• Journal of Broadcast Engineering
• /
• v.21 no.1
• /
• pp.87-96
• /
• 2016

Recently, there is a need for automatic recognition of a variety of symbols on roads because of activation of information services using digital maps on the Web or mobile devices. This paper proposes a method which automatically recognizes 11 kinds of symbolic road markings on the road surface with HOG-SP(Histogram of oriented Gradients-Split Projection) descriptor and shows improvement of lane position detection with recognized symbolic road markings. With the proposed method, recognition rate of 81.99% has been proven on NAVER road view images and the experiments proves the superiority of proposed method by comparisons with other existing methods. Moreover, this paper shows 7.64% higher lane position detection rate by recognizing road surface marking beforehand than only detecting lanes' positions.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.5
• /
• pp.178-188
• /
• 2020

This paper proposes a lane recognition CNN network using split-attention network as a backbone to extract feature. Split-attention is a method of assigning weight to each channel of a feature map in the CNN feature extraction process; it can reliably extract the features of an image during the rapidly changing driving environment of a vehicle. The proposed deep neural networks in this paper were trained and evaluated using the Tusimple data set. The change in performance according to the number of layers of the backbone network was compared and analyzed. A result comparable to the latest research was obtained with an accuracy of up to 96.26, and FN showed the best result. Therefore, even in the driving environment of an actual vehicle, stable lane recognition is possible without misrecognition using the model proposed in this study.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.3
• /
• pp.563-570
• /
• 2024

This paper proposes a method to recognize and track drivable lane areas to assist the driver. The main topic is designing a deep-based network that predicts drivable road areas using computer vision and deep learning technology based on images acquired in real time through a camera installed in the center of the windshield inside the vehicle. This study aims to develop a new model trained with data directly obtained from cameras using the YOLO algorithm. It is expected to play a role in assisting the driver's driving by visualizing the exact location of the vehicle on the actual road consistent with the actual image and displaying and tracking the drivable lane area. As a result of the experiment, it was possible to track the drivable road area in most cases, but in bad weather such as heavy rain at night, there were cases where lanes were not accurately recognized, so improvement in model performance is needed to solve this problem.

• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.2
• /
• pp.25-31
• /
• 2019

As artificial intelligence technology has been developed rapidly, many researchers who are interested in next-generation vehicles have been studying on applying the artificial intelligence technology to advanced driver assistance systems (ADAS). In this paper, a method of applying deep learning algorithm to the lane departure warning system which is one of the main components of the ADAS was proposed. The performance of the proposed method was evaluated by taking a comparative experiments with the existing algorithm which is based on the line detection using image processing techniques. The experiments were carried out for two different driving situations with image databases for driving on a highway and on the urban streets. The experimental results showed that the proposed system has higher accuracy and precision than the existing method under both situations.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.36 no.4
• /
• pp.685-694
• /
• 2016

Visibility of lane marking is impaired at night, or in case of rain, and thereby threatens traffic safety. Recently, various studies and technology have been developed to improve lane marking visibility, such as the extension of lane marking life expectancy (up to 1.5 times), improvement of lane marking equipment, improvement of lane marking visibility (32.7%) by applying phosphorescent material mixed paint, and expressway lane design standards alternative (length 6m, gap 12m, width 13cm: 27.8% of painted surface are reduced) adoption with ergonomic analysis. In this study, a set of cost-benefit analyses was performed for the cases where such techniques were applied. Based on the literature review, 26.9% of traffic accidents would be prevented by improving lane marking visibility by 32.7%; accident reduction benefit was calculated as much as 12.5 billion KRW. Meanwhile, total increased cost when introducing phosphorescent material mixed paint and lane design standards alternative is calculated as 30.6 billion KRW. However, economic feasibility could not be secured with 0.41 of cost-benefit ratio when applied to the expressway network as a whole. Additionally, cost-benefit (B/C) analysis was applied to each of the top 20 night accident hot spots and the results of B/C ratios were between 0.67 and 4.20, showing that 11 out of 20 spot sections of expressway can have economic feasibility. This results indicate, with this kind of pavement marking applied to accident hot spots in rural expressway, better visibility and economic feasibility can be guaranteed through traffic accident reduction. Some limitations and future research agenda have also been discussed.

