• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.8
• /
• pp.1547-1552
• /
• 2017

Unlike diesel locomotives, electric vehicles have various issues because they have very quiet engine sound. For example, pedestrians are exposed to the dangerous electric vehicles on the road because they can not recognize the electric vehicles' sound. Moreover, the driver is unable to recognize how fast driver's car is driving at a certain speed. To solve these problems, electric cars' sound needs to be artificially implemented and played. This paper examines the problems of the previous sampling engine sound approach. In this paper, instead of using sampling sounds, we developed a novel synthesizer algorithm via programming languages as a software. In experimental results, we demonstrated and verified our proposed synthesizer's approach is superior to the previous sampling approach. In addition, through these synthesizer's approach, we highly expect the proposed synthesizer's approach will give safety, convenience and comfort to the electric vehicles' users.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.1
• /
• pp.13-19
• /
• 2011

In this paper, a visual surveillance system using SOPC based NIOS II embedded processor and C2H compiler was implemented. In this system, the IP is constructed by C2H compiler for the output of the camera images, image processing, serial communication and network communication, then, it is implemented to effectively control each IP based on the SOPC and the NIOS II embedded processor. And, an algorithm which updates the background images for high speed and robust detection of the moving objects is proposed using the Adaptive Gaussian Mixture Model(AGMM). In results, it can detecte the moving objects(pedestrians and vehicles) under day-time and night-time. It is confirmed that the proposed AGMM algorithm has better performance than the Adaptive Threshold Method(ATM) and the Gaussian Mixture Model(GMM) from our experiments.

• International Journal of Highway Engineering
• /
• v.12 no.4
• /
• pp.11-16
• /
• 2010

Various researches have been performed on the topic of pedestrian traffic flow. At the beginning, the modeling and simulation method for the vehicular traffic flow was simply applied to pedestrian traffic flow. Recently, CA based simulation models are frequently applied to pedestrian flow analysis. Initially, the square Lattice Model is a base model for applying to pedestrians of counterflow and then Hexagonal Lattice Model improves its network as a hexagonal cell for more realistic movement of the avoidance of pedestrian conflicts. However these lattice models express only one directional movement because they express only one directional movement. In this paper, MLPM (the Multi-Layer Pedestrian Model) is suggested to give various origins and destinations for more realistic pedestrian motion in some place.

• International Journal of Highway Engineering
• /
• v.15 no.1
• /
• pp.111-119
• /
• 2013

PURPOSES: Though the situation that the roundabouts are actively constructed, researches on the effect of the roundabouts focus mainly on the analysis of the expected effects of using only traffic simulation on the operation. Considering such problems, this study is conducted to analyze the effects of the various aspects based on field observation studies. METHODS: This study evaluated and analyzed the effects from the aspects of traffic operation, traffic safety, and traffic behavior by performing field observation studies with six roundabouts with/without signal controls on the pilot project areas for the roundabouts installed in 2010. RESULTS: Through the study results, it was found that the average travel time decreases by 14.7% and 2.4% on the signalized intersections and unsignalized intersections, respectively. The average travel speed increases by 9.7 and 5.8km/h on the roundabouts with/without signal lights. Regarding traffic safety, the speed deviation among individual vehicles decreases by approximately 18.4 to 32.7km/h, thus confirming the safety effects. As the decrease of the number of conflicts, it might be explained that car crashes and collision with pedestrians decreased by 62.2% and 66.7%. Also the result shows that the lowest point of speed in roundabouts appears near the yield line on the entry area on the roundabouts. When passing through the roundabouts, vehicles enter at a speed of 20-30km/h, which is the design speed of the circulatory lane and drive out the roundabout with a higher speed than the entry speed. CONCLUSIONS: When a roundabout is introduced at the intersections below certain traffic volume there are effects of traffic operation, traffic safety, and traffic behavior.

• Journal of Korean Society of Transportation
• /
• v.28 no.5
• /
• pp.7-15
• /
• 2010

The walkway level of service (LOS) is conceptualized using pedestrian flow rate, speed, and density according to the Korean Highway Capacity Manual (KHCM). However, as it is based on the data of commuters at peak hours, it needs to be reevaluated considering various trip purposes and a pleasant pedestrian environment. Thus, the authors aimed to investigate and analyze the characteristics of each group: pedestrians during the peak hour and those during the non-peak hour. Then they were verified statistically for the walkway evaluation criteria. In this study, the authors investigated pedestrian speed and flow in a complex transit center walkway with diverse trip purposes by peak and non-peak hour. Then the authors statistically verified the differences between the groups. A model was built for estimating pedestrian density by speed and flow; it was used to calculate the walkway capacity (67.3p/m/m) corresponding to LOS E. The authors established new criteria for LOS, applying the LOS from the HCM. These standards can then be used as the design standards for pedestrian walkways.

