• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2005.11a
• /
• pp.190-200
• /
• 2005

In this paper, the image modelling of road's lane markings is established using view frustum(VF) modeling. This algorithm also involve the real time processing of the 3D position coordinate and the distance data from the camera to the points on the 3D world coordinate by the camera calibration. In order to reduce their measurement error, an useful algorithm for which analyze the geometric variations clue to traveling vehicle's fluctuation using VF model is proposed. In experiments, without correction, for instance, the $0.4^{\circ}$ of pitching rotation gives the error of $0.4^{\sim}0.6m$ at the distance of 10m, but the more far distance cause exponentially the more error. We confirmed that this algorithm can be reduced less than 0.1m of error at the same condition.

• 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 Association of Geographic Information Studies
• /
• v.25 no.4
• /
• pp.181-199
• /
• 2022

This study presented a methodology for evaluating the performance of the lane departure warning system was derived by calculating the relationship between the behavior information of the car and the location of the high-precision map using a high-precision map. The evaluation criteria of the mood and lane departure warning system for the installation of road markings in Korea were analyzed, a high-precision map was constructed to meet the evaluation criteria, and an evaluation system was constructed to verify the proposed methodology. Evaluation of lane departure warning systems using high-precision maps can be quantified and applied to various road environments through accurate location-based comparative analysis and reduced manual post-processing work time to confirm evaluation results.

• Current Optics and Photonics
• /
• v.3 no.5
• /
• pp.415-422
• /
• 2019

Retroreflection of vehicle headlights, as induced by spherical glass beads, is a key optical phenomenon that provides road-surface markings with greatly enhanced visibility, thus better securing a driver's safety in the nighttime as well as in unclear daytime. Retroreflectance of glass beads is a quite sensitive function of their refractive index, so that measurement of the refractive index of glass specifically in the shape of spherical beads needs to be performed within a reasonable uncertainty that is tolerable for road-marking applications. The Becke line method has been applied in assessing refractive index of such glass beads as e.g. an industrial standard in the Republic of Korea; however, the reference refractive-index liquids are not commercially available these days for refractive index greater than 1.80 due to the toxicity of the constituent materials. As such, high-refractive-index glass beads require an alternate method, and in this regard we propose a practically serviceable technique with uncertainty tantamount to that of the Becke line method: Based on comparison of calculated and measured retroreflectance values of commercial glass beads, we discover that their refractive index can be determined with reasonable precision via the retroreflectance measurement. Specifically, in this study the normalized retroreflectance originating from a single glass sphere is computed as a function of refractive index using the Fresnel equations, which is then validated as coinciding well with retroreflectance values measured from actual specimens, i.e. glass-bead aggregates. The uncertainties involved are delineated in connection with radius and imperfections of the glass beads.

• Proceedings of the KOR-KST Conference
• /
• 1998.10a
• /
• pp.342-351
• /
• 1998

노면표시는 운전자에게 시선유도와 각종 규제 및 지시에 대한 정보를 제공함으로써 교통안전 및 소통에 도움을 주는 시설로써 주야간의 시인성 확보가 중요하며 이를 위해서는 반사화가 필요하다. 노면표시의 반사성능은 유리알 (Glass Bead)의 함량 및 종류, 용융온도, 도료의 색도등 각 영향인자에 의해 결정되지만 현재는 시공법 및 관련 연구의 미흡으로 현행기준의 최하수준을 상회하는 정도로 제공되고 있다. 따라서 본 연구에서는 노면표시의 시공에 관계되는 각 요인중 반사성능가 내구성에 영향을 미치는 주요인자 및 반사성능을 최적화하기 위한 인자별 최적조합을 도출하였다. 연구결과 유리알 살포량이 중량비로 25%-30%, 용융시 온도가 $188^{\circ}C$$\pm$$10^{\circ}C$일 때 노면표면시의 반사성능이 최적화됨을 밝혀내었다. 또한 유리알의 품질개선과 함께 황색 노면표시의 재귀반사 휘도계수 기준을 현재 기준보다 상향조정할 필요성이 있음을 제안하였다.

