• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.6
• /
• pp.1562-1582
• /
• 2024

The prediction of pedestrian trajectory is conducive to reducing traffic accidents and protecting pedestrian safety, which is crucial to the task of intelligent driving. The existing methods mainly use the past pedestrian trajectory to predict the future deterministic pedestrian trajectory, ignoring pedestrian intention and trajectory diversity. This paper proposes a multi-modal trajectory prediction model that introduces pedestrian intention. Unlike previous work, our model makes multi-modal goal-conditioned trajectory pedestrian prediction based on the past pedestrian trajectory and pedestrian intention. At the same time, we propose a novel Gate Recurrent Unit (GRU) to process intention information dynamically. Compared with traditional GRU, our GRU adds an intention unit and an intention gate, in which the intention unit is used to dynamically process pedestrian intention, and the intention gate is used to control the intensity of intention information. The experimental results on two first-person traffic datasets (JAAD and PIE) show that our model is superior to the most advanced methods (Improved by 30.4% on MSE_0.5s and 9.8% on MSE_1.5s for the PIE dataset; Improved by 15.8% on MSE_0.5s and 13.5% on MSE_1.5s for the JAAD dataset). Our multi-modal trajectory prediction model combines pedestrian intention that varies at each prediction time step and can more comprehensively consider the diversity of pedestrian trajectories. Our method, validated through experiments, proves to be highly effective in pedestrian trajectory prediction tasks, contributing to improving traffic safety and the reliability of intelligent driving systems.

• Journal of Auto-vehicle Safety Association
• /
• v.11 no.3
• /
• pp.37-42
• /
• 2019

This paper presents an autonomous acceleration planning algorithm for pedestrian collision avoidance at urban. Various scenarios between pedestrians and a vehicle are designed to maneuver the planning algorithm. To simulate the scenarios, we analyze pedestrian's behavior and identify limitations of fusion sensors, lidar and vision camera. Acceleration is optimally determined by considering TTC (Time To Collision) and pedestrian's intention. Pedestrian's crossing intention is estimated for quick control decision to minimize full-braking situation, based on their velocity and position change. Feasibility of the proposed algorithm is verified by simulations using Carsim and Simulink, and comparisons with actual driving data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.1
• /
• pp.180-194
• /
• 2015

On roads vehicles are the bossy, while pedestrians are the frangible. The current paper has a purpose for contributing to pedestrian's safety. First, it studies the association between demographic parameters and TPB(Theory of Planned Behavior)'s variables(pedestrian's attitude toward crossing behavior in roads, personal norm, etc.) and his/her crossing intention, perceived risk while crossing, and the experience of past traffic accidents. Its sample comes from a specific population(college students). Further, the present study endeavors to explain the portion of human cognitive failure/error, impulsiveness, time perspective, and probabilistic/math-logical judgment ability in pedestrian's riky crossings on roads. Research results found that TPB variables and such a few human characteristics have some significant association with the risky crossing intention on the road. Considering the human psychological portion in pedestrian accidents would help us prevent the accidents and reduce unhappiness of the accidents and, further, economic loss and insurance expenditure related with the accidents.

• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.440-448
• /
• 2015

A pedestrian collision warning system which makes a judgement of pedestrian's intention to help avoiding hitting accidents is proposed. This system uses the image sequences obtained from a car black box as well as vehicle's speed obtained from a GPS. It detects pedestrians, if any, based on the Histogram of Gradient method and extracts several information such as the pedestrian's relative positions, the direction of motion vectors, and distance between vehicle and pedestrian . A fuzzy logic based on these extracted information is applied to analyze the pedestrian's safety levels. When the safety level is determined to be danger, an alarm is triggered to the driver. The performance of the proposed algorithm is tested under various driving scenarios, which shows it works successfully in real-time.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.3
• /
• pp.68-83
• /
• 2019

The number of pedestrian traffic accident fatalities is three times the number of car accidents in South Korea. Serious accidents are caused especially at intersections when the vehicle turns to their right. Various pedestrian collision warning services have been developed, but they are insufficient to prevent dangerous pedestrians. In this study, P2CWS is developed to warn approaching vehicles based on the pedestrians' characteristics. In order to evaluate the performance of the service, actual pedestrian data were collected at the intersection of Daejeon, and comparative analysis was carried out according to pedestrian characteristics. As a result, the performance analysis showed a higher accordance when the characteristics of the pedestrian is considered. Accordingly, we can conclude that identifying pedestrian characteristics in predicting the pedestrian crossing is important.

