• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.2
• /
• pp.79-88
• /
• 2004

Gaze detection is to locate the position on a monitor screen where a user is looking by computer vision. Gaze detection systems have numerous fields of application. They are applicable to the man-machine interface for helping the handicapped to use computers and the view control in three dimensional simulation programs. In our work, we implement it with a computer vision system setting a IR-LED based single camera. To detect the gaze position, we locate facial features, which is effectively performed with IR-LED based camera and SVM(Support Vector Machine). When a user gazes at a position of monitor, we can compute the 3D positions of those features based on 3D rotation and translation estimation and affine transform. Finally, the gaze position by the facial movements is computed from the normal vector of the plane determined by those computed 3D positions of features. In addition, we use a trained neural network to detect the gaze position by eye's movement. As experimental results, we can obtain the facial and eye gaze position on a monitor and the gaze position accuracy between the computed positions and the real ones is about 4.8 cm of RMS error.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.39 no.5
• /
• pp.455-461
• /
• 2015

A high-pressure fuel pump is a key component in a gasoline direct injection (GDI) engine; thus, understanding its flow characteristics is essential for improving the engine power and fuel efficiency. In this study, AMESim, which is a hydraulic analysis program, was used to analyze the performance of the high-pressure fuel pump. However, since AMESim uses a one-dimensional model for the system analysis, it does not accurately analyze the complicated flow characteristics. Thus, Fluent, computational fluid dynamics (CFD) software, was used to calculate the flow rates and net forces at the intake and discharge ports of the high-pressure fuel pump where turbulent flow occurs. The CFD analysis results for various pressure conditions and valve lifts were used as look-up tables for the AMEsim model. The CFD analysis results complemented the AMEsim results, and thus, improved the accuracy of the performance analysis results for the high-pressure fuel pump.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.4
• /
• pp.10-16
• /
• 2012

For high speed visual inspection in semiconductor industries, it is essential to acquire two-dimensional images on regions of interests with a large field of view (FOV) and a high resolution simultaneously. In this paper, an imaging system is newly proposed to achieve high quality image in terms of precision and FOV, which is composed of single lens, a beam splitter, two camera sensors, and stereo image grabbing board. For simultaneously acquired object images from two camera sensors, Zhang's camera calibration method is applied to calibrate each camera first of all. Secondly, to find a mathematical mapping function between two images acquired from different view cameras, the matching matrix from multiview camera geometry is calculated based on their image homography. Through the image homography, two images are finally registered to secure a large inspection FOV. Here the inspection system of using multiple images from multiple cameras need very fast processing unit for real-time image matching. For this purpose, parallel processing hardware and software are utilized, such as Compute Unified Device Architecture (CUDA). As a result, we can obtain a matched image from two separated images in real-time. Finally, the acquired homography is evaluated in term of accuracy through a series of experiments, and the obtained results shows the effectiveness of the proposed system and method.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.16 no.4
• /
• pp.19-26
• /
• 2012

For a seismic design or performance evaluation of a structure, an experimental investigation on a scale model of the structure or numerical analysis based on the finite element model is considered. Regarding the numerical analysis, a three-dimensional finite element analysis is performed if a high accuracy of the results is required, while a sensitivity or fragility analysis which uses huge seismic ground motions leads to the use of a lumped-mass stick model. The conventional modeling technique to build the lumped-mass stick model calculates the amount of the lumped mass by considering the geometric shape of the structure, like a tributary area. However, the eigenvalues of the conventional model obtained through such a calculation are normally not the same as those of the actual structure. In order to overcome such a deficiency, in this study, a new lumped mass stick model is proposed. The model is named the "frequency adaptive-lumped-mass stick model." It provides the same eigenvalues and similar dynamic responses as the actual structure. A non-prismatic column is considered as an example, and its natural frequencies as well as the dynamic performance of the new lumped model are compared to those of the full-finite element model. To investigate the damping effect on the new model, 1% to 5% of the critical damping ratio is applied to the model and the corresponding results are also compared to those of the finite element model.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.4
• /
• pp.255-262
• /
• 2018

In order to determine the three-dimensional position in photogrammetry, a spatial resection is a pre-requisite step to determine exterior orientation parameters. The existing spatial resection method is a non-linear equation that requires initial values of exterior orientation parameters and has a problem that a gimbal lock phenomenon may occur. On the other hand, the spatial resection using quaternion is a closed form solution that does not require initial values of EOP (Exterior Orientation Parameters) and is a method that can eliminate the problem of gimbal lock. In this study, to analyze the stability of the quaternion-based spatial resection, the exterior orientation parameters were determined according to the different layout of control points and were compared with the determined values using existing non-linear equation. As a result, it can be seen that the quaternionbased spatial resection is affected by the layout of the control points. Therefore, if the initial value of exterior orientation parameters could not be obtained, it would be more effective to estimate the initial exterior orientation values using the quaternion-based spatial resection and apply it to the collinearity equation-based spatial resection method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.3
• /
• pp.639-647
• /
• 2011

In this paper, we introduce a design methodology of data-centroid Radial Basis Function neural networks with extended polynomial function. The two underlying design mechanisms of such networks involve K-means clustering method and Particle Swarm Optimization(PSO). The proposed algorithm is based on K-means clustering method for efficient processing of data and the optimization of model was carried out using PSO. In this paper, as the connection weight of RBF neural networks, we are able to use four types of polynomials such as simplified, linear, quadratic, and modified quadratic. Using K-means clustering, the center values of Gaussian function as activation function are selected. And the PSO-based RBF neural networks results in a structurally optimized structure and comes with a higher level of flexibility than the one encountered in the conventional RBF neural networks. The PSO-based design procedure being applied at each node of RBF neural networks leads to the selection of preferred parameters with specific local characteristics (such as the number of input variables, a specific set of input variables, and the distribution constant value in activation function) available within the RBF neural networks. To evaluate the performance of the proposed data-centroid RBF neural network with extended polynomial function, the model is experimented with using the nonlinear process data(2-Dimensional synthetic data and Mackey-Glass time series process data) and the Machine Learning dataset(NOx emission process data in gas turbine plant, Automobile Miles per Gallon(MPG) data, and Boston housing data). For the characteristic analysis of the given entire dataset with non-linearity as well as the efficient construction and evaluation of the dynamic network model, the partition of the given entire dataset distinguishes between two cases of Division I(training dataset and testing dataset) and Division II(training dataset, validation dataset, and testing dataset). A