• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.5
• /
• pp.325-333
• /
• 2015

Vision based night-time vehicle detection has been an emerging research field in various advanced driver assistance systems(ADAS) and automotive vehicle as well as automatic head-lamp control. In this paper, we propose night-time vehicle detection method based on multi-class support vector machine(SVM) that consists of thresholding, labeling, feature extraction, and multi-class SVM. Vehicle light candidate blobs are extracted by local mean based thresholding following by labeling process. Seven geometric and stochastic features are extracted from each candidate through the feature extraction step. Each candidate blob is classified into vehicle light or not by multi-class SVM. Four different multi-class SVM including one-against-all(OAA), one-against-one(OAO), top-down tree structured and bottom-up tree structured SVM classifiers are implemented and evaluated in terms of vehicle detection performances. Through the simulations tested on road video sequences, we prove that top-down tree structured and bottom-up tree structured SVM have relatively better performances than the others.

• Structural Monitoring and Maintenance
• /
• v.9 no.1
• /
• pp.43-57
• /
• 2022

One of the instances which demand structural engineer's greatest attention and upgradation is the changing live load requirement in bridge design code. The challenge increases in developing countries as the pace of infrastructural growth is being catered by the respective country codes with bigger and heavier vehicles to be considered in the design. This paper presents the case study of India where Indian Roads Congress (IRC) codes in its revised version from 2014 to 2017 introduced massive Special vehicle (SV) around 40 m long and weighing 3850 kN to be considered in the design of road bridges. The code does not specify the minimum distance between successive special vehicles unlike other loading classes and hence the consequences of it form the motivation for this study. The effect of SV in comparison with Class 70R, Class AA, Class A, and Class B loading is studied based on the maximum bending moment with moving load applied in Autodesk Robot Structural Analysis. The spans considered in the analysis varied from 10 m to 1991 m corresponding to the span of Akashi Kaikyo Bridge (longest bridge span in the world). A total of 182 analyses for 7 types of vehicles (class B, class A, class 70R tracked, class 70R wheeled, class AA tracked, AA wheeled, and Special vehicle) on 26 different span lengths is carried out. The span corresponding to other vehicles which would equal the bending moment of a single SV is presented along with a comparison relative to Standard Uniformly Distributed Load. Further, the results are presented by introducing a new parameter named Intensity Factor which is proven to relate the effect of axle spacing of vehicle on the normalized bending moment developed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.68-70
• /
• 2021

The wind power generators installed in the Jeju area have already exceeded the supply in the Jeju area and are being thrown away. Accordingly, the government is conducting research on installing a 2MWh-class ESS(energy storage system) through a technology development project to charge wasted power and use it in an electric vehicle charging station. In this paper, in order to stably install a 2MWh class ESS, the electric vehicle charging model and ESS discharge model were modeled and simulated using Matlab Simulink. Through simulation, it was verified that the 2MWh class ESS operates stably in various scenarios.

• Journal of Aerospace System Engineering
• /
• v.14 no.1
• /
• pp.68-73
• /
• 2020

This purpose of this paper was to review the development trend of the VTOL MAVs with a ducted propellant that can fly like the VTOL at intermediate and high speeds, hovering, landing, and lifting off vertically over urban areas, warships, bridges, and mountainous terrains. The MAV differs in flight characteristics from helicopters and fixed wings in many respects. In addition to enhancing thrust, the duct protects personnel from accidental contact with the spinning rotor. The purpose of the U.S. Army FCS and DARPA's OAV program is spurring development of a the VTOL ducted MAV. Today's MAVs are equipped with video/infrared cameras to hover-and-stare at enemies hidden behind forests and hills for approximately one hour surveillance and reconnaissance. Class-I is a VTOL ducted MAV developed in size and weight that individual soldiers can store in their backpacks. Class-II is the development of an organic VTOL ducted fan MAV with twice the operating time and a wider range of flight than Class-I. MAVs will need to develop to perch-and-stare technology for lengthy operation on the current hover-and-stare. The near future OAV's concept is to expand its mission capability and efficiency with a joint operation that automatically lifts-off, lands, refuels, and recharges on the vehicle's landing pad while the manned-unmanned ground vehicle is in operation. A ducted MAV needs the development of highly accurate relative position technology using low cost and small GPS for automatic lift-off and landing on the landing pad. There is also a need to develop a common command and control architecture that enables the cooperative operation of organisms between a VTOL ducted MAV and a manned-unmanned ground vehicle.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.12 no.2
• /
• pp.236-247
• /
• 2009

In Korea, the driving system restriction criteria is strictly applied(gross weight 400kN, axial load 100kN). Especially after the Seoungsu Bridge accident, safety factor has been strictly applied. The Safety factor is applied to the cumulative results for each steps like design, construction, maintenance of the Bridge. Because of it, the bridge is undervalued compared to its capacity. So, this generates loss for both private and military sector(eg. logistical delays, structural damage, etc.). But analyzing data from many existing researches we have confirmed that the military heavy vehicle may pass through the first class bridges. In consequence, this study have focused on determining whether HETS vehicles can pass over the first class bridge, without safety issues, using MIDAS structural analysis program. The results have confirmed that the military heavy vehicle may pass over the bridge.

