• 대한교통학회지
• /
• 제19권6호
• /
• pp.161-170
• /
• 2001

차량검출은 교통량 관측(모니터링)을 위해서 필요한 가장 기본적인 요소이다. 영상을 기반으로 한 교통정보추출 시스템은 다른 방식을 이용하는 시스템들과 비교했을 때 몇 가지 두드러진 장점을 가지고 있다. 그러나 영상기반 시스템에서는 영상에 포함된 그림자가 차량검출의 정확도를 저해하는 요소로 작용하는 데, 특히 이동 중인 차량에 의해서 발생하는 환성 그림자는 심각한 성능저하를 야기할 수 있다. 본 논문에서는 차량검출과 그림자 영향 제거를 위해서 배경 빼기와 에지 검출을 결합한 새로운 접근방법을 제안하였다. 제안한 방법은 노변의 지형지물에 의해서 발생하는 비활성 그림자가 크게 증가하는 상황에서도, 98(%)이상의 차량검출 정확도를 나타내었다. 본 논문에서 제안한 차량검출 방법을 기반으로 하여, 차량 추적, 차량 계수, 차종 분류, 그리고 속도 측정을 수행하여 각 차로의 부하를 나타내는 데 사용되는 차량 흐름과 관련된 여러 가지 교통정보를 추출하였다.

• International Journal of Precision Engineering and Manufacturing
• /
• 제6권4호
• /
• pp.3-7
• /
• 2005

Recently, vehicle simulators are widely used to evaluate driver s responses and driver assistance systems. It needs much effort to construct the virtual driving environment for a vehicle simulator. In this study, it is described how to make effectively the roads and the driving environment for a vehicle simulator. GIS (Geographic Information System) is used to construct the roads and the environment effectively. Because the GIS is the integrated system of geographical data, it contains useful data to make virtual driving environment. First, boundaries and centerlines of roads are extracted from the GIS. From boundaries, the road width is calculated. Using centerlines, mesh models of roads are constructed. The final graphic model of roads is constructed by mapping road images to those mesh models considering the number of lanes and the kind of surface. Data of buildings from the GIS are extracted. Each shape and height of building is determined considering the kind of building to construct the final graphic model of buildings. Then, the graphic model of roadside trees is constructed to decide their locations. Finally, the driving environment for driving simulator is constructed by converting the three graphic models with the graphic format of Direct-X and by joining the three graphic models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권2호
• /
• pp.383-403
• /
• 2021

With the development of mobile edge computing (MEC), some late-model application technologies, such as self-driving, augmented reality (AR) and traffic perception, emerge as the times require. Nevertheless, the high-latency and low-reliability of the traditional cloud computing solutions are difficult to meet the requirement of growing smart cars (SCs) with computing-intensive applications. Hence, this paper studies an efficient offloading decision and resource allocation scheme in collaborative vehicular edge computing networks with multiple SCs and multiple MEC servers to reduce latency. To solve this problem with effect, we propose a context-aware offloading strategy based on differential evolution algorithm (DE) by considering vehicle mobility, roadside units (RSUs) coverage, vehicle priority. On this basis, an autoregressive integrated moving average (ARIMA) model is employed to predict idle computing resources according to the base station traffic in different periods. Simulation results demonstrate that the practical performance of the context-aware vehicular task offloading (CAVTO) optimization scheme could reduce the system delay significantly.

• 한국산업융합학회 논문집
• /
• 제23권6_2호
• /
• pp.1025-1032
• /
• 2020

In this paper, we propose a method to classify road weather conditions into rain, fog, and sun using a SVM (Support Vector Machine) classifier after extracting weather features from images acquired in real time using an optical sensor installed on a roadside post. A multi-dimensional weather feature vector consisting of factors such as image sharpeness, image entropy, Michelson contrast, MSCN (Mean Subtraction and Contrast Normalization), dark channel prior, image colorfulness, and local binary pattern as global features of weather-related images was extracted from road images, and then a road weather classifier was created by performing machine learning on 700 sun images, 2,000 rain images, and 1,000 fog images. Finally, the classification performance was tested for 140 sun images, 510 rain images, and 240 fog images. Overall classification performance is assessed to be applicable in real road services and can be enhanced further with optimization along with year-round data collection and training.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4573-4594
• /
• 2020

Announcement protocol in Internet of Vehicles (IoV) is an intelligent application to enhance public safety, alleviate traffic jams and improve transportation quality. It requires communication between vehicles, roadside units and pedestrian to disseminate safety-related messages. However, as vehicles connected to internet, it makes them accessible globally to a potential adversary. Safety-related application requires a message to be reliable, however it may intrude the privacy of a vehicle. Contrarily, if some misbehaviour emerges, the malicious vehicles must be able to traceable and revoke from the network. This is a contradiction between privacy and accountability since the privacy of a user should be preserved. For a secure communication among intelligent entities, we propose a novel announcement protocol in IoV using group signature. To the best of our knowledge, our work is the first comprehensive construction of an announcement protocol in IoV that deploys group signature. We show that our protocol efficiently solves these conflicting security requirements of message reliability, privacy and accountability using 5G communication channel. The performance analysis and simulation results signify our work achieves performance efficiency in IoV communication.