• Journal of Environmental Science International
• /
• v.16 no.2
• /
• pp.159-169
• /
• 2007

The overall purpose of this study was to investigate pedestrians and commercial business men and employers' recognition on management of street trees and green spaces along street sides. The followings were main results of this study. Both pedestrians and commercial business men and employers mostly perceived positive influence of street trees on urban environment and their business. In addition, pedestrians gave higher scores of positive influence of trees function than those of commercial business men and employers. Pedestrians showed strong intention to participate management activities of street trees or green spaces. This study indicated that negative perception on street trees came from improper management rather than existence of street trees. Therefore, more intensive management actions are needed.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.37 no.2
• /
• pp.35-42
• /
• 2014

The purpose of this study is to analyze job stress factors of hospital workers, which has an effect on their turnover intention. For identifying the influences on turnover intention, types of hospitals (university hospital, general hospital, private hospital) and types of workers(office workers, technical workers, and nursing staffs) were categorized. We went to the hospitals and carried out the survey under the cooperation with the concerned hospitals. The period of survey was from 23. Sep. 2013 to 30. Oct. 2013, and 293 worker participated in the survey. On the basis of the previous study, the measurement of job stress factors and turnover intention was set up as the survey method, and its reliability and validity were measured. The stress factors were subdivided into seven factors; occupational climate, organizational system, autonomy job control, uncertainty of getting a new job, job ability to perform, job demand, job ambiance. The value of job stress factors by the measuring instrument, Cronbach's Alpha, was 0.805 and the value of the subordination variable of turnover intention was 0.881. IBM SPSS Statistics 21 was used as the statistic analysis tool and the descriptive statistics about job stress factors. As a result, the turnover intention were analyzed depending on the types of hospitals, job groups, working years, and gender. Result shows that the job stress factors are differed according to the types of hospitals, and these job stress factors have influence on turnover intention. Therefore, it could be considered that, if the hospital managers find out the major job stress factors of their employees and resolve them in advance, the job stress of the hospital workers and their turnover intention can be reduced.

• Journal of Acupuncture Research
• /
• v.35 no.2
• /
• pp.69-74
• /
• 2018

Background: We conducted a cross-sectional study to analyze the pain characteristics and satisfaction scores in traffic accident (TA) patients seeking Korean medicine treatment. Methods: A survey was conducted in 845 outpatients who visited 10 Korean medicine institutions due to TA-associated symptoms from February 25th, 2016 to March 9th, 2016. The questionnaire included information about patient sociodemographic characteristics, accident circumstance details, pain levels, treatment methods, satisfaction and pre-existing musculoskeletal disorders. All statistical analyses were performed using STATA 14.0. Results: A total 754 of the 845 respondents had experienced acute pain of onset within 1-2 days. Pain in the neck or low back was most common, and low back pain (LBP) was more prevalent in pedestrian-vehicle accident cases. Patients showed highest satisfaction with pharmacopuncture treatment, followed by acupuncture and Chuna manual therapy. Although treatments were not completed at the time of the survey, the majority of patients were satisfied with the Korean medicine treatments they received and indicated their intent to reuse this treatment in the future. The degree of pain reduction after treatment was a factor that influenced patient satisfaction with and intention to reuse Korean medicine. Conclusion: This study determined the characteristics and status of TA patients using Korean medicine and suggests the need for further more inclusive studies.

• Journal of the Korean Institute of Rural Architecture
• /
• v.13 no.3
• /
• pp.61-72
• /
• 2011

The purpose of this study is to examine and investigate the characteristics of locational facilities and the purchase and leisure patters of residents with its focus on downtown streets of Yeongam-eup which is a eup-level small town. In the subject downtown streets, commercial and residential functions coexisted. While most locational facilities were small-scale sale(buy), food(eat), and employment(public institutions) facilities which were needed for neighborhood life and supporting daily life, the lack of facilities which supported leisure life(enjoy) and represented small town identity was found. The most common frequency of using downtown streets by residents was 'almost everyday'; the most common intention to use was 'to purchase daily things'; and the most common purchase good was 'groceries', followed by farming machines, books, and stationery. It suggested that the use of downtown streets was characterized by daily neighborhood life. In particular, it was found that expensive goods(more than 500,000 won) were commonly purchased in neighboring middle or large cities. Thus, it is necessary to consider the option and professionality of goods. Finally, it is necessary to consider residents' accessibility through reorganizing a street form from car-focused to pedestrian-focused.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.1
• /
• pp.415-423
• /
• 2021

Citizen participation and Living Lab are attracting interest as one of the major strategies for the success of smart cities. In a Living Lab, citizens, who are the end-users of technology, participate in the search for alternatives to define and solve problems and repeat experiments to verify alternatives in a circular process. The purpose of this research was to present an operating model of a citizen-participating online community platform to improve urban problems, implement and test it, and show its applicability. To this end, an operation model of a citizen-participating online community platform was proposed to improve urban problems. An online platform was designed and implemented to reflect the functions pursued by the operation model. Finally, a pilot test for the function was performed using the Oma Elementary School case located in Ilsan, Goyang-si, Gyeonggi-do. The operating model was designed with the city's pedestrian environment and children. As a result, the sharing and communicating process of urban issues among community members worked appropriately according to the designed intention. The Living Lab coordinator could visualize and view urban issues posted by users on a map based on location information. Visualizing the urban problem as a heat map confirmed that urban problems were concentrated in a specific area.