• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.149-161
• /
• 2022

Because the speed limit affects moving speed, it is closely related to traffic accidents as well as traffic flow. The existing speed limit calculation methods consider various engineering factors such as lanes, intersection spacing, driveways, crosswalks, 85 percentile speed, land uses, and roadway geometric characteristics etc. However, it can be said that the engineering analysis is insufficient because the traffic impact analysis considering traffic volume is not carried out. In addition, only 85 percentile speed, which is the spot speed, does not reflect the characteristics of the traffic flow on the road. In this paper, the effect of the speed limit change on the moving speed and the travel speed was analyzed in detail accordinr to the variation of intersection spacing and traffic volume. And by using the results, we proposed a speed limit calculation method that maintains the same service level as before the speed limit change, thereby increasing the speed improvement effect and reducing the difference between moving speed and travel speed. In addition, a variable speed limit operation method according to the change in traffic volume was also suggested. This method is expected to be effective in terms of safety by reducing the speed difference, which affects the severity of traffic accidents, while securing the speed improvement effect, and increasing the speed limit compliance rate of drivers by operating the speed limit that reflects the speed change due to the variation of traffic volume.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.4
• /
• pp.1-9
• /
• 2023

In this paper, we propose a method to recognize the braille blocks for embedded devices in real time through deep learning. First, a deep learning model for braille block recognition is trained on a high-performance computer, and the learning model is applied to a lightweight tool to apply to an embedded device. To recognize the walking information of the braille block, an algorithm is used to determine the path using the distance from the braille block in the image. After detecting braille blocks, bollards, and crosswalks through the YOLOv8 model in the video captured by the embedded device, the walking information is recognized through the braille block path discrimination algorithm. We apply the model lightweight tool to YOLOv8 to detect braille blocks in real time. The precision of YOLOv8 model weights is lowered from the existing 32 bits to 8 bits, and the model is optimized by applying the TensorRT optimization engine. As the result of comparing the lightweight model through the proposed method with the existing model, the path recognition accuracy is 99.05%, which is almost the same as the existing model, but the recognition speed is reduced by 59% compared to the existing model, processing about 15 frames per second.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.166-172
• /
• 2022

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• The Journal of the Korea Contents Association
• /
• v.22 no.5
• /
• pp.288-304
• /
• 2022

Walking is an eco-friendly and sustainable means of transportation that promotes health and endurance. Despite the positive health benefits of walking, pedestrian safety is a serious problem in Korea. Therefore, it is necessary to investigate with various studies to reduce pedestrian-vehicle crashes. In this study, the cognitive characteristics affecting pedestrian-vehicle crashes were considered by applying deep learning semantic segmentation. The main results are as follows. First, it was found that the risk of pedestrian-vehicle crashes increased when the ratio of buildings among cognitive factors increased and when the ratio of vegetation and the ratio of sky decreased. Second, the humps were shown to reduce the risk of pedestrian-related collisions. Third, the risk of pedestrian-vehicle crashes was found to increase in areas with many neighborhood roads with lower hierarchy. Fourth, traffic lights, crosswalks, and traffic signs do not have a practical effect on reducing pedestrian-vehicle crashes. This study considered existing physical neighborhood environmental factors as well as factors in cognitive aspects that comprise the visual elements of the streetscape. In fact, the cognitive characteristics were shown to have an effect on the occurrence of pedestrian- related collisions. Therefore, it is expected that this study will be used as fundamental research to create a pedestrian-friendly urban environment considering cognitive characteristics in the future.

• 한국노년학
• /
• v.30 no.3
• /
• pp.843-853
• /
• 2010

The purpose of this study is to find out the characteristics of elderly pedestrian accidents and to suggest policy implications to enhance the level of elderly pedestrian safety. Although much efforts has made to enhance traffic safety environment, pedestrian traffic accidents among elderly population are not significantly decreased. This is mainly because current traffic safety measures do not much consider the characteristics of elderly pedestrians in the aspects of physical and psychological conditions. Main findings from vehicle-pedestrian traffic accident data and survey are as follows. First elderly pedestrians have high probability of traffic accident near crosswalks or cross streets rather than on crosswalk or cross streets. Second they need more green light time for crossing the streets. Third, they feel motor cycles running on the side walk and parked vehicles on the side walk are the most dangerous factors. Forth, general drivers do not have reasonable understanding for the walking behaviors of elderly pedestrians. Fifth, elderly pedestrians frequently need to rest while walking. Sixth, elderly people do not see clearly or understand traffic signs. Finally, many elderly pedestrians experience accidents or inconvenience while walking on the sidewalk.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.81-89
• /
• 2023

