• Journal of Electrical Engineering and Technology
• /
• v.13 no.2
• /
• pp.961-968
• /
• 2018

Recently, researches on automatic recognition of human activities have been actively carried out with the emergence of various intelligent systems. Since a large amount of visual data can be secured through Closed Circuit Television, it is required to recognize human behavior in a dynamic situation rather than a static situation. In this paper, we propose new intelligent human activity recognition model using the trajectory information extracted from the video sequence. The proposed model consists of three steps: segmentation and partitioning of trajectory step, feature extraction step, and behavioral learning step. First, the entire trajectory is fuzzy partitioned according to the motion characteristics, and then temporal features and spatial features are extracted. Using the extracted features, four pedestrian behaviors were modeled by decision tree learning algorithm and performance evaluation was performed. The experiments in this paper were conducted using Caviar data sets. Experimental results show that trajectory provides good activity recognition accuracy by extracting instantaneous property and distinctive regional property.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.89-92
• /
• 2022

본 논문에서는 딥러닝 모델 기반 보행자의 GPS 경로를 예측하는 시스템을 제안한다. 다양한 경로 예측 방식들 중 본 논문은 GPS 데이터 기반 경로 예측 연구이다. 시계열 데이터인 보행자의 GPS 경로를 학습하여 다음 경로를 예측하도록 하는 딥러닝 모델 기반 연구이다. 본 논문에서는 보행자의 GPS 경로를 딥러닝 모델이 학습할 수 있도록 데이터 구성 방식을 제시하였으며, 예측 범위에 큰 제약이 없는 예측 딥러닝 모델을 제안한다. 본 논문의 딥러닝 모델에 적합한 파라메터들을 제시하였으며, 우수한 예측 성능을 보이는 결과를 제시한다.

• Journal of Korean Society of Transportation
• /
• v.28 no.2
• /
• pp.123-133
• /
• 2010

The national standards for the installation of pedestrian crosswalks prohibits installation of crosswalks within 200 meters of nearby overpasses, underpasses, or crosswalks. In case the exceptional installation is required, the feasibility study is to be thoroughly conducted by the local police agency. However, it is an undeniable fact that the specific installation standards for optimal types and locations of crosswalks are not yet to be established. This paper examines the development of traffic accident prediction model applicable to different types and locations of bus stops(type A and type B) at mid-block intersections. Furthermore, it develops the poisson regression model which sets the "number of traffic accidents" and "traffic accident severity" as dependent variables, while using "traffic volumes", "pedestrian traffic volumes" and "the distance between crosswalks and bus stops" as independent variables. According to the traffic accident prediction model applicable to the type A bus stop location, the traffic accident severity increases relative to the number of traffic volumes, the number of pedestrian traffic volumes, and the distance between crosswalks and bus stops. In case of the type B bus stop model, the further the bus stop is from crosswalks, the number of traffic accidents decreases while it increases when traffic volumes and pedestrian traffic volumes increase. Therefore, it is reasonable to state that the bus stop design which minimizes the traffic accidents is the type C design, which is the one in combination of type A and type B, and the optimal distance is found to be 65 meters. In case of the type A design and the type B design, the optimal distances are found to be within range 60~70meters.

• Proceedings of the KOR-KST Conference
• /
• 2007.11a
• /
• pp.852-858
• /
• 2007

• 한국ITS학회:학술대회논문집
• /
• v.2006 no.10
• /
• pp.236-241
• /
• 2006

• Proceedings of the KOR-KST Conference
• /
• 2007.02a
• /
• pp.296-305
• /
• 2007

• Wind and Structures
• /
• v.1 no.4
• /
• pp.337-349
• /
• 1998

A numerical and experimental study was performed for the wind flow field in one area, comprising a group of several pavilions separated by passageways, of the EXPO '98 - a World Exposition (Lisbon, Portugal). The focus of this study is the characterization of the flow field to assess pedestrian comfort. The predictions were obtained employing the Reynolds averaged Navier-Stokes equations with the turbulence effects dealt with the ${\kappa}-{\varepsilon}$ RNG model. The discretization of the differential equations was accomplished with the control volume formulation in a Cartesian coordinate system, and an advanced segregated procedure was used to achieve the link between continuity and momentum equations. The evaluation of the overall numerical model was performed by comparing its predictions against experimental data for a square cylinder placed in a channel. The predicted values, for the practical geometry studied, are in a good agreement with the experimental data, showing the performance and the reliability of the ${\kappa}-{\varepsilon}$ RNG model and suggesting that the numerical simulation is a reliable methodology to provide the required information.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.2
• /
• pp.63-75
• /
• 2013

Roundabouts have been operated in Europe, America and Australia since the 1970s, and many relevant researches continually was carried out. Though many studies regarding roundabout have been recently conducted in korea, most of them have focused on its operational safety and efficiency. Moreover, roundabout design guideline did not define a clear criteria related to pedestrian in roundabout, but seldom investigate the influences of pedestrian on crosswalk. In this study, we seek ways to operate the pedestrian crosswalk signal on roundabout maximizing their operational effects in exceptional case such as rush hour or intersection near the special facilities. We proved that roundabout signal operation is effective under certain circumstances in according to the number of pedestrian, and suggested the optimal signal timing plan for signalized roundabouts. For pursuing the above, we conducted the simulation test using the VISSIM model. The results show that the operational effectiveness of signalized roundabout was evaluated to be better than non-signalized roundabout in specific pedestrian volume condition. In addition, those results are confirmed using simulation analysis conducted on the real roundabout.

• Journal of Korean Society of Transportation
• /
• v.32 no.6
• /
• pp.638-650
• /
• 2014

The objective of this study is to identify the causes of pedestrian volume path to the destination by investigating the influential levels of regional and planning features in the central area of Seoul. Regional characteristics can be classified from the result of the analysis and through the spatial characteristics of pedestrian volume. For global scale analysis, Ordinary Least Squares (OLS) regression is used for the degree of influence of each characteristics to pedestrian volume. For the local scale, Geographically Weighted Regression (GWR) is used to identify regional influential factors with consideration for spatial differences. The results of OLS indicate that boroughs with transportation facilities, commercial business districts, universities, and planning features with education research facilities and planning facilities have a positive effect on pedestrian volume path to the destination. Correspondingly, transportation hubs and congested areas, commercial and business centers, and university towns and research facilities in the Seoul central area can be identified through the results of GWR. The results of this study can provide information with relevance to existing plans and policies about the importance of regional characteristics and spatial heterogeneity effects on pedestrian volume, as well as significance in the establishment of regional development plans.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.10 no.1
• /
• pp.1-9
• /
• 2007

3D data are in great demand for pedestrian navigation recently. For pedestrian navigation, we needs to reconstruct 3D model in detail from people's eye. In order to present spatial features in detail for pedestrian navigation, it is indispensable to develop 3D model not only in outdoor environment but also in indoor environment such as underground shopping complex. However, it is very difficult to acquire 3D data efficiently by mobile mapping without GPS. In this research, 3D shape was acquired by Laser scanner, and texture by CCD(Charge Coupled Device) sensor. Continuous changes position and attitude of sensors were measured by IMU(Inertial Measurement Unit). Moreover, IMU was corrected by relative orientation of CCD images without GPS(Global Positioning System). In conclusion, Reliable, quick, and handy method for acquiring 3D data for indoor environment is proposed by a combination of a digital camera and a laser scanner with IMU.