• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.141-148
• /
• 2021

In some intersections or busy traffic roads, there are more pedestrians in a specific period of time, and there are many traffic accidents caused by road congestion. Especially at the intersection where there are schools nearby, it is particularly important to protect the traffic safety of students in busy hours. In the past, when designing traffic lights, the safety of pedestrians was seldom taken into account, and the identification of motor vehicles and traffic optimization were mostly studied. How to keep the road smooth as far as possible under the premise of ensuring the safety of pedestrians, especially students, will be the key research direction of this paper. This paper will focus on person, motorcycle, bicycle, car and bus recognition research. Through investigation and comparison, this paper proposes to use YOLO v4 network to identify the location and quantity of objects. YOLO v4 has the characteristics of strong ability of small target recognition, high precision and fast processing speed, and sets the data acquisition object to train and test the image set. Using the statistics of the accuracy rate, error rate and omission rate of the target in the video, the network trained in this paper can accurately and effectively identify persons, motorcycles, bicycles, cars and buses in the moving images.

• Journal of the Korean Society of Safety
• /
• v.33 no.1
• /
• pp.135-141
• /
• 2018

Rotary that causes traffic delays and safety issues by high-speed entry vehicles is currently being improved to roundabout. The operational difference between rotary and roundabout can cause driver's confusion and traffic accident. The purpose of this study is to develop the accident rate models which explain the factors related to the accidents by land use and intersection type. The main results are as follows. First, the null hypotheses that the type of land use and two intersections do not affect the accident rate are rejected. Second, the conflicting factors such as the number of crosswalk and bicycle lane should be carefully considered to reduce traffic accident at rotary. In the case of roundabout, greater than 3.5 m in circulatory lane width and two circulatory lane are analyzed to be important to prevent the accidents. Finally, the commercial and mixed areas are evaluated to be weak to traffic accidents than residential area.

• Korean Journal of Environment and Ecology
• /
• v.28 no.3
• /
• pp.365-373
• /
• 2014

This study is to analyze the physical environment and conduct spatial data for bicycle road system in changwon. Index for evaluation index was developed based on literatures. Then the level of importance and weight have been modified through experts review. Finally, index with eight categories such as greenness(40% over), bicycle road connectivity(1.8, 9.8%), road type bike(bicycle lane, 24.4%), pave type(asphalt 72.5%), illegal parking(none, 93.9%), bike road surface visibility(exist, 46.8%), vehicle speed limits(30km, under), vehicle traffic(500/hr under, 44.3%) have been applied to empirical investigation. Collected data has been hierarchically classification by ArcGIS Program. The Highest grades(score 31-35, level 1) occupied 35% of target destination. High level of greenness and load type has contributed to high score. In addition, average level of greenness of those destination was 35% and higher, which provide high degree of security and freshness for bicycle riding. Meanwhile, lowest level(level 5, which earned 15 point or less) occupied 24.5%. illegal parking, low level of greenness, and no surface sign caused low score.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.8
• /
• pp.4077-4085
• /
• 2013

The purpose of this study is to analyze relationships between compact city development and residents' shopping trips in Seoul. Compact city planning factors are classified into land use and traffic environment. The main data source used for this research is 2006 Household Travel Survey data, then a statistic analysis was carried out by applying random intercept logit model. Analysis shows that a high level of residential density increases residents' local shopping. Also, a high level of residential density and land use mix results in more uses of public transportation, bicycle and walking for shopping. Also, more access to public transportation leads to more use of public transportation for shopping. Therefore, compact city development will have a positive impact on activating the use of public transportation, bicycle and walking for shopping.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.1290-1293
• /
• 2021

Currently, blind people are experiencing a lot of inconvenience in their daily lives. In order to provide helpful service for the visually impaired, this study was carried out to make a new smart glasses that transmit information monitoring walking environment in real-time object recognition. In terms of object recognition, YOLOv4 was used as the artificial intelligence model. The objects, that should be identified during walking of the visually impaired, were selected, and the learning data was populated from them and re-learning of YOLOv4 was performed. As a result, the accuracy was average of 68% for all objects, but for essential objects (Person, Bus, Car, Traffic_light, Bicycle, Motorcycle) was measured to be 84%. In the future, it is necessary to secure the learning data in more various ways and conduct CNN learning with various parameters using darkflow rather than YOLOv4 to perform comparisons in the various ways.