In modern society, blind people face difficulties in navigating common environments such as sidewalks, elevators, and crosswalks. Research has been conducted to alleviate these inconveniences for the visually impaired through the use of visual and audio aids. However, such research often encounters limitations when it comes to practical implementation due to the high cost of wearable devices, high-performance CCTV systems, and voice sensors. In this paper, we propose an artificial intelligence fusion algorithm that utilizes low-cost video sensors integrated into smartphones to help blind people safely navigate their surroundings during walking. The proposed algorithm combines motion capture and object detection algorithms to detect moving people and various obstacles encountered during walking. We employed the MediaPipe library for motion capture to model and detect surrounding pedestrians during motion. Additionally, we used object detection algorithms to model and detect various obstacles that can occur during walking on sidewalks. Through experimentation, we validated the performance of the artificial intelligence fusion algorithm, achieving accuracy of 0.92, precision of 0.91, recall of 0.99, and an F1 score of 0.95. This research can assist blind people in navigating through obstacles such as bollards, shared scooters, and vehicles encountered during walking, thereby enhancing their mobility and safety.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.2
• /
• pp.119-125
• /
• 2023

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.6
• /
• pp.1297-1308
• /
• 2015

In Korea, the local traffic safety master plan has been established and implemented according to the Traffic Safety Act. Each local government is required to establish a customized traffic safety policy and share roles for improvement of traffic safety and this means that local governments lead and promote effective local traffic safety policies fit for local circumstances in substance. For implementing efficient traffic safety policies, which accord with many-sided characteristics of local governments, the prediction of community-based traffic accidents, which considers local characteristics and the analysis of accident influence factors must be preceded, but there is a shortage of research on this. Most of existing studies on the community-based traffic accident prediction used social and economic variables related to accident exposure environments in countries or cities due to the limit of collected data. For this reason, there was a limit in applying the developed models to the actual reduction of traffic accidents. Thus, this study developed a local traffic accident prediction model, based on smaller regional units, administrative districts, which were not omitted in existing studies and suggested a method to reflect traffic safety facility and policy variables that traffic safety policy makers can control, in addition to social and economic variables related to accident exposure environments, in the model and apply them to the development of local traffic safety policies. The model development result showed that in terms of accident exposure environments, road extension, gross floor area of buildings, the ratio of bus lane installation and the number of crossroads and crosswalks had a positive relation with accidents and the ratio of crosswalk sign installation, the number of speed bumps and the results of clampdown by police force had a negative relation with accidents.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.36 no.5
• /
• pp.847-856
• /
• 2016

Recently, with a high level of economic growth, rapid urbanization, population, environment and housing problems were accompanied in Korea. In particular, the traffic problem has become a serious social problem. As the current transportation policy has been carried out, concentrating on traffic flow, in 2015, death rate for pedestrians while walking (1,795 persons) is 38.8% compared to entire death rate in car accident (4,621 persons), so there is need to solve it. Although, crosswalk should make pedestrian cross it safely, it has been made on the basis of the width of road without exact standard for current width of the crosswalk and the location of stop line. Moreover, in the area around many campuses or commercial facilities, crosswalks are set with not considering pedestrian passage, but designed uniformly. Therefore, the purpose of this study is to estimate reasonable dimension of crosswalk considering pedestrian traffic and walking speed and it makes the accident rate lower in the crosswalk, which has a lot of problems including decisions of vehicle traffic signal time, lack of pedestrian's signal timing, pedestrian's crossing of long-distance. The following are the methodology of the study. Firstly, for crosswalk calculation of specifications, examination relating existing regulations and researches dealing with crosswalk, pedestrians and stop line is needed. After analyzing problems of current width of crosswalk and stop line, present the methodology to calculation of specifications and basing on these things, calculation of specifications for crosswalk will be decided. In conclusion, the calculation of specification and improvement of stop line for crosswalk laid out in this study are expected to be utilized as base data in case of establishing relevant safety facilities and standards.