• Journal of Korean Society of Transportation
• /
• v.30 no.2
• /
• pp.43-52
• /
• 2012

A lane departure warning system (LDWS) is an effective technology-based countermeasure for preventing traffic crashes as it provides warning information to drivers. Understanding the characteristics of perception and satisfaction levels on LDWS is fundamental for deriving better performance and functionality enhancements of the system. The purpose of this study is to evaluate the user satisfaction of LDWS. A survey to collect user perception and user preference data was conducted. Both cross-tabulation analysis and binary logistic regression technique were adopted to identify the factors affecting user satisfaction for LDWS. The results revealed that the accuracy and timeliness of warning information was significant for evaluating the effectiveness of LDWS. In particular, the warning accuracy at a curve segment on the road was the most dominant factor affecting user satisfaction. The outcome of this study would be valuable in evaluating and designing LDWS functionalities.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06d
• /
• pp.343-345
• /
• 2012

기존의 교통제어 시스템은 고정된 녹색 신호의 길이와 주기를 갖고 있다. 그에 따라 차선 간 차량 밀집도가 불균형한 경우 교통 처리량이 저하되고 응급상황이 발생할 경우 지정체가 유발된다. 본 논문에서는 VANET을 이용하여 교통량의 실시간 정보를 수집해 적응적으로 교통 신호를 제어하는 시스템을 제안한다. 차량의 수, 평균 신호대기 시간, 차선 간 균형, 응급상황 등을 고려하여 교통 신호를 가변적으로 제어 한다. 차량이 교차로에 진입하기 전 통신모듈을 갖고 있는 신호등에게 위치, 방향, 속도 정보 등을 송신하고 traffic control system에서 교통량을 분석하여 녹색 신호를 가변적으로 할당 한다. 실험결과 제안 기법이 교통 처리량, 평균 신호대기시간에서 기존 교통신호 제어 기법보다 높은 성능을 확일 할 수 있었다.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2477-2479
• /
• 2004

본 논문에서는 차선관련 정보의 변이도함수(DLI, Disparity of Lane-related Information)를 기반으로 하는 선행차량 인식 알고리즘을 제안한다. 본 논문에서 제안하는 알고리즘을 이용하여, 주행차선내에 있는 선행차량의 유무 검출과 위치 유추 및 선행차량 인식을 수행한다. DLI를 이용하는 방법은 특징점의 탐색공간을 현저히 줄여 실시간 처리문제를 해결한 수 있는 장점을 가지고 있다. 본 논문에서는 제안된 선행차량 인식알고리즘의 성능을 검증하기 위하여 다양한 환경의 도로영상에 알고리즘을 적용하여, 제안된 선행차량 인식기법의 우수함을 확인하였다.

• Journal of IKEEE
• /
• v.15 no.3
• /
• pp.255-260
• /
• 2011

In this paper, we propose a parallelization technique in lane detection by using Hough transform. Hough transform has a weakness that it has a lot computation quantity, because it has to compute ${\rho}$ value in all candidate ${\Theta}$ to be detected in an image. We propose an architecture of parallel processing for this transform in a multi-core environment. The parallel processing has application to Hough transform as well as noise reduction and edge detection. This proposed architecture has 5.17 times improvement in performance compare to the existing algorithm.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.25 no.1
• /
• pp.99-107
• /
• 2014

Abruptly occurred obstacles on highway threaten driving safety. Radar draws the attention to the collision avoidance system because it can be fully operational in all weather, and day and night condition. This paper presents the design, implementation and performance test results of pulsed Doppler radar system for detection and warning of road obstacles. The system is designed to consider highway environment and detection capability about various fixed and moving obstacles. The system consists of 4 subsystems, which include antenna unit, transmitter and receiver unit, radar signal & data processing unit, and controller & display unit. The core technologies include clutter map based change detection for fixed obstacles detection, Doppler estimation for velocity detection of moving targets, and azimuth angle estimation method using monopulse for lane estimation and tracking. The design performance of the developed radar system is verified through experiments using a fixed reference target and moving vehicles in test highway.