• Journal of Auto-vehicle Safety Association
• /
• v.16 no.3
• /
• pp.55-63
• /
• 2024

As autonomous driving performance, such as automatic emergency braking (AEB) and advanced driver assistance systems (ADAS), continues to improve, collision angles and occupant seating postures become more diverse, and there is a need to study how occupant injury mechanisms change depending on the type of collision. Accordingly, a representative crash test mode was derived. Using the derived crash test mode, we analyzed the crash injury mechanism according to the impact angle and the occupant's seating posture (seat back angle). Sled is a crash simulation test that applies a pulse corresponding to the vehicle body acceleration pulse generated during a collision. Sled testing has advantages in terms of cost and time compared to actual vehicle crash testing. We focus on the correlation between crash tests reflecting autonomous vehicle crash modes and Sled tests. The results obtained through this study can be used to develop new crash evaluation methods. As a result, we will present the results of an experimental study on the actual vehicle crash test Sled test method.

• Journal of Positioning, Navigation, and Timing
• /
• v.11 no.4
• /
• pp.389-395
• /
• 2022

In order to ensure reliability the high-level automated driving such as Advanced Driver Assistance System (ADAS) and universal robot taxi provided by autonomous driving systems, the operation with high integrity must be generated within the defined Operation Design Domain (ODD). For this, the position and posture accuracy requirements of autonomous driving systems based on the safety driving requirements for autonomous vehicles and domestic road geometry standard are necessarily demanded. This paper presents localization requirements for safe road driving of autonomous ground vehicles based on the requirements of the positioning system installed on autonomous vehicle systems, the domestic road geometry standard and the dimensions of the vehicle to be designed. Based on this, 4 Protection Levels (PLs) such as longitudinal, lateral, vertical PLs, and attitude PL are calculated. The calculated results reveal that the PLs are more strict to urban roads than highways. The defined requirements can be used as a basis for guaranteeing the minimum reliability of the designed autonomous driving system on roads.

• International Journal of Contents
• /
• v.14 no.1
• /
• pp.39-44
• /
• 2018

Today, cars have developed into intelligent automobiles that combine advanced control equipment and IT technology to provide driving assistance and convenience to users. These vehicles provide infotainment services to the driver, but this does not improve the safety of the driver. Accordingly, V2X communication, which forms a network between a vehicle and a vehicle, between a vehicle and an infrastructure, or between a vehicle and a human, is drawing attention. Therefore, various techniques for improving channel estimation performance without changing the IEEE 802.11p standard have been proposed, but they do not satisfy the packet error rate (PER) performance required by the C-ITS service. In this paper, we analyze existing channel estimation techniques and propose a new channel estimation scheme that achieves better performance than existing techniques. It does this by applying the updated matrix for the data pilot symbol to the construct data pilot (CDP) channel estimation scheme and by further performing the interpolation process in the frequency domain. Finally, through simulations based on the IEEE 802.11p standard, we confirmed the performance of the existing channel estimation schemes and the proposed channel estimation scheme by coded PER.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.3
• /
• pp.60-64
• /
• 2022

In the automotive industry, the development of automobiles to meet safety requirements is becoming increasingly complex. This is because quality evaluation agencies in each country are continually strengthening new safety standards for vehicles. Among these various requirements, collision safety must be satisfied by controlling airbags, seat belts, etc., and can be defined as post-crash safety. Apart from this safety system, the Advanced Driver Assistance Systems (ADAS) use advanced detection sensors, GPS, communication, and video equipment to detect the hazard and notify driver before the collision. However, research to improve passenger safety in case of an accident by using the sensor of active safety represented by ADAS in the existing passive safety is limited to the level that utilizes the sudden braking level of the FCA (Forward Collision-avoidance Assist) system. Therefore, this study aims to develop logic that can improve passenger protection in case of an accident by using ADAS information and driving information secured before a collision. The proposed logic was constructed based on LSTM deep learning techniques and trained using crash test data.

• Journal of IKEEE
• /
• v.20 no.4
• /
• pp.351-360
• /
• 2016

Recently, machine learning algorithms, especially deep learning-based algorithms, have been receiving attention due to its high classification performance. Among the algorithms, Convolutional Neural Network(CNN) is known to be efficient for image processing tasks used for Advanced Driver Assistance Systems(ADAS). However, it is difficult to achieve real-time processing for CNN in vehicle embedded software environment due to the repeated operations contained in each layer of CNN. In this paper, we propose a hardware accelerator which enhances the execution time of CNN by parallelizing the repeated operations such as convolution. Xilinx ZC706 evaluation board is used to verify the performance of the proposed accelerator. For $36{\times}36$ input images, the hardware execution time of CNN is 2.812ms in 100MHz clock frequency and shows that our hardware can be executed in real-time.

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.358-367
• /
• 2017

Advanced Driver Assistance Systems(ADAS), such as Front Collision Warning System (FCWS) are currently being developed. FCWS require high processing speed because it must operate in real time while driving. In addition, a low-power system is required to operate in an automobile embedded system. In this paper, FCWS is implemented in CPU-FPGA architecture in embedded system to enable real-time processing. The lane detection enabled the use of the Inverse Transform Perspective (IPM) and sliding window methods to operate at fast speed. To detect the vehicle, a Convolutional Neural Network (CNN) with high recognition rate and accelerated by parallel processing in FPGA is used. The proposed architecture was verified using Intel FPGA Cyclone V SoC(System on Chip) with ARM-Core A9 which operates in low power and on-board FPGA. The performance of FCWS in HD resolution is 44FPS, which is real time, and energy efficiency is about 3.33 times higher than that of high performance PC enviroment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.12
• /
• pp.5669-5684
• /
• 2018

The new mobile edge network architecture has been required for an increasing amount of traffic, quality requirements, advanced driver assistance system for autonomous driving and new cloud computing demands on highway. This article proposes a hierarchical cloud computing architecture to enhance performance by using adaptive data load distribution for buses that play the role of edge computing server. A vehicular dynamic cloud is based on wireless architecture including Wireless Local Area Network and Long Term Evolution Advanced communication is used for data transmission between moving buses and cars. The main advantages of the proposed architecture include both a reduction of data loading for top layer cloud server and effective data distribution on traffic jam highway where moving vehicles require video on demand (VOD) services from server. Through the description of real environment based on NS-2 network simulation, we conducted experiments to validate the proposed new architecture. Moreover, we show the feasibility and effectiveness for the connected car media service on highway.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.12 no.2
• /
• pp.113-120
• /
• 2017

In this paper, we present a night-time vehicle detection method using CNN (Convolutional Neural Network) classification. The camera based night-time vehicle detection plays an important role on various advanced driver assistance systems (ADAS) such as automatic head-lamp control system. The method consists mainly of thresholding, labeling and classification steps. The classification step is implemented by existing CIFAR-10 model CNN. Through the simulations tested on real road video, we show that CNN classification is a good alternative for night-time vehicle detection.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.25 no.2
• /
• pp.219-226
• /
• 2017

This paper addresses the effective and quantitative image DB construction for the development of front looking camera systems. The automotive industry has expanded the capability of front camera solutions that will help ADAS(Advanced Driver Assistance System) applications targeting Euro NCAP function requirements. These safety functions include AEB(Autonomous Emergency Braking), TSR(Traffic Signal Recognition), LDW(Lane Departure Warning) and FCW(Forward Collision Warning). In order to guarantee real road safety performance, the driving image DB logged under various real road conditions should be used to train core object classifiers and verify the function performance of the camera system. However, the driving image DB would entail an invalid and time consuming task without proper guidelines. The standard working procedures and design factors required for each step to build an effective image DB for reliable automotive front looking camera systems are proposed.

• Korean Journal of Computational Design and Engineering
• /
• v.19 no.3
• /
• pp.272-280
• /
• 2014

Most of the car navigation systems pzrovide 2D or 3D virtual map-based driving guidance. One of the important issues is how to reduce cognitive burden to the driver who should interpret the abstracted information to real world driving information. Recently, an augmented reality (AR)-based navigation is considered as a new way to reduce cognitive workload by superimposing guidance information into the real world scene captured by the camera. In particular, head-up display (HUD) is popular to implement AR navigation. However, HUD is too expensive to be set up in most cars so that the HUD-based AR navigation is currently unrealistic for navigational assistance. Meanwhile, smartphones with advanced computing capability and various sensors are popularized and also provide navigational assistance. This paper presents a research on cognitive effect and responsiveness of an AR navigation by a comparative study with a conventional virtual map-based navigation on the same smartphone. This paper experimented both quantitative and qualitative studies to compare cognitive workload and responsiveness, respectively. The number of eye gazing at the navigation system is used to measure the cognitive effect. In addition, questionnaires are used for qualitative analysis of the responsiveness.