• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.43 no.5 s.311
• /
• pp.1-9
• /
• 2006

Because most applications of vision-based object tracking demonstrate satisfactory operations only under very constrained environments that have simplifying assumptions or specific visual attributes, these approaches can't track target objects for the highly variable, unstructured, and dynamic environments like a traffic scene. An adaptive fusion framework is essential that takes advantage of the richness of visual information such as color, appearance shape and so on, especially at cluttered and dynamically changing scenes with partial occlusion[1]. This paper develops a particle filter based adaptive fusion framework and improves the robustness and adaptation of this framework by adding a new distinctive visual attribute, an image feature descriptor using SIFT (Scale Invariant Feature Transform)[2] and adding an automatic teaming scheme of the SIFT feature library according to viewpoint, illumination, and background change. The proposed algorithm is applied to track various traffic objects like vehicles, pedestrians, and bikes in a driver assistance system as an important component of the Intelligent Transportation System.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.9
• /
• pp.4112-4118
• /
• 2011

Electrical Railroads provide electric power, which can operate vehicles, via feeder wires. And the supplied current returns to the transformer substation through lines and ground net. The return current, related to signal, power and power line, and track circuit systems, is one of the most important component in the electric railway. Therefore, to prevent system faults and breakdown according to unbalance and overcurrent of the return current, various and detailed analyses for the return current are needed. In the paper, we present measurement and analysis manners in real environment and evaluate its safety. For analysis, we utilize the measured values of return currents measured in track circuits in electric railway. we expect that this research plays a key role to the related fields.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.265-270
• /
• 2022

The purpose of this study is to derive the damage weak part of the elastic rail fastening system for concrete tracks (System 300-1). In the concrete tracks, the elastic rail fastening system sticks the rail and the sleeper and reacts all the time when the train is running. Among the components of the rail fastening system, the resilience pad and tension clamp were fatigue members and were constantly deformed in response to compressive and uplift forces. In this study, the residual deformation characteristics of the tension clamp according to the period of use were analyzed using by specimens taken on site in the same section for 6, 11, and 16 years on the serviced urban transit. In addition, the damage mechanisms for each component were derived based on finite element analysis. As a result of the numerical analysis, the stress (strain) of each part of the tension clamp according to the external force from the applied clamping force was analyzed to derive the damaged weak part of the tension clamp.

• The KIPS Transactions:PartB
• /
• v.16B no.5
• /
• pp.385-394
• /
• 2009

Face tracking and recognition are difficult problems because the face is a non-rigid object. The main reasons for the failure to track and recognize the faces are the changes of a face pose and environmental illumination. To solve these problems, we propose a nonlinear manifold framework for the face pose and the face illumination normalization processing. Specifically, to track and recognize a face on the video that has various pose variations, we approximate a face pose density to single Gaussian density by PCA(Principle Component Analysis) using images sampled from training video sequences and then construct the GMM(Gaussian Mixture Model) for each person. To solve the illumination problem for the face tracking and recognition, we decompose the face images into the reflectance and the illuminance using the SSR(Single Scale Retinex) model. To obtain the normalized reflectance, the reflectance is rescaled by histogram equalization on the defined range. We newly approximate the illuminance by the trained manifold since the illuminance has almost variations by illumination. By combining these two features into our manifold framework, we derived the efficient face tracking and recognition results on indoor and outdoor video. To improve the video based tracking results, we update the weights of each face pose density at each frame by the tracking result at the previous frame using EM algorithm. Our experimental results show that our method is more efficient than other methods.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.7
• /
• pp.4087-4092
• /
• 2014

The gangway connection of the articulated high speed railway vehicles (HSRV) is a double wrinkled rubber component to seal the air of the corridor under a range of angular deviations between the carriage end parts. From the results of non-linear structural analysis, one of the severe loading conditions for the connection is mixed mode (rolling+yawing) angular displacements while passing through the small-radius curved siding track of the HSRV depot. In this study, to ensure the safety enhancement of the component, the optimal design for the cross section of that was performed using the Solid Isotropic Material with Penalization (SIMP) method. Nonlinear finite element analysis confirmed that the decreases in the maximum principal strain of the optimized design under rolling and mixed modes are 68% and 39%, respectively, compared to the initial design.

• Journal of Korea Multimedia Society
• /
• v.10 no.1
• /
• pp.26-35
• /
• 2007

We present a robust face tracking system from the sequence of video images based on effective detector and Kalman filter. To construct the effective face detector, we extract the face features using the five types of simple Haar-like features. Extracted features are reinterpreted using Principal Component Analysis (PCA), and interpreted principal components are used for Support Vector Machine (SVM) that classifies the faces and non-faces. We trace the moving face with Kalman filter, which uses the static information of the detected faces and the dynamic information of changes between previous and current frames. To make a real-time tracking system, we reduce processing time by adjusting the frequency of face detection. In this experiment, the proposed system showed an average tracking rate of 95.5% and processed at 15 frames per second. This means the system is robust enough to track faces in real-time.

• Wind and Structures
• /
• v.25 no.1
• /
• pp.63-77
• /
• 2017

When railway vehicles run by towers of long span bridges, the railway vehicles might experience a sudden load-off and load-on phenomenon in crosswind conditions. To ensure the running safety of the railway vehicles and the running comfort of the passengers, some studies were carried out to investigate the impacts of sudden changes of aerodynamic loads on moving railway vehicles. In the present study, the aerodynamic coefficients which were measured in wind tunnel tests using a moving train model are converted into the aerodynamic coefficients in the actual scale. The three-component aerodynamic loads are calculated based on the aerodynamic coefficients with consideration of the vehicle movement. A three-dimensional railway vehicle model is set up using the multibody dynamic theory, and the aerodynamic loads are treated as the inputs of excitation varied with time for kinetic simulations of the railway vehicle. Thus the dynamic responses of the railway vehicle passing by the bridge tower can be obtained from the kinetic simulations in the time domain. The effects of the mean wind speeds and the rail track positions on the running performance of the railway vehicle are discussed. The three-component aerodynamic loads on the railway vehicle are found to experience significant sudden changes when the vehicle passes by the bridge tower. Correspondingly, such sudden changes of aerodynamic loads have a large impact on the dynamic performance of the running railway vehicle. The dynamic responses of the railway vehicle have great fluctuations and significant sudden changes, which is adverse to the running safety and comfort of the railway vehicle passing by the bridge tower in crosswind conditions.

• Journal of Internet Computing and Services
• /
• v.4 no.4
• /
• pp.9-14
• /
• 2003

A GUI (graphical user interface) has been a dominant platform for HCI (human computer interaction). A GUI - based interaction has made computers simpler and easier to use. The GUI - based interaction, however, does not easily support the range of interaction necessary to meet users' needs that are natural. intuitive, and adaptive. In this paper, the modified BMA (block matching algorithm) is proposed to track a hand in a sequence of an image and to recognize it in each video frame in order to replace a mouse with a pointing device for a virtual reality. The HCI system with 30 frames per second is realized in this paper. The modified BMA is proposed to estimate a position of the hand and segmentation with an orientation of motion and a color distribution of the hand region for real - time processing. The experimental result shows that the modified BMA with the YCbCr (luminance Y, component blue, component red) color coordinate guarantees the real - time processing and the recognition rate. The hand tracking by the modified BMA can be applied to a virtual reclity or a game or an HCI system for the disable.

• Journal of Convergence for Information Technology
• /
• v.11 no.9
• /
• pp.138-144
• /
• 2021

In the electronic component assembly business, when product defects occur, it is important to track incoming raw material defects or work defects, and it is important to improve suppliers or work sites according to the results. The core task of the smart factory is to build an integrated data hub to process storage, management, and analysis in real time, and to manage cluster processes, energy, environment, and safety. In order to improve reliability through accurate analysis and collection of production data by real-time monitoring of production site management for electronic parts-related small and medium-sized enterprises (SMEs), the establishment of a smart factory is essential. This paper was developed to be utilized in the construction by defining the system configuration method, smart factory-related technology and application cases, considering the characteristics of SMEs related to electronic components that want to introduce a smart factory.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2006.11a
• /
• pp.747-750
• /
• 2006

A turnout which permits trains to pass from one track to another has a disconnecting rail component, namely a crossing, so that noise and vibration arc occurred abruptly when train is passing through it. In Korea, it is planned to adopt the high speed tilting train, which operates at the speed of 180 km/h, at the conventional line. However, for application of the tilting train, it is prerequisite to establish the stable turnout system allowing the tilting train to pass through it without reducing speed. This study was performed to evaluate noise and vibration emitted from the prototype turnout which is developed for speed-up of the conventional line. For the purpose, noise and vibration were measured at near the conventional turnout and the improved one, which is constructed at Waegwan station and Kumi station of Gyeongbu line, respectively.