• Journal of Korean Society of Transportation
• /
• v.26 no.1
• /
• pp.15-24
• /
• 2008

Located in the middle of lanes, the station of a median exclusive bus lane generates pedestrian groups on the green light of a crosswalk and causes pedestrians delays passing the access section. For the purpose of showing these facts, the pedestrian analysis, on which the queuing theory is applied, is presented in this study. The Result is that the pedestrian environment was deteriorated (LOS D) compared to an exciting pedestrian analysis based on 15 minutes of pedestrian volume (LOS A). A pedestrian level of service has been reevaluated based on an arrival rate on the median bus station in order to examine whether the result reflects reality or not. In result, it was similar outcomes to this study.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.28 no.8
• /
• pp.14-23
• /
• 2014

According to the analysis of crosswalk pedestrian accidents, accidents that occur at night represent 70% of all deaths among crosswalk pedestrians when compared to accidents occurring in the daytime. This is due to the poor visibility that hinders drivers to recognize pedestrians at night. Illuminance on the horizontal plane of the road and the current state of crosswalk lighting are not sufficient enough to comply with standards. Thus, we analyzed factors derived from lighting environment studies on improving crosswalk visibility, domestic and foreign crosswalk lighting standards, and subsequently proposed solutions which are needed to raise domestic crosswalk lighting standards, and a means to uphold those standards through proper verification.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.836-846
• /
• 2023

Mobile robots are used in modern life; however, object recognition is still insufficient to realize robot navigation in crowded environments. Mobile robots must rapidly and accurately recognize the movements and shapes of pedestrians to navigate safely in pedestrian-rich spaces. This study proposes real-time, accurate, three-dimensional (3D) multi-pedestrian detection and tracking using a 3D light detection and ranging (LiDAR) point cloud in crowded environments. The pedestrian detection quickly segments a sparse 3D point cloud into individual pedestrians using a lightweight convolutional autoencoder and connected-component algorithm. The multi-pedestrian tracking identifies the same pedestrians considering motion and appearance cues in continuing frames. In addition, it estimates pedestrians' dynamic movements with various patterns by adaptively mixing heterogeneous motion models. We evaluate the computational speed and accuracy of each module using the KITTI dataset. We demonstrate that our integrated system, which rapidly and accurately recognizes pedestrian movement and appearance using a sparse 3D LiDAR, is applicable for robot navigation in crowded spaces.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.27 no.9
• /
• pp.606-611
• /
• 2014

Recently, LED lighting fixtures for crosswalk become popular in order to recognize the pedestrians at crosswalk, which can enhance the safety of the pedestrian at crosswalk. However, there are several problems related to the LED lighting fixtures for crosswalk, such as a lot of energy consumption due to a constant illumination during night and glaring of pedestrians at the opposite side of crosswalk. In this study, in order to overcome these problems, we have investigated a novel LED lighting fixture for crosswalk, which has two modules with different angles ($60^{\circ}$, $120^{\circ}$). Illuminance of min and max at four-line city street crosswalk shown 50 Lux, 125 Lux, respectively. Illuminance of min and max at eight-line city street crosswalk shown 150 Lux, 200 Lux, respectively. Simulation investigation was optimized design using optical program. Prototype was verified measurement by goniometer system.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.361-368
• /
• 2018

As autonomous driving research is rapidly developing, pedestrian detection study is also successfully investigated. However, most of the study utilizes color image datasets and those are relatively easy to detect the pedestrian. In case of color images, the scene should be exposed by enough light in order to capture the pedestrian and it is not easy for the conventional methods to detect the pedestrian if it is the other case. Therefore, in this paper, we propose deep neural network (DNN)-based multi-spectrum pedestrian detection method using color and thermal images. Based on single-shot multibox detector (SSD), we propose fusion network structures which simultaneously employ color and thermal images. In the experiment, we used KAIST dataset. We showed that proposed SSD-H (SSD-Halfway fusion) technique shows 18.18% lower miss rate compared to the KAIST pedestrian detection baseline. In addition, the proposed method shows at least 2.1% lower miss rate compared to the conventional halfway fusion method.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.35 no.8
• /
• pp.101-109
• /
• 2019