• 생태와환경
• /
• 제54권2호
• /
• pp.142-150
• /
• 2021

To analyze the distribution characteristics of alien plants in various habitat types, 249 sites were selected from four administrative districts in the Gyeongsang region of Korea. The survey was conducted across nine different habitat types. A total of 115 species of alien plants were collected; comprising 23 families, 73 genera, 112 species, and 3 varieties. Species from the family Compositae were the most common at 33.0%. Raunkiaer's life forms had the highest occurrence rate with 70 species(60.9%) of therophytes(Th) followed by 30 species (26.1%) of hemicryptophytes (H) and 8 species (7.0%) of geophytes (G). The distributions of alien plant species per habitat type were: 81 species on the roadside; 80 species on vacant lots and artificial habitats; 67 species in streams; 53 species in grasslands; 47 species in cultivated lands; and 39 species on the coast. Since 2017, the number of alien plants has increased in Gyeongju-si, Cheongdo-gun, and Pohang-si, and decreased in Ulsan Metropolitan-si. In each region, 614 taxa were observed. The invasive alien species, Sicyos angulatus, Hypocaeris radicata, and Solanum carolinense, were observed for the first time and are expected to further increase the disturbance of the ecosystem.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권4호
• /
• pp.1216-1231
• /
• 2021

With the increase in the population of our cities and the rapid increase in the number of private cars, urban traffic has become more and more congested. At this stage, urban public transportation has become one of the main ways to improve urban traffic congestion. Aiming at the problem of how to improve the basic capacity of buses in multi-line transfer stations, this paper conducts simulation research based on anylogic software. Through micro-simulation analysis of vehicles entering, stopping, and exiting the station, combined with the delay model theory, the vehicle is given Stop organization optimization and station layout improvement methods, so that vehicles can run in the station more stably, smoothly and safely. Case analysis shows that applying this method to the roadside parking problem, the main and auxiliary bus stations have a significant improvement in operating capacity compared with the conventional tandem double bus stations, and the service level of the main and auxiliary bus stations has been significantly improved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권2호
• /
• pp.609-631
• /
• 2022

The main goal of VANETs is to improve the safety of all road users. Therefore, the accuracy and trustworthiness of messages transmitted in VANETs are essential, given that life may rely on them. VANETs are provided with basic security services through the use of public key infrastructure-based authentication. However, the trust of users is still an open issue in VANETs. It is important to prevent bogus message attacks from internal vehicles as well as protect vehicle privacy. In this paper, we propose a trust management scheme that ensures trust in VANETs while maintaining vehicle privacy. The trust scheme establishes trust between vehicles where a trust value is assigned to every vehicle based on its behavior and messages are accepted only from vehicles whose trust value is greater than a threshold, therefore, protecting VANETs from malicious vehicles and eliminating bogus messages. If a traffic event happens, vehicles upload event messages to the reachable roadside unit (RSU). Once the RSU has confirmed that the event happened, it announces the event to vehicles in its vicinity and records it into the blockchain. Using this mechanism, RSUs are prevented from sending fake or unverified event notifications. Simulations are carried out in the context of bogus message attacks to evaluate the trust scheme's reliability and efficiency. The results of the simulation indicate that the proposed scheme outperforms the compared schemes and is highly resistant to bogus message attacks.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.640-648
• /
• 2022

In the United States, the Safety Rest Areas (SRAs) were introduced as highway roadside infrastructures in the early 1900s. The State Departments of Transportation (DOTs) operate/maintain their SRAs using different methods. The Washington DOT used the in-house workforce method for over 20 years, whereas some states moved to Performance-Based Contracting (PBC) from the in-house workforce to save cost primarily. Several existing studies claimed that using the PBC approach saved costs on several highway assets. Thus, the principal objective of this study is to compute and compare the unit operating/maintenance cost of SRAs using the in-house workforce method (in Washington state) with the PBC approach (in other states). The findings of this study show that the average annual cost using the PBC approach was much more than the average annual cost using the in-house workforce approach. The findings also show that in Washington state, the 'Labor Cost' category was a key expenditure, which is statistically higher than other categories. The 'Labor Cost' was followed by the 'Other Services', and then 'Materials and Supplies' and 'Equipment.' The study's findings indicated that outsourcing does not always save costs for agencies. The study findings may help transportation construction/maintenance professionals select a cost-effective approach for their future planning.

• 한국항만학회지
• /
• 제7권2호
• /
• pp.19-36
• /
• 1993

In this study for relieving traffic congestion on the main arterial in Pusan using TSM Techniques, the travel system, roadway system and signal system analyses were dine. Through these above analyses, it was shown that the peak-time periods on the main arterial were shaped between 10 : 00 and 11 : 00 in the morning and between 15 : 00 and 16 : 00 in the afternoon for the business and shopping trips. Especially, there appeared to be about 23% reduction in the average delay when roadway system management including left-turn links increased were done, about 29% reduction in the average delay when signal system management including the signal phases and timings readjusted were conducted, and about 48% reduction in average delay when roadway system and signal system management were taken into consideration simultaneously. Based upon these results, it was concluded that there might be considerably better results in the average delay if the progressive signal system analyses on the arterial were applied with the land and road widths balanced, the difference on the turning vehicles and mid-block volumes readjusted, and roadside parking traffic prohibited.