on the mobile platforms. Second, the planar homography of projective geometry is used to calculate the distance between the camera and the vehicles ahead. The results show that our detection system achieves 13FPS detection speed and 60.0% mAP on the Adreno 530 GPU of Samsung Galaxy S7, while only requires 7.1MB of storage space. Compared with the methods existed, the proposed method achieves a better performance.

• Proceedings of the KSR Conference
• /
• 2007.05a
• /
• pp.99-108
• /
• 2007

The bi-modal tram guided by the magnetic guidance system has two car-bodies and three axles. Each axle of the vehicle has an independent suspension to lower the floor of the car and improve ride quality. The turning radius of the vehicle may increase as a consequence of the long wheel base. Therefore, the vehicle is equipped with the All-Wheel-Steering(AWS) system for safe driving on a curved road. Front and rear axles should be steered in opposite directions, which means a negative mode, to minimize the turning radius. On the other hand, they also should be steered in the same direction, which means a positive mode, for the stopping mode. Moreover, only the front axle is steered for stability of the vehicle upon high-speed driving. In summary, steering angles and directions of the each axle should be changed according to the driving environment and steering mode. This paper proposes an appropriate AWS control algorithm for stable driving of the bi-modal tram. Furthermore, a multi-body model of the vehicle is simulated to verify the suitability of the algorithm. This model can also analyze the different dynamic characteristics between 2WS and AWS.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.2
• /
• pp.196-200
• /
• 2013

In this paper, the design of PRT vehicle power supply system is discussed. Since there is no power feeding line facilities in PRT system under development, the PRT vehicle must have its own energy storage device on board. For the energy storage device, ultra-capacitor bank is applied due to its fast charging capability and long life time. Charging the Ultra-capacitor bank is performed by wireless inductive power transfer system. The capacitor bank is charged up in less than 10 seconds when the vehicle is traveling by passenger stations. In this paper the design of the ultra-capacitor bank and the wireless inductive power transfer system for the PRT vehicle are discussed. Tests are conducted for the both system and the result shows the efficiency of the wireless inductive power transfer system is higher than 80%.

• Journal of ILASS-Korea
• /
• v.23 no.4
• /
• pp.234-243
• /
• 2018

Since September 2017, a small diesel vehicle certification test mode has been enhanced from NEDC to WLTC. The main reason for the change of the certification test mode is that the certification test mode of the emission control standard of the diesel vehicle does not sufficiently reflect various driving patterns of the actual roads. Several automakers have developed after-treatment systems such as LNT, SCR, and DPF to meet enhanced emissions regulations. In this study, four small diesel cars were selected for sale in Korea, and the exhaust gas measurement test was performed in the WLTC mode, which reflects the driving characteristics of the actual roads. As a result of test, LNT vehicle exceeded Euro 6 NOx regulation and SCR vehicle satisfied Euro 6 NOx regulation. In addition, both LNT and SCR systems showed high NOX emission characteristics due to speed, RPA and Vxa. For the PN, all test vehicles were fitted with a DPF and met the Euro 6 PN regulations, with similar PN emissions results in LNT and SCR system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.529-535
• /
• 2018

The range extender vehicle runs on a mechanism that allows the small power generation engine to start in the most efficient specific operating range to charge the battery and extend the mileage. In this study, we developed a step motor type intake air supply system that replaces existing throttle body system to develop a simple low cost control logic system. The system was applied to the existing base engine, and in order to improve the performance by increasing the amount of intake air, the effect of changing the length of the intake and exhaust manifold was experimentally examined. As a result, the Type B intake air control actuator operated by one step motor showed higher performance than the Type A in all the operation region, but the performance was lower than that of the base engine due to the increase of flow resistance. To improve this, it was confirmed that the engine performance was improved at both speeds of 2200rpm and 4300rpm when the 140mm adapter was installed in the intake manifold and when the newly designed 70mm exhaust manifold was applied. Through this process, high - precision operation control was realized by connecting the generator load to the optimized engine for the range extender electric vehicle. Experimental results showed that the speed change rate was within ${\pm}2.5%$ at 2200rpm in 1st stage and 4300rpm in 2nd stage and the speed follow-up result of 610 rpm/s was obtained when the speed was increased from 2200rpm to 4300rpm.