Korea's transportation paradigm is shifting from a vehicle-oriented transportation plan to a pedestrian-friendly environment that emphasizes walking safety. However, the level of pedestrian traffic accidents in Korea is still high and serious. The purpose of this study is to investigate factors affecting the severity of pedestrians traffic accidents using the multilevel logistic regression model based on 2015-2017 pedestrian accidents data provided by the Traffic Accident Analysis System(TAAS). The main results of the multilevel logistic regression model showed that 89% of pedestrian traffic accidents in Seoul were explained by individual characteristics such as drivers and pedestrians, and 11% were explained by neighborhood environmental characteristics. The results are as follows : In the individual characteristics such as pedestrians and drivers, the older the pedestrians and the drivers, the higher the traffic accident severity. The severity of traffic accidents was high when the pedestrians were female and the drivers were male. In the case of accident types, traffic accidents were more serious in the cases of heavy vehicles, inclement weather, and occurring at intersections and crosswalks. The results of the neighborhood environmental characteristics are as follows. The intersection density and the crosswalk density tended to reduce the severity of traffic accidents. On the other hand, the traffic light density and the school zones were founded to related to the higher level of traffic accident severity. This study suggests that both individual and neighborhood environmental characteristics should be considered together to prevent and reduce the severity of pedestrian traffic accidents.

• KIEAE Journal
• /
• v.16 no.3
• /
• pp.47-55
• /
• 2016

Purpose: This study was aimed at providing the basic checklist as a means to assess the crime risk in physical environment of the pedestrian passage at residential area. Method: For this purpose, the preliminary checklists were selected according to the review of the precedent studies of checklists in exterior pedestrian passage. The usefulness and the importance of the preliminary checklists were analyzed through the seven expert group meetings, the 87 questionnaires survey of the crime experts & the architectural/urban experts, preliminary assessment and field survey. Results: The assessment categories of checklists were sorted into six types, i.e. spatial structure & function, lighting, landscaping, security facilities, other facilities and cleaning & maintenance. The 49 checklists were proposed according to the assessment categories. The final checklists were divided key checklists and general checklists based on the results of experts' weighting of each list item. There were significant differences between crime experts' weighting and architectural/urban experts' weighting in several checklists, i.e. dividing between pavements and streets, the brightness of light, white light.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2008.04a
• /
• pp.282-287
• /
• 2008

Since glass-fiber reinforced composite decks have high-strength, light-weight and high durability, many researchs on the composite decks for bridges are currently performed and many composite decks are developed. In this paper, a composite deck with snap-fit connection for pedestrian bridge is developed and studied. A study on behavior of snap-fit connection of composite deck for pedestrian bridge during assembling or disassembling is performed by analysis and experiment.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2007.04a
• /
• pp.539-544
• /
• 2007

Glass fiber reinforced composite decks have high-strength, light-weight and high durability. The composite decks having vertical snap-fit connections are designed for pedestrian bridges and their structural behaviour are studied. The existing connection method of the composite decks in horizontal direction is replaced by the developed snap-fit connection method in vertical direction. The section shape of the composite decks having the vertical snap-fit connection is designed. The safety of the vertical snap-fit connection is verified by finite element analysis.

• Journal of the HCI Society of Korea
• /
• v.14 no.2
• /
• pp.41-47
• /
• 2019

In this study, a smart assistive device is designed to recognize pedestrian signal and to provide audio instructions for visually impaired people in crossing streets safely. Walking alone is one of the biggest challenges to the visually impaired and it deteriorates their life quality. The proposed device has a camera attached on a pair of glasses which can detect traffic lights, recognize pedestrian signals in real-time using a machine learning algorithm on GPU board and provide audio instructions to the user. For the portability, the dimension of the device is designed to be compact and light but with sufficient battery life. The embedded processor of device is wired to the small camera which is attached on a pair of glasses. Also, on inner part of the leg of the glasses, a bone-conduction speaker is installed which can give audio instructions without blocking external sounds for safety reason. The performance of the proposed device was validated with experiments and it showed 87.0% recall and 100% precision for detecting pedestrian green light, and 94.4% recall and 97.1% precision for detecting pedestrian red light.