• Proceedings of the KSR Conference
• /
• 2009.05a
• /
• pp.1308-1317
• /
• 2009

The mass transit networks in Korea, such as buses, metro and subway, are co-related and the number of transfer points, in which a lot of pedestrian movement is generated, are rising. The functions of the transfer centers, in which several travel modes cross at a point, have to include convenience and comfort for pedestrians using the transfer centers, and such functions can make transit a more attractive travel option and thus eventually contribute to increases in ridership. However, the guidelines for station layouts and their assessments in transfer stations are not suggested so far. So the pedestrian pattern data (pedestrian walking distances and times, pedestrian approaching distances and times, pedestrian walking paths in the inside of stations) was collected and analyzed. Based on the results of the analysis, the ways to measure the quality of comfort for those who using transfer facilities were suggested using the times that pedestrians consume to transfer from a travel mode to another. The walking time of pedestrians at the inside of stations was also measured by pre-selected pedestrian pathways as the guidelines for station layout assessment in transfer facilities.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.5D
• /
• pp.597-604
• /
• 2009

The mass transit networks in Korea, such as buses, metro and subway, are co-related and the number of transfer points, in which a lot of pedestrian movement is generated, are rising. The functions of the transfer centers, in which several travel modes cross at a point, have to include convenience and comfort for pedestrians using the transfer centers, and such functions can make transit a more attractive travel option and thus eventually contribute to increases in ridership. However, the guidelines for station layouts and their assessments in transfer stations are not suggested so far. So the pedestrian pattern data (pedestrian walking distances and times, pedestrian approaching distances and times, pedestrian walking paths in the inside of stations) was collected and analyzed. Based on the results of the analysis, the ways to measure the quality of comfort for those who using transfer facilities were suggested using the times that pedestrians consume to transfer from a travel mode to another. The walking time of pedestrians at the inside of stations was also measured by pre-selected pedestrian pathways as the guidelines for station layout assessment in transfer facilities.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.5 no.1
• /
• pp.21-29
• /
• 2001

주차장, 버스터미널, 스타디움, 집회공간과 같은 낮은 고유진동수를 갖는 장경간 건축물에서는 저속 차량의 이동하중이나 보행자의 보행하중과 같은 동적하중에 의해 과도한 바닥판 진동이 발생할 수 있으며 이러한 진동은 건축물의 이용자에게 불쾌감을 일으켜 건축물의 사용성에 심각한 영향을 주게된다. 구조물에 가해지는 보행하중의 일반적인 적용방법은 분할된 요소의 절점을 따라 절점하중으로 가하는 것이다. 그러나 이러한 해석모델은 보행하중을 절점에만 가해야하는 제한적인 문제점을 가지고 있어 보폭 수만큼 절점을 생성시켜야 하며 보폭이 변하거나 절점이외에 하중이 작용할 경우 해석모델을 수정해야하는 번거로움이 있다. 본 연구에서는 보행하중에 대한 계측과 분석을 통하여 보행하중의 동적특성을 분석하였으며 계측한 보행하중을 예제구조물에 적용하였다. 그리고 보행하중에 의한 구조물 진동의 효율적인 해석을 위하여 구조물에 가해지는 보행하중을 등가의 절점하중으로 치환하는 방법을 제안하였으며 제안된 등가절점 하중의 타당성을 검증하기 위하여 예제구조물의 진동해석을 수행하였다.

• Smart Media Journal
• /
• v.4 no.2
• /
• pp.26-33
• /
• 2015

In this paper, we propose an efficient automatic pedestrian removal system from a frame in a video sequence. It firstly finds pedestrians from the frame using a Histogram of Oriented Gradient(HOG) / Linear-Support Vector Machine(L-SVM) classifier, searches for proper background patches, and then the patches are used to replace the deleted pedestrians. Background patches are retrieved from the reference video sequence and a modified feather blender algorithm is applied to make boundaries of replaced blocks look naturally. The proposed system, is designed to automatically detect object and generate natural-looking patches, while most existing systems provide search operation in manual. In the experiment, the average PSNR of the replaced blocks is 19.246

• Journal of Korean Society of Transportation
• /
• v.32 no.6
• /
• pp.628-637
• /
• 2014

The purpose of this study is to investigate the actual conditions of the mobility convenience facilities for pedestrians and their perception of the facilities, and thereby provide fundamental material necessary to establish a strategy of improving mobility convenience facilities. This study tried to analyze the characteristics of the mobility convenience facilities for pedestrians. Based on previous studies and "Report of Mobility Facilities of the Mobility Handicapped", this study first chose the evaluation items related to mobility convenience facilities, and then conducted a questionnaire survey and Importance-Performance Analysis (IPA). According to the study results, first, the item that needs intensive improvement was sidewalks, and the detailed indicators for sidewalks were walking safety, convenient facilities for the disabled, and pavement in order. Secondly, the items that need to be maintained were bus and crossroad. Thirdly, the low-ranking items were under-passageway and pedestrian overpass. And lastly, the items that need to be controlled were facilities for passenger terminals and bus terminals. Based on the comprehensive IPA result, this researcher judged the actual use conditions of the mobility convenience facilities in Buyeo-gun, Chungcheongnamdo. Therefore, it was found that it would be urgent to improve the direct walking environment on sidewalks. In this aspect, for future policy decision and facility maintenance, it is desirable to put the item in priority in terms of investment and come up with an improvement strategy.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.2
• /
• pp.26-36
• /
• 2008