• 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.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.5
• /
• pp.481-489
• /
• 2017

The study area,Cheonan Stream, is an urban river that flows through urban areas in close proximity to densely populated areas and multi-use facilities. The natural river improvement project from 2006 to 2015 improved the quality of life of local residents with the improvement of river function, the restoration of the natural ecosystem and the securement of hydrophilic space. A bike way in the constructed waterside space was built focusing on trails. This study suggests improvements appropriate for insufficient bike way function-related regulations. The problems of ramps, river crossing facilities, stairway facilities, safety facilities, signs, road markings, and parking facilities, etc.have arisen in the utilization situation and citizen consciousness survey. As an improvement, it was suggested that 12% or fewer ramps should be improved, a submerged bridge should be installed at 7 places separated by stepping bridges, and signs and road markings according to bike way-related regulations should be installed and bike parking facilities at Cheonan station and Cheonan bus terminal should be expanded. The bike way in the waterfront of ChoenanCheon(river) will increase the accessibility and utilization rate of short-distance transportation with the institutional expansion of bike use facilities and work organizations and the improvement of facilities in accordance with urban rivers and bike-related regulations. Therefore, it is expected that the development of the living space will be beneficial for the citizens due to the elimination of traffic in the city and the activation of bike traffic.

• International Journal of Highway Engineering
• /
• v.13 no.3
• /
• pp.75-82
• /
• 2011

There is the uncertain period of the construction in case of the products meeting the quality standard of KS M 6080, the quality is degraded because of the abrasive loss of the paint caused by vehicle tires as the traffic amount increases and of the loss and detachment of the glass beads providing the retroreflective function. The abrupt degradation of visibility causes the high frequency of traffic accidents at night and increases the traffic accident rate. Additional supplementary construction induces the direct material and construction costs. As the more cost induction effect than the direct cost, the traffic jam caused by the additional construction increases the indirect social costs such as time cost and vehicle cost. Hence, the study is concerned with performing the abrasion resistance test based on the EN 1436 standard to check and improve the quality of various road marking materials resulting in improving the durability of road marking materials. However, even though the difference in the durability lifetime of resins(binders) is bibliographically or theoretically clear, there was no difference in the durability lifetime (retroreflectivity aspect) of the road marking paint using these binders. The reason is that the bonding of beads was very insufficient or that the cross density caused by crack or freshness was low. Moreover, the measured wet retroreflectivity was distributed as the Rw3 or higher class in average on the basis of EN 1436 but was very insufficient on the basis of the minimum wet threshold retroreflectivity with 100mcd/($m^2{\cdot}lx$) managed overseas.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.1
• /
• pp.89-97
• /
• 2013

Recently, economic and social damages are globally increased due to the heavy snowfall caused by global warming. To reduce the damages of sudden regional heavy snow in roads, suitable countermeasures should be established based on the accurate detection of snowfall intensity for each roadway segment. In this paper, we deal with snowfall intensity detecting algorithm in the road area from CCD Imagery. First, we determine the MLZ (MotionLess Zone), which does not contain lane markings and moving cars, in the image space. Next, snow streaks trespassing the MLZ are extracted with Canny operator and proposed algorithm. Also, the concept of SII (Snow Intensity Index), which is the number of snow streaks during one minute in the MLZ, is defined. Finally, the effectiveness of proposed algorithm is proved by visually comparing the imagery and SII value obtained during 69 minutes. In consequence, we figured out that the integration of SII is significantly related to an actual amount of snowfall.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.48 no.6
• /
• pp.15-24
• /
• 2011

As increase awareness of intelligent vehicle systems, many kinds of lane detection algorithm have been proposed. General boundary extraction method can bring good result in detection of lane on the road. But a shadow on the road, or other boundaries, such as horizontal lines can be detected. The method using morphological operations was used to extract information about Lane. By applying HSV color model for color information of lane, the candidate of the lane can be extracted. In this paper, the lane detection region was set by Hough transformation using the candidate of the lane. By extracting lane markings on the lane detection region, lane detection method can bring good result.