• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.169-176
• /
• 2022

With the continuous development of technologies related to 5G, artificial intelligence, and autonomous vehicle systems, standards and services for V2X and C-ITS environments are being studied a lot. BSM (basic safety message) was adopted as a standard for exchanging data between vehicles based on data collected and generated by vehicle systems in a V2V environment. In this paper, we propose a framework that can safely store BSM messages and effectively check the stored messages using Event-Sourcing and CQRS patterns. The proposed framework can securely store and manage BSM messages using hash functions. And it has the advantage of being able to check the stored BSM data in real time based on the time series and to reproduce the state.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.352-354
• /
• 2022

Position measurement using a camera has been studied for a long time. This is being studied for distance recognition or object recognition in autonomous vehicles, and it is being studied in the field of indoor navigation, which is a limited space where GPS is difficult to apply. In general, in a method of measuring the distance using a camera, the distance is measured using a distance between the cameras using two stereo cameras and a value measured through a captured image or photo. In this paper, we propose a method of measuring the distance of an object using a single camera. The proposed method measures the distance by using the distance between cameras, such as a stereo camera, and the value measured by the photographed picture through the gap of the photographing time and the distance between photographing.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.2
• /
• pp.325-336
• /
• 2023

With the development of autonomous driving technology, the number of external contact sensors mounted on vehicles is increasing, and the importance is also rising. The vehicular ultrasonic sensor uses the LIN protocol in the form of a bus topology and reports a status message about its surroundings through the vehicle's internal network. Since ultrasonic sensors are vulnerable to various threats due to poor security protocols, physical testing on actual vehicle is needed. Therefore, this paper developed a LIN-CAN co-analysis testbed with a jig for location-specific distance test to examine the operational relation between LIN and CAN caused by ultrasonic sensors.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.1090-1093
• /
• 2020

운전자가 아닌 자율주행 시스템이 운전을 주도하기 위한 기술의 상용화를 위해 많은 기업이 노력 중이다. 특히 운전자의 안전을 보장하기 위한 운전자와 자율주행 시스템 간의 제어권전환이 중요하다. 운전자의 주행과 관련 없는 행동은 제어권전환 상황에서 운전자를 위험에 빠뜨릴 수 있으므로 제어권전환을 돕기 위한 운전자 모니터링 기술에 관한 많은 연구가 진행되고 있다. 운전자 모니터링 기술은 주로 생체 정보, 차량 정보, 영상을 사용하여 운전자의 상태와 부주의 행동 등을 감지하는 기술이다. 최근 머신 러닝, 딥 러닝을 사용한 영상처리 및 인식 기술 등의 발전으로 영상을 사용한 운전자 모니터링 기술이 활발하게 연구되고 있다. 따라서 본 논문에서는 영상기반 운전자 모니터링 기술 동향에 대해 상세히 기술하였다. 특히 운전자의 부주의 행동 중 졸음은 운전자가 주행 상황을 전혀 인지하지 못하게 할 수 있어 더욱 위험한 행동이다. 따라서 영상기반 운전자 모니터링 기술을 졸음 인식과 그 외의 행동 인식으로 분류하여 동향을 정리하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.60-63
• /
• 2020

With the advent of deep learning, a lot of attempts have been made in computer vision to substitute deep learning models for conventional algorithms. Among them, image classification, object detection, and image restoration have received a lot of attention from researchers. However, most of the contributions were refined in one of the fields only. We propose a new paradigm of model structure. End-to-end model which we will introduce classifies noise of an image and restores accordingly. Through this, the model enhances universality and efficiency. Our proposed model is an 'One-For-All' model which classifies weather condition in an image and returns clean image accordingly. By separating weather conditions, restoration model became more compact as well as effective in reducing raindrops, snowflakes, or haze in an image which degrade the quality of the image.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.376-378
• /
• 2022

Artificial intelligence technology is widely used in various fields such as artificial intelligence speakers, artificial intelligence chatbots, and autonomous vehicles. Among these AI application fields, the image processing field shows various uses such as detecting objects or recognizing objects using artificial intelligence. In this paper, data synthesized by a virtual human is used as a method to analyze images taken in a specific space.

• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.92-99
• /
• 2023

Autonomous vehicles should recognize and respond to the specified speed to drive in compliance with regulations. To recognize the specified speed, the most representative method is to read the numbers of the signs by recognizing the speed signs in the front camera image. This study proposes a method that utilizes YOLO-Labeling-Labeling-EfficientNet. The sign box is first recognized with YOLO, and the numeric digit is extracted according to the pixel value from the recognized box through two labeling stages. After that, the number of each digit is recognized using EfficientNet (CNN) learned with the virtual environment dataset produced directly. In addition, we estimated the depth of information from the height value of the recognized sign through regression analysis. We verified the proposed algorithm using the virtual racing environment and GTSRB, and proved its real-time performance and efficient recognition performance.

• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.140-149
• /
• 2023

Wire harness is a component for efficient control when electronic parts are required such as construction machinery and electric vehicles. With emerging issues such as autonomous driving and automation in construction, a wire harness composed of multiple cables has become an essential part because more electronic parts are required. However, when a wire harness failure occurs, systems can be stopped, accidents can occur, and economic damage can be significant. Therefore, in this paper, we developed a digital fault screening system that could easily and quickly diagnose faults in the wire harness. The principle of the developed system was to sequentially send pulse signals to the wire harness and use returned signals to perform fault detection. As a result of diagnosing faults using the developed failure detection system, a detection accuracy of 99.9 % was confirmed through the experiments.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.2
• /
• pp.91-99
• /
• 2024

Collision avoidance system is important to improve the robustness and functional safety of autonomous vehicles. This paper proposes an object-level distance estimation method to develop a collision avoidance system, and it is applied to golfcarts utilized in country club environments. To improve the detection accuracy, we continually trained an object detection model based on pseudo labels generated by a pre-trained detector. Moreover, we propose object-aware depth estimation (OADE) method which trains a depth model focusing on object regions. In the OADE algorithm, we generated dense depth information for object regions by utilizing detection results and sparse LiDAR points, and it is referred to as object-aware LiDAR projection (OALP). By using the OALP maps, a depth estimation model was trained by backpropagating more gradients of the loss on object regions. Experiments were conducted on our custom dataset, which was collected for the travel distance of 22 km on 54 holes in three country clubs under various weather conditions. The precision and recall rate were respectively improved from 70.5% and 49.1% to 95.3% and 92.1% after the continual learning with pseudo labels. Moreover, the OADE algorithm reduces the absolute relative error from 4.76% to 4.27% for estimating distances to obstacles.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.1
• /
• pp.77-86
• /
• 2024

Urban Air Mobility (UAM) is considered the future of transportation, offering solutions to urban challenges and reducing environmental issues through the use of electric power and leveraging the sky as a new transportation corridor. UAM has diverse applications, including passenger and goods transportation, emergency rescue operations, patient transfers, and urban tourism. Furthermore, it is poised to revolutionize the transportation landscape, impacting existing infrastructures such as roads and parking lots, along with autonomous vehicles. The UAM industry is anticipated to exert a significant impact on various sectors, including airframe manufacturing, the development of new materials (e.g., fuel cells and batteries), and even the defense industry, resulting in substantial economic benefits. Consequently, conducting proactive research and setting industry standards for UAM takeoff and landing infrastructure is crucial for securing market leadership. In this regard, the case of Pontoise-Cormeiles, France, stands out as it achieved the world's inaugural successful demonstration of a vertiport before the 2024 Olympics. This achievement has significant implications for our preparations for the commercialization of UAMs. Thus, a detailed review of the French vertiport construction case in this study will serve as a foundation for guiding the planning and operation of UAMs in South Korea, particularly in anticipation of upcoming demonstration tests.