• ETRI Journal
• /
• v.36 no.6
• /
• pp.968-978
• /
• 2014

Autonomous vehicle technology based on information technology and software will lead the automotive industry in the near future. Vehicle localization technology is a core expertise geared toward developing autonomous vehicles and will provide location information for control and decision. This paper proposes an effective vision-based localization technology to be applied to autonomous vehicles. In particular, the proposed technology makes use of numerical maps that are widely used in the field of geographic information systems and that have already been built in advance. Optimum vehicle ego-motion estimation and road marking feature extraction techniques are adopted and then combined by an extended Kalman filter and particle filter to make up the localization technology. The implementation results of this paper show remarkable results; namely, an 18 ms mean processing time and 10 cm location error. In addition, autonomous driving and parking are successfully completed with an unmanned vehicle within a $300m{\times}500m$ space.

• International Journal of Highway Engineering
• /
• v.14 no.6
• /
• pp.85-92
• /
• 2012

PURPOSES : Since expressways in South Korea are toll roads, many trumpet type interchanges exist, resulting in the installation of loop ramps very frequently. While the travel speed of the main lane is designed to be 100-110 km/h, the structure of a loop ramp is different and is designed for a minimum speed of 40 km/h. In fact, most of the actual travel speeds measured on the ramp exceed the designated speed, which has been a major problem in traffic safety. In this research, a type of pavement marking speed-reduction treatment called the "Peripheral Transverse Line" is installed on expressway loop ramps in order to study the change of driving speeds after the installation. METHODS : To verify statistically the change, this speed-reduction treatment has been installed on the Chungju interchange and the Yeoju junction. The driving speeds before the installation were compared with driving speeds both one month and five monthsafter the installation. RESULTS : As a result, the reductions of the average driving speeds after the treatment were statistically significant. More specifically, the average driving speeds of the Chungju interchange were reduced by 7.1-7.7 % for its tangent road section, and the speeds decreased by 8.5-9.5 % for its curve section. Similarly, in the Yeoju junction, an average speed reduction of 2.9-4.8 % for its tangent section was measured, along with 3.9% long-term speed reduction for its curve section. CONCLUSIONS : Since the pavement marking speed-reduction treatment has been partially proven to be effective from this research, we expect to expand this treatment and re-confirm the effect from a long-term perspective in the future.

• Journal of Korean Society of Transportation
• /
• v.25 no.4
• /
• pp.33-42
• /
• 2007

This study analyzes presentation methods of traffic guide maps to guide drivers easily and correctly to their destinations on complex road networks. The problems of Korea's guidance systems were analyzed and domestic and international road guide maps were compared. This study includes the problems of road number discernment, such as the sizes, colors and marking intervals on the map. The widths and colors of different hierarchical roads were evaluated. The indices, enlarged downtown maps and uncertainty of grade separation on the map were analyzed and the solutions were also provided.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.5
• /
• pp.224-230
• /
• 2013

Lane boundary detection plays a key role in the driver assistance system. This study proposes a robust method for detecting lane boundary in severe environment. First, a horizontal line detects form the original image using improved Vertical Mean Distribution Method (iVMD) and the sub-region image which is under the horizontal line, is determined. Second, we extract the lane marking from the sub-region image using Canny edge detector. Finally, K-means clustering algorithm classifi left and right lane cluster under variant illumination, cracked road, complex lane marking and passing traffic. Experimental results show that the proposed method satisfie the real-time and efficient requirement of the intelligent transportation system.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.2
• /
• pp.711-718
• /
• 2013

Traffic pavement markings are one of primary transportation facilities that provide drivers with various road information directly. Thus, a clear understanding of traffic pavement markings is utmost important to improve traffic safety as well as to establish a proper traffic culture. However, no past studies examined drivers' understanding of traffic pavement markings in Korea. Hence, this study investigated drivers' understanding of traffic pavement markings through an elaborated administrated survey, and analyzed the relationship between various drivers' characteristics and understanding regarding pavement marking via cross-classification table and logistic model. The analysis results show that drivers have limited understanding regarding the purpose of the markings. Specifically, the average understanding of pavement markings is 57.41%: the lowest understanding is 25.88% for yield pavement marking, and the highest understanding is 91.18% for advanced pedestrian crosswalk pavement marking. This study also revealed that the understanding of some pavement markings are somewhat influenced by user group such as drivers with suspended or revoked driver licenses, but the overall understanding of pavement markings are not significantly affected by drivers' characteristics such as gender and driving experiences at ${\alpha}$=0.05. Thus, it might be desirable for policy makers to establish pavement marking-related policies for overall drivers rather than specific drivers.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.12
• /
• pp.69-74
• /
• 2018

The road name address is a two-dimensional location marking method for naming each road and assigning a number to each building. However, the road name address only shows the necessary parts for administrative and legal acts, and it does not properly display the main characteristics of various roads and non-residential areas. This has become more and more difficult to standardize different location identification methods, merely as a separate location identification method. This paper proposes road-based 3D location identification code to overcome the difficulties of integrating different location identification methods in Korea and to overcome the limit of 2D plane. This is a method to integrate various location identification methods based on roads and to identify spatial coordinates. It is a study on 3D digital coding of the land suitable for the 4th Industrial Revolution era.