• Journal of the Korean Society for Railway
• /
• v.15 no.4
• /
• pp.343-351
• /
• 2012

With the cooperation of many research institutes and railway companies, the next generation high speed train is under development for many years. To confirm the safety requirement of the developed high speed train, multibody dynamic analysis is implemented. Through this analysis, railway derailment and lateral guiding force simulation was evaluated according to UIC code 518 OR for international railway vehicle. Test results were compared by limit value of safety criteria. Safety evaluation results, according to international standards, would provide basic reference data of ensuring safety speed and track radius curve. The safety of the train at the maximum speed is verified by numerical analysis results.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.9
• /
• pp.4149-4155
• /
• 2013

High speed machining for higher cutting speed and feedrate lead to a increase of surface quality and material removal rate. This paper presents a study of the influence of cutting conditions on the vibration characteristics obtained by machining with face milling cutter for high speed machining. In this paper, Taguchi experimental design method which is based on orthogonal array table was applied to study vibration characteristics with high speed face milling cutter. The experimental conditions used orthogonal array of $L_{27}(3^{13})$. In this work, design and analysis of experiments is conducted to study the effects of these parameters on the vibration by using the S/N ratio, analysis of variance. Four cutting parameters namely, feed rate, champer length, cutting speed, and depth of cut were optimized with consideration of vibration characteristics.

• Journal of Korean Society of Transportation
• /
• v.26 no.3
• /
• pp.85-95
• /
• 2008

The purpose of this study is to reduce a high speed driving, it is a large scale traffic accident as the most dangerous fact on the highway. So traffic accidents related to high speed driving, a number of automated speed enforcement system has been established up to now. At present automated speed enforcement system in Korea control overspeed vehicle only in the specific spot. Because the drivers generally recognize the previous stated fact. therefore, we need speed control by new system. it is necessary to establish the automated traffic enforcement system based on the travel time speed. In conclusion, we obtain the desired results about automated traffic enforcement system based on the travel time speed. it is important that the number of traffic accidents has decreased and try to secure the safety of traffic.

• International Journal of Highway Engineering
• /
• v.14 no.6
• /
• pp.183-190
• /
• 2012

PURPOSES : The fundamental diagram provides basic information necessary in the analysis of traffic flow and highway operation. When traffic flow is congested, the density-flow points in the fundamental diagram are widely scattered and move in a stochastic manner. This paper investigates the pattern of density-flow point transitions and identifies car-following behaviors underlying the density-flow transitions. METHODS : From a microscopic analysis of 722 fundamental diagrams of NGSIM data, a total of 20 transition patterns of fundamental diagrams are identified. Prominent features of the transition patterns are explained by the behavior of the leader and follower. RESULTS : It is found out that the average speed and the speed difference between the leader and the follower critically determine the density-flow transition pattern. The density-flow path is very sensitive to the values of vehicle speed and spacing especially at low speed and high density such that most fluctuations in the fundamental diagram in the congested regime is due to the noise of speed and spacing variations. CONCLUSIONS : The result of this study suggests that the average speed, the speed difference between the leader and the follower, and the random variations of speed and spacing are dominant factors that explain the transition patterns of a fundamental diagram.

• Environmental Engineering Research
• /
• v.25 no.3
• /
• pp.366-373
• /
• 2020

The autonomous vehicles (AVs) could make a positive or negative impact on reducing mobile emissions. This study investigated the changes of mobile emissions that could be caused by large-scale adoption of AVs. The factors of road capacity increase and speed limit increase impacts were simulated using a conceptual modeling approach that combines a hypothetical speed-emission function and a traffic demand model using a virtual transportation network. The simulation results show that road capacity increase impact is significant in decreasing mobile emissions until the market share of AVs is less than 80%. If the road capacity increases by 100%, the mobile emissions will decrease by about 30%. On the other hand, driving speed limit increase impact is significant in increasing mobile emissions, and the environmentally desirable speed limit was found at around 95 km/h. If the speed limit increases to 140 km/h, the mobile emissions will increase by about 25%. This is because some vehicles begin to bypass the congested routes at high speeds as speed limit increases. Based on the simulation results, it is clear that the vehicle platooning technology implemented at reasonable speed limit is one of the AV technologies that are encouraging from the environmental point of view.