• International Journal of Highway Engineering
• /
• v.17 no.2
• /
• pp.123-134
• /
• 2015

PURPOSES : The key point of a multimodal LOS (level-of-service) evaluation system is that all of the modes are mutually associated to determine each mode's LOS. For example, the LOS of the bicycle mode is measured based on not only bicycle volumes, but also automobile volumes. However, the Korea Highway Capacity Manual (KHCM) still focuses on the automobile mode in evaluating the LOS of the roads. Additionally, the KHCM's LOS of the other modes, except for the automobile, is not consistent with actual road conditions. The KHCM, therefore, needs to develop and introduce a multimodal LOS system in order to evaluate the service conditions more accurately. METHODS: As a preliminary step to the introduction of multimodal LOS research, in this study the current problem of the KHCM's LOS system through a close review and comparison with other HCMs (highway capacity manuals) was identified. Secondly, a field survey and investigation of the urban streets to apply the HCM's multimodal LOS system was conducted. Finally, a comparison analysis of the results of the HCM and KHCM LOS was performed. RESULTS: In the study, it was found that the results of the LOS for the automobile mode did not show a significant difference between the HCM and KHCM. However, the LOS of the bicycle and pedestrian mode tended to be worse in the multimodal LOS system, which results from considering the effects of the automobile mode. Moreover, it was found that many cases have the potential to improve the overall LOS conditions, while reducing the automobile capacity. CONCLUSIONS: With the introduction of the multimodal LOS system, road diet and complete streets can be easily applied to ans actual road improvement project. Ultimately, the multimodal LOS system should be introduced into the KHCM, which can then be applied to traffic impact studies and other road improvement projects for more accurate evaluations.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.861-866
• /
• 2022

Seoul introduced the shared bicycle system, "Seoul Public Bike" in 2015 to help reduce traffic volume and air pollution. Hence, to solve various problems according to the supply and demand of the shared bicycle system, "Seoul Public Bike," several studies are being conducted. Most of the research is a strategic "Bicycle Rearrangement" in regard to the imbalance between supply and demand. Moreover, most of these studies predict demand by grouping features such as weather or season. In previous studies, demand was predicted by time-series-analysis. However, recently, studies that predict demand using deep learning or machine learning are emerging. In this paper, we can show that demand prediction can be made a little better by discovering new features or ordering the importance of various features based on well-known feature-patterns. In this study, by ordering the selection of new features or the importance of the features, a better coefficient of determination can be obtained even if the well-known deep learning or machine learning or time-series-analysis is exploited as it is. Therefore, we could be a better one for demand prediction.

• Journal of Trauma and Injury
• /
• v.19 no.1
• /
• pp.74-80
• /
• 2006

Purpose: For prevention and suitable administration, the effect of age on the severity of injuries in traffic accidents should be considered when evaluating a patient, but there have not been enough epidemiological studies that evaluate the age factor in traffic accidents. For that reason, we investigated old-aged patients who were involved in traffic accidents (65 years old or more) and who were admitted to the emergency department of a college hospital in an urban city of Korea. Methods: We collected data from traffic-accident patients who came to the emergency room of a university hospital in Seoul from Jan.1, 2004 to Dec.31, 2005. We compared their abilities to ambulate and the RTSs (Revised trauma scores) by using a LSD (least significant difference), linear regression. Results: A total of 1460 patients were included. The mean RTS of all traffic-accident patients was $7.77{\pm}0.280$. The scores for drivers and passengers, motor-cycle drivers and passengers, bicycle drivers and passengers, and pedestrians were $7.79{\pm}0.21$, $7.78{\pm}0.22$, $7.54{\pm}0.25$, $7.77{\pm}0.20$, and $7.80{\pm}0.21$ respectively (p=0.000). There was no statistically significant difference between the RTS of patients over 65 years and that of other patients. In a regression analysis, the number of patients over 45 ages who were able to ambulate was lower than that of younger people, independently of other influencing factors (B=-0.330, R-square = 0.243, p=0.000). Conclusion: We expected that RTS of old age group more than 65 years old will significantly lower than that of others, but there was no statistically significant difference.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.5
• /
• pp.79-90
• /
• 2019

This study aims to develop time headway distribution models of bicycle traffic flow in a uninterrupted bikeway. The sample data were collected and classified into two groups of traffic volume levels. The lower level traffic volume is defined to be under 8 bicycles per minute, and the higher one is greater or equal to 8 bicycles per minute. The data aggregation interval size was set to be 0.5-second. Four distribution models including normal distribution, negative exponential distribution, shifted negative exponential distribution, and Pearson III distribution were tested, and Chi-square test results shows that the negative exponential distribution and the shifted negative exponential distribution are well fitted to the sample data. Another test results with different sample data also shows the same conclusion.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.139-149
• /
• 2021

Ddareungi, a public bicycle service in Seoul, establishes itself as a means of daily transportation for citizens in Seoul. We speculated that the pattern of using Ddareungi may have changed since COVID-19. This study explores changes in using Ddareungi after COVID-19 with descriptive statistical analysis and network analysis. The analysis results are summarized as follows. The average traveling distance and average traveling speed have decreased over the entire time in a day since COVID-19. The round trip rate has increased at dawn and morning and has decreased in the evening and night. The average weighted degree and average clustering coefficient have decreased, and the modularity has increased. The clusters, located north of the Han River in Seoul, had a similar geographic distribution before and after COVID-19. However, the clusters, located south of the Han River, had different geographic distributions after COVID-19. Traveling routes added to the top 5 traffic rankings after COVID-19 had an average traveling distance of fewer than 1,000 meters. We expect that the results of this study will help improve the public bicycle service in Seoul.