• International Journal of Highway Engineering
• /
• v.14 no.3
• /
• pp.131-140
• /
• 2012

Lane markings such as edgelines, centerlines, and lines that delineate lanes generally provide drivers with the various information for safe driving. Drivers can easily recognize the lane markings through the color differences between the markings and road surfaces during the daytime. However, it is a bit difficult for drivers to perceive them during the nighttime due to the lack of artificial lights. Although the glass beads with the 1.5-refractive index have been used to improve the visibility of the lane markings during the nighttime, it is still difficult for drivers to recognize the lane markings properly, especially during the rainy nighttime, which may often lead to traffic accidents. To improve the retroreflectivity and visibility of the lane markings during the rainy nighttime, the high refractive beads with the 2.4-refractive index are essentially required, but they do not work appropriately during the dry nighttime. Thus, the mixed materials with the 1.5, 1.9, and 2.4-refractive beads should be considered for the satisfactory implementation of the lane markings. This study reveals the best mixing rates of the beads by conducting benefit-cost analysis under various weather conditions in Korea. The analysis results show that the lane markings with the 100% of the 2.4-refractive beads provide the highest visibility of lane markings regardless of the roadway conditions, but the benefit-cost (B/C) ratio of the bead mixture is merely 0.46. The best mixing rate of the beads, from the highest B/C ratio viewpoint, was identified as the mixture with a 80% of 1.5-refractive beads and a 20% of 2.4-refractive beads. Some limitations and future research agenda have also been discussed.

• Applied Chemistry for Engineering
• /
• v.26 no.4
• /
• pp.439-444
• /
• 2015

Several attempts to design the best-available thermosetting road markings by using MMA to improve the durability and retroreflectivity are presented in this paper. In order to improve field applicability, the components of main materials were designed by means of reducing the hardening time lower than eight minutes. The optimum mixing ratio of thermosetting road marking was TSRM-6 composed of 15.6 wt% of MMA monomer ($Tg=105^{\circ}C$), 6.0 wt% of PMMA (MW = 70,000, $Tg=60^{\circ}C$) and 1.2 wt% of TMPTA (MW = 338, $Tg=27^{\circ}C$). Also the homogeneous mixing of all components was necessary. The use of ceramic glass beads with an optimized TSRM-6 exhibited excellent performance by achieving retroreflectivity coefficients of 431, 354 and $172mcd{\cdot}m^{-2}{\cdot}lux^{-1}$ for dry, wet and rainy test condition, respectively at two hundred thousand cycles.

• ETRI Journal
• /
• v.37 no.6
• /
• pp.1220-1230
• /
• 2015

An autonomous valet parking (AVP) system is designed to locate a vacant parking space and park the vehicle in which it resides on behalf of the driver, once the driver has left the vehicle. In addition, the AVP is able to direct the vehicle to a location desired by the driver when requested. In this paper, for an AVP system, we introduce technology to recognize a parking space using image sensors. The proposed technology is mainly divided into three parts. First, spatial analysis is carried out using a height map that is based on dense motion stereo. Second, modelling of road markings is conducted using a probability map with a new salient-line feature extractor. Finally, parking space recognition is based on a Bayesian classifier. The experimental results show an execution time of up to 10 ms and a recognition rate of over 99%. Also, the performance and properties of the proposed technology were evaluated with a variety of data. Our algorithms, which are part of the proposed technology, are expected to apply to various research areas regarding autonomous vehicles, such as map generation, road marking recognition, localization, and environment recognition.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.133-139
• /
• 2021

Currently, the process of constructing a high-definition road map has a high proportion of manual labor, so there are limitations in construction time and cost. Research to automate map production with high-definition road maps using artificial intelligence is being actively conducted, but since the construction of training data for the map construction is also done manually, there is a need to automatically build training data. Therefore, in this study, after converting to images using point clouds acquired by a mobile mapping system, the road marking areas were extracted through image reclassification and overlap analysis using thresholds. Then, a methodology was proposed to automatically construct training data for deep learning data for the high-definition road map through the classification of the polygon types in the extracted regions. As a result of training 2,764 lane data constructed through the proposed methodology on a deep learning-based PointNet model, the training accuracy was 99.977%, and as a result of predicting the lanes of three color types using the trained model, the accuracy was 99.566%. Therefore, it was found that the methodology proposed in this study can efficiently produce training data for high-definition road maps, and it is believed that the map production process of road markings can also be automated.