• Journal of Korean Society of Transportation
• /
• v.31 no.1
• /
• pp.57-64
• /
• 2013

Recently, bicycle accidents have increased with the ever-increasing number of cyclists. Bicycle accidents occurred frequently in intersections, and the perpendicular collision between a right-turning car and a crossing bicycle was the most prevalent accident type. In particular, the collision was caused by motorists' carelessness. In other words, the accident-involved motorists did not pay sufficient attention to a bicycle crossing behind them. Another cause was a cyclist's higher speed than pedestrians. This paper evaluated the potential risk of the collision between right-turning cars and crossing bicycles based on simulation experiments, with motorists' speed and carelessness focused on. Consequently, it was found that to reduce the potential risk of the collisions a motorist should slow down and pay more attention to the rear sight by turning his/her head.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.12
• /
• pp.3315-3337
• /
• 2012

Crowded scenes analysis is a challenging topic in computer vision field. How to detect diverse motion patterns in crowded scenarios from videos is the critical yet hard part of this problem. In this paper, we propose a novel approach to mining motion patterns by utilizing motion information during both long-term period and short interval simultaneously. To capture long-term motions effectively, we introduce Motion History Image (MHI) representation to access to the global perspective about the crowd motion. The combination of MHI and optical flow, which is used to get instant motion information, gives rise to discriminative spatial-temporal motion features. Benefitting from the robustness and efficiency of the novel motion representation, the following motion pattern mining is implemented in a completely unsupervised way. The motion vectors are clustered hierarchically through automatic hierarchical clustering algorithm building on the basis of graphic model. This method overcomes the instability of optical flow in dealing with time continuity in crowded scenes. The results of clustering reveal the situations of motion pattern distribution in current crowded videos. To validate the performance of the proposed approach, we conduct experimental evaluations on some challenging videos including vehicles and pedestrians. The reliable detection results demonstrate the effectiveness of our approach.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.6
• /
• pp.493-497
• /
• 2016

Infrared (IR) imaging is capable of detecting targets that are not visible at night, thus it has been widely used for the security and defense system. However, the quality of the IR image is often degraded by low resolution and noise corruption. This paper addresses target segmentation with the IR image. Multiple regions of interest (ROI) are extracted by the multi-level segmentation and targets are segmented from the individual ROI. Each level of the multi-level segmentation is composed of a k-means clustering algorithm an expectation-maximization (EM) algorithm, and a decision process. The k-means clustering algorithm initializes the parameters of the Gaussian mixture model (GMM) and the EM algorithm iteratively estimates those parameters. Each pixel is assigned to one of clusters during the decision. This paper proposes the selection and the merging of the extracted ROIs. ROI regions are selectively merged in order to include the overlapped ROI windows. In the experiments, the proposed method is tested on an IR image capturing two pedestrians at night. The performance is compared with conventional methods showing that the proposed method outperforms others.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1244-1253
• /
• 2021

In this paper, we propose a method for predicting in advance whether pedestrians will enter the hazardous area after the current time using the pedestrian trajectory prediction method and an efficient simplification method of the trajectory prediction network. In addition, we propose a method to apply KD(Knowledge Distillation) to a small network for real-time operation in an embedded environment. Using the correlation between predicted future paths and hazard zones, we determined whether to enter or not, and applied efficient KD when learning small networks to minimize performance degradation. Experimentally, it was confirmed that the model applied with the simplification method proposed improved the speed by 37.49% compared to the existing model, but led to a slight decrease in accuracy. As a result of learning a small network with an initial accuracy of 91.43% using KD, It was confirmed that it has improved accuracy of 94.76%.

• Journal of the Korean Institute of Gas
• /
• v.25 no.3
• /
• pp.53-58
• /
• 2021

The number of patients with cardiovascular diseases who experience an out-of-hospital cardiac arrest (OHCA) are increasing among young adults as well as the aged population. An automated external defibrillator (AED) is vital in improving survival rates of OHCA victims. Survival rates of OHCA were shown to decline exponentially in time to defibrillation, yet studies in Korea are uncommon that captures the properties of their survival rates in examining optimal locations of AEDs. In this study, we worked on the maximal gradual coverage location problem (MGCLP) with exponential decay coverage function to decide on their optimal locations. The exponential decay coverage function mitigates the drawback of over-estimating survival rates of OHCA patients. It is expected that a more sophisticated facility location problem will be developed to identify the "emergent" characteristics of pedestrians who responds to the OHCA occurrence by incorporating random pedestrian locations and movement through simulation.