• Journal of Auto-vehicle Safety Association
• /
• v.11 no.1
• /
• pp.7-16
• /
• 2019

There are trying to reduce damage from automobile accident in many countries. In many automobile companies, there have been active study on development of ADAS (Advanced Driver Assistance Systems) for commercialization, in order to reduce damage from automobile accident. ADAS is the system providing convenience and safeness for drivers. Generally, ADAS is composed of ACC (Adaptive Cruise Control), LKAS (Lane Keeping Assist System), and AEB (Autonomous Emergency Braking). AEB of the ADAS, it is an autonomous emergency braking system and it senses potential collide and avoids or degrades it. Therefore AEB plays a significant role in reducing automobile accident rate. However, AEB safety evaluation method is not established not yet. For this reason, this study suggests safety evaluation scenarios with adding cut-in, sensor malfunctioning scenario that scenario domestic street conditions considered as well as original standard AEB scenario of Euro NCAP for establishment of safety evaluation method of AEB. And verifying validity of suggested scenario by comparing the calculated values of the theoretical formulas presented in the previous study with results of the actual vehicle test.

• International Journal of Computer Science & Network Security
• /
• v.24 no.8
• /
• pp.14-20
• /
• 2024

Traffic sign recognition is an essential feature of intelligent transportation systems and Advanced Driver Assistance Systems (ADAS), which are necessary for improving road safety and advancing the development of autonomous cars. This research investigates the incorporation of the YOLOv9 model into traffic sign recognition systems, utilizing its sophisticated functionalities such as Programmable Gradient Information (PGI) and Generalized Efficient Layer Aggregation Network (GELAN) to tackle enduring difficulties in object detection. We employed a publically accessible dataset obtained from Roboflow, which consisted of 3130 images classified into five distinct categories: speed_40, speed_60, stop, green, and red. The dataset was separated into training (68%), validation (21%), and testing (12%) subsets in a methodical manner to ensure a thorough examination. Our comprehensive trials have shown that YOLOv9 obtains a mean Average Precision (mAP@0.5) of 0.959, suggesting exceptional precision and recall for the majority of traffic sign classes. However, there is still potential for improvement specifically in the red traffic sign class. An analysis was conducted on the distribution of instances among different traffic sign categories and the differences in size within the dataset. This analysis aimed to guarantee that the model would perform well in real-world circumstances. The findings validate that YOLOv9 substantially improves the precision and dependability of traffic sign identification, establishing it as a dependable option for implementation in intelligent transportation systems and ADAS. The incorporation of YOLOv9 in real-world traffic sign recognition and classification tasks demonstrates its promise in making roadways safer and more efficient.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.3
• /
• pp.219-230
• /
• 2023

With the development of autonomous driving technology, as the use of software in vehicles increases, the complexity of the system increases and the difficulty of development increases. Developments that meet ISO 26262 must be carried out to reduce the malfunctions that may occur in vehicles where the system is becoming more complex. ISO 26262 for the functional safety of the vehicle industry proposes to consider functional safety from the design stage to all stages of development. Specifically at the software level, the requirements to be complied with during development and the requirements to be complied with during verification are defined. However, it is not clearly expressed about specific design methods or development methods, and it is necessary to supplement development guidelines. The importance of analysis and verification of requirements is increasing due to the development of technology and the increase of system complexity. The vehicle industry must carry out developments that meet functional safety requirements while carrying out various development activities. We propose a process that reflects the perspective of system engineering to meet the smooth application and developmentrequirements of ISO 26262. In addition, the safety analysis/verification FMEA processforthe safety of the proposed ISO 26262 function was conducted based on the FCAS (Forward Collision Avoidance Assist System) function applied to autonomous vehicles and the results were confirmed. In addition, the safety analysis/verification FMEA process for the safety of the proposed ISO 26262 function was conducted based on the FCAS (Forward Collision Avoidance Assist System) function applied to the advanced driver assistance system and the results were confirmed.

• Journal of Korean Society for Geospatial Information Science
• /
• v.25 no.2
• /
• pp.21-29
• /
• 2017

For the efficient and stable operation of autonomous vehicles or advanced driver assistance systems being actively studied nowadays, it is important to determine the positions of the vehicle accurately and economically. A satellite based navigation system is mainly used for positioning, but it has a limitation in signal blockage areas. To overcome this limitation, sensor fusion methods including additional sensors such as an inertial navigation system have been mainly proposed but the high sensor cost has been a problem. In this work, we develop a vehicle position estimation algorithm using in-vehicle sensors and a low-cost imaging sensor without any expensive additional sensor. We determine the vehicle positions using the velocity and yaw-rate of a car from the in-vehicle sensors and the position and attitude of the camera based on the single photo resection process. For the evaluation, we built a prototype system, acquired test data using the system, and estimated the trajectory. The proposed algorithm shows the accuracy of about 40% higher than an in-vehicle sensor only method.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.110-123
• /
• 2019

Traffic data is the most basic element necessary for transportation planning and traffic system operation. Recently, a method of estimating traffic flow characteristics using distance to a leading vehicle measured by an ADAS camera has been attempted. This study investigated the feasibility of the ADAS vehicle reflecting the distance error of image-based vehicle identification technology as a means to estimate the traffic flow through the normalized root mean square error (NRMSE) based on the number of lanes, traffic demand, penetration rate of probe vehicle, and time-space estimation area by employing the microscopic simulation model, VISSIM. As a result, the estimate of low density traffic flow (i.e., LOS A, LOS B) is unreliable due to the limitation of the maximum identification distance of ADAS camera. Although the reliability of the estimates can be improved if multiple lanes, high traffic demands, and high penetration rates are implemented, artificially raising the penetration rates is unrealistic. Their reliability can be improved by extending the time dimension of the estimation area as well, but the most influential one is the driving behavior of the ADAS vehicle. In conclusion, although it is not possible to accurately estimate the traffic flow with the ADAS camera, its applicability will be expanded by improving its performance and functions.

• Journal of Broadcast Engineering
• /
• v.26 no.2
• /
• pp.155-166
• /
• 2021

Most object detection algorithms are studied based on RGB images. Because the RGB cameras are capturing images based on light, however, the object detection performance is poor when the light condition is not good, e.g., at night or foggy days. On the other hand, high-quality infrared(IR) images regardless of weather condition and light can be acquired because IR images are captured by an IR sensor that makes images with heat information. In this paper, we performed the object detection algorithm based on the compression ratio in RGB and IR images to show the detection capabilities. We selected RGB and IR images that were taken at night from the Free FLIR Thermal dataset for the ADAS(Advanced Driver Assistance Systems) research. We used the pre-trained object detection network for RGB images and a fine-tuned network that is tuned based on night RGB and IR images. Experimental results show that higher object detection performance can be acquired using IR images than using RGB images in both networks.