• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.1
• /
• pp.35-45
• /
• 2013

A autonomous vehicle requires improved and robust perception systems than conventional perception systems of intelligent vehicles. In particular, single sensor based perception systems have been widely studied by using cameras and laser radar sensors which are the most representative sensors for perception by providing object information such as distance information and object features. The distance information of the laser radar sensor is used for road environment perception of road structures, vehicles, and pedestrians. The image information of the camera is used for visual recognition such as lanes, crosswalks, and traffic signs. However, single sensor based perception systems suffer from false positives and true negatives which are caused by sensor limitations and road environments. Accordingly, information fusion systems are essentially required to ensure the robustness and stability of perception systems in harsh environments. This paper describes a perception system for autonomous vehicles, which performs information fusion to recognize road environments. Particularly, vision and laser radar sensors are fused together to detect lanes, crosswalks, and obstacles. The proposed perception system was validated on various roads and environmental conditions with an autonomous vehicle.

• International Journal of Highway Engineering
• /
• v.19 no.4
• /
• pp.69-78
• /
• 2017

PURPOSES : In this study, we analyzed the road crossing behavior of older pedestrians on a mid-block signalized crosswalk, and compared it to that of younger pedestrians. In addition, we analyzed the correlation between accidents involving older pedestrians while crossing roads and their behavioral characteristics. Finally, we confirmed the reasons for an increase in accidents involving older pedestrians. METHODS : First, 30 areas with the highest incidence of accidents involving older pedestrians while crossing roads were selected as target areas for analysis. Next, we measured the start-up delay (the time elapsed from the moment the signal turns green to the moment the pedestrian starts walking) and head movement (the number of head turns during crossing a road) of 900 (450 older and 450 younger) pedestrians. The next step was to conduct a survey and confirm the differences in judgment between older and younger pedestrians about approaching vehicles. Finally, we analyzed the correlation between the survey results and traffic accidents. RESULTS : The average start-up delay and head movement of the older pedestrians was 1.58 seconds and 3.15 times, respectively. A definite correlation was obtained between head movement and the frequency of pedestrian traffic accidents. The results of our survey indicate that 17.3% of the older pedestrians and 7.8% of the younger pedestrians have a high crash risk. CONCLUSIONS : Behavioral characteristics of older pedestrians were closely correlated with accidents involving older pedestrians while crossing roads in mid-block signalized crosswalks. Our study indicates that in order to reduce the number of accidents involving older pedestrians, it is necessary to develop an improvement plan including measures such as installation of safety facilities taking the behavioral characteristics of older pedestrians into consideration and their safety education.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.5
• /
• pp.138-150
• /
• 2020

Pedestrians are the most vulnerable road users. According to one analysis of traffic accidents over a five year period, pedestrians accounted for about 40% of all road traffic deaths in South Korea. Although some policy and engineering approaches have been taken to reduce and prevent traffic accidents, the annual accident change rate is -0.7%, which is insufficient. This study verifies the effectiveness of presenting visual messages to pedestrians and the effect from adding auditory messages to the visual messages. The experiment was conducted on crosswalks adjacent to an intersection, and safety behaviors were recorded for a total of 898 pedestrians and considered sufficient. As a result of the study, overall pedestrian safety behavior improved when both visual and auditory messages were presented, rather than just visual messages. Therefore, the results indicate it is more effective to provide a mixed visual/auditory form of messages, rather than providing single stimulus messages.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.61-68
• /
• 2024

Despite the continuous efforts to mitigate pedestrian accidents at crosswalks, the problem persist. Vulnerable groups, including the elderly and disabled individuals are at a risk of being involved in traffic incidents. This paper proposes the implementation of object detection algorithm using the YOLO v5 model specifically for pedestrians using assistive devices like wheelchairs and crutches. For this research, data was collected and utilized through image crawling, Roboflow, and Mobility Aids datasets, which comprise of wheelchair users, crutch users, and pedestrians. Data augmentation techniques were applied to improve the model's generalization performance. Additionally, ensemble techniques were utilized to mitigate type 2 errors, resulting in 96% recall rate. This demonstrates that employing ensemble methods with a single YOLO model to target transportation-disadvantaged individuals can yield accurate detection performance without overlooking crucial objects.

• International Journal of Highway Engineering
• /
• v.9 no.4
• /
• pp.33-43
• /
• 2007

Because usually signal controllers on the crosswalks of mid-block provide pedestrian signals every cycle based on the fixed signal plan, pedestrian signals are provided even when there is no pedestrian demand. Consequently, signal is operated inefficiently and this may cause drivels to experience useless delay or violate the signal. Even though recently pushbuttons have been installed to improve the efficiency of pedestrian signal control in the crosswalks of mid-block and the pedestrian safety. they are not spread out national-wide in Korea because of the cost of the pushbutton equipments and the lack of an acknowledgement of the efficiency of the pushbutton. In this study, the effectiveness of the pushbutton on saving the vehicle delay was verified through before and after study in 4 study sites using a traffic micro-simulation model, VISSIM. To evaluate the viability of the pushbutton, a benefit/cost analysis was also performed for 4 study sites. It was found that B/C ratio of all of 4 study sites was greater than 1. The sensitivity analysis for the traffic volume and pedestrian volume were performed to identify the impact of the both volume on the operation of pushbutton. And, a benefit/cost analysis was performed for all scenarios. It was found that when the pedestrian volume is greater than 90ped/h, the pedestrian signal was operated same as the fixed signal plan. That is, there is no benefit of pushbutton at all once the pedestrian volume is greater than 90ped/h. When the pedestrian volume is equal to or less than 90ped/h and the traffic volume is greater than 2,500veh/h, B/C ratio is greater than 1. Also it was found that as traffic volume increases and pedestrian volume decreases, the benefit increases. In this study, the criteria for installation of pushbutton on the crosswalks of mid-block are developed through the sensitivity analysis and benefit/cost analysis. The results of this study may be used as a criteria for expansion of pushbutton system.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.5
• /
• pp.1135-1146
• /
• 2015

This thesis aims to improve the safety of bicycle traffic for activating the use of bicycle, main means of non-powered and non-carbon transportation in order to cope with worldwide crisis such as climate change and energy depletion and to implement sustainable traffic system. In this regard, I analyzed the problem of bicycle roads currently installed and operated, and developed the bicycle accident forecasting model. Following are the processes for this. First, this study presented the current status of bicycle road in Korea as well as accident data, collect the data on bicycle traffic accidents generated throughout the country for recent 3 years (2009~2011) and analyzed the features of bicycle traffic accidents based on the data. Second, this study selected the variable affecting the number of bicycle accidents through accident feature analysis of bicycle accidents at Jeollanam-do, and developed accident forecast model using the multiple regression analysis of 'SPSS Statistics 21'. At this time, the number of accidents due to extension per road types (crossing, crosswalk, other single road) was used. To verify the accident forecast model deduced, this study used the data on bicycle accident generated in Gwangju, 2011, and compared the prediction value with actual number of accidents. As a result, it was found out that reliability of accident forecast model was secured through reconciling with actual number of cases except certain data. Third, this study carried out field survey on the bicycle road as well as questionnaire on satisfaction of bicycle road and use of bicycle for analysis of bicycle road problems, and presented safety improvement measures for the problems deduced as well as bicycle activation plans. This study is considered to serve as the fundamental data for planning and reorganizing of bicycle road in the future, and expected to improve safety of bicycle users and to promote activation of bicycle use as the means of transportation.