• Journal of Aerospace System Engineering
• /
• v.9 no.1
• /
• pp.1-6
• /
• 2015

A critical speed analysis of oxidizer pump was peformed for a 7 ton class liquid rocket engine as the third stage engine of the Korea Space Launch Vehicle II. Based on the previously developed experimental 30 ton class turbopump and presently developing 75 ton class turbopump for the first and second stage rocket engine of Korea Space Launch Vehicle II, a layout and configuration of the 7 ton class turbopump rotor assembly are determined. A ball bearing stiffness analysis and rotordynamic analysis are performed for both of the bearing unloaded condition and loaded condition. Structural flexibility of the oxidizer pump casing is also included to predict critical speeds. From the numerical analysis, it is confirmed that the rotor system acquires sufficient separate margin of critical speed as a sub-critical rotor even though decrease of critical speed due to the casing structural flexibility.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.2
• /
• pp.361-368
• /
• 2019

This paper is a study on integrated air-conditioning system for 1-ton class commercial vehicle based on electric vehicle. In the case of an electric commercial vehicle, since the opening and closing of the door is frequently performed in order to get in and out of the cargo, the heat loss largely occurs. Therefore, the heating and cooling load is required to be larger than the electric vehicle. As a result, the energy consumed by the heating and cooling system is larger than the passenger electric car in order to satisfy the heat comfort required by passengers. In order to overcome these disadvantages, we performed research using an efficient integrated air conditioning system. Finally, the design and analysis of a heat pump system for heating and a electrical compressor for cooling need to be proceed to develop a high-efficiency air conditioning system for improving the commerciality of 1 ton-class electric trucks and expanding the industrial ecosystem in the electric truck sector.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.6
• /
• pp.194-210
• /
• 2022

The user-centered EV charging infrastructure construction policy the government is aiming for can increase convenience for electric vehicle users and bring new electric vehicle users into the market. This study was conducted to provide an in-depth understanding of the charging behaviors of actual electric vehicle users, which can be used as basic information for the electric vehicle charging infrastructure. Based on charging diary data collected for a week, the charging of electric vehicles was analyzed on a daily and weekly basis, and sequence analysis and latent class analysis were used. As a result, five daily charging profiles and four weekly charging profiles were identified, which are expected to contribute to revitalizing the electric vehicle market by providing key information for decision-making by potential electric vehicle users as well for establishing user-centered charging infrastructure policies in the future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2098-2114
• /
• 2021

Light intensity variation is one of the key factors which affect the accuracy of vehicle face re-identification, so in order to improve the robustness of vehicle face features to light intensity variation, a Nonnegative Matrix Factorization model with the constraint of image acquisition time difference is proposed. First, the original features vectors of all pairs of positive samples which are used for training are placed in two original feature matrices respectively, where the same columns of the two matrices represent the same vehicle; Then, the new features obtained after decomposition are divided into stable and variable features proportionally, where the constraints of intra-class similarity and inter-class difference are imposed on the stable feature, and the constraint of image acquisition time difference is imposed on the variable feature; At last, vehicle face matching is achieved through calculating the cosine distance of stable features. Experimental results show that the average False Reject Rate and the average False Accept Rate of the proposed algorithm can be reduced to 0.14 and 0.11 respectively on five different datasets, and even sometimes under the large difference of light intensities, the vehicle face image can be still recognized accurately, which verifies that the extracted features have good robustness to light variation.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.1D
• /
• pp.45-51
• /
• 2010

Traffic volume is essential data for traffic control or maintenance and rehabilitation planning. The volume especially with respect to the type of vehicles can facilitate to those road operations. In this research, a method for vehicle classification was developed using skewed sensors which can generate traffic signatures. In order to characterize vehicle types, the method investigates whether the second axle of each vehicle consists of dual tires. The presence of dual tire is determined by the discriminate function obtained from discriminant analysis. The validation using 1,878 vehicles recorded from a highway using a CCTV camera indicated significantly accurate results: 96.92% for class 1, 82.91% for class 3 and 79.13% for class 4.