Currently, the pedestrian signal timing model has no consideration on the characteristics of different land use patterns and pedestrian behaviors during pedestrian signal timing calculation. This study intended to propose pedestrian signal timing models that could reflect the inherent characteristics of pedestrian and land use patterns. For this study, three major variables affecting the length of signal timing were identified: walking speed, perception-reaction time, and density-delay time. Then, the representative values of each variable were estimated through the field studies. By combining this information, several pedestrian signal timing models were developed. The data in this paper can be used for future references, and the walking environments for pedestrians could be improved by applying the models suggested in this paper.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.5
• /
• pp.692-699
• /
• 2008

This paper describes optimal operation method using recognition of walker's will for a robotic walker. Recently, walking aid system has been required according to the increase of elder and handicapped person. However, most of walking aid system don't have actuator for its movement. Unfortunately, standard frames have weakness for the movement to upward/download direction of slope. So, active type walking aids are interested, but it is not easy to control. In this paper, we adapt user's will system that can recognize walking direction and speed. First, FSR(Force Sensing Register) is applied to measure user's will to walk. And then, fuzzy algorithm is used for determining optimal wheel velocity and direction of the walking aid. From the result, walking aid can move smoothly and safely following the user's will. The walking aid can help user to walk more optimally. Here, all the processes are verified experimentally in the real world.

• Journal of Korean Society of Transportation
• /
• v.34 no.3
• /
• pp.207-221
• /
• 2016

In Korea, older pedestrian accounted for 57% of all pedestrian deaths although a ratio of older pedestrian accidents to total pedestrian accidents was only 25.9%. Though ageing population problem becomes more challenging for road safety, little is know about the behaviour of older pedestrian's behaviour. This study aimed to identify road crossing behaviour of older pedestrian at three-lane unsignalized crosswalks using video image analysis and to compare the behaviour of older pedestrian to younger one by indicators including approaching speed, the number of walking steps and other factors. The results showed that there was a difference of approaching time at kerb, waiting time at kerb, the number of glances at kerb, and the number of glances at crossing between two groups under the situation of car approaching to crosswalks. It also showed that older pedestrian usually spent 1.16 times more than younger pedestrian to walk across the crosswalk with only 84.4% of walking speed of younger pedestrian. The number of steps of older pedestrian for road crossing was 1.12 times higher with 90% shorter steps than younger pedestrian. It was concluded that older pedestrian usually decided to walk across in case of 1.67 times longer headway than younger pedestrian's decision. These results could be applied in road and facility design for better safety of older pedestrians.

• ICROS
• /
• v.21 no.2
• /
• pp.25-30
• /
• 2015

본 논문에서는 간병인의 도움없이 자가 보행 재활에 효과적으로 사용될 수 있는 새로운 개념의 가슴 착용형 로봇을 개발하였다. 개발된 로봇의 특징은 크게 세 가지로 나뉜다. 첫째, 구조적 특징으로써, 하박에 착용하는 기존 지팡이 타입의 엘보 크러치와 달리 개발된 로봇은 가슴에 착용되어 착용자의 두 팔을 자유롭게 하는 동시에 팔의 부담을 제거하여 준다. 둘째는 구동 알고리즘의 특징으로써, 가슴부에 부착된 압력센서로부터 사용자의 보행의도를 자동적으로 인식하여 로봇의 다리를 이동시킨다. 또한 착용자의 안전을 위해 초음파 센서를 이용하여 착용자 전방에 장애물이 나타날 시 보행을 멈추고 경고음을 발생시킨다. 마지막으로, 스카치요크 메커니즘을 사용하여 지지다리의 상승과 하강 시 지면 반발력으로 인하여지지 발 상/하강 모터에 과도한 토크가 부과되지 않도록 하였다. 이러한 세 가지 특징으로부터 개발된 로봇이 자가 보행 재활에 효과적으로 사용될 수 있음을 실험적으로 보였으며, EMG (Electromyography) 센서를 이용하여 근력 보조 성능을 정량적으로 검증하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.61-68
• /
• 2022

In this paper, we propose a system to predict the GPS trajectory of a pedestrian based on a deep learning model. Pedestrian trajectory prediction is a study that can prevent pedestrian danger and collision situations through notifications, and has an impact on business such as various marketing. In addition, it can be used not only for pedestrians but also for path prediction of unmanned transportation, which is receiving a lot of spotlight. Among various trajectory prediction methods, this paper is a study of trajectory prediction using GPS data. It is a deep learning model-based study that predicts the next route by learning the GPS trajectory of pedestrians, which is time series data. In this paper, we presented a data set construction method that allows the deep learning model to learn the GPS route of pedestrians, and proposes a trajectory prediction deep learning model that does not have large restrictions on the prediction range. The parameters suitable for the trajectory prediction deep learning model of this study are presented, and the model's test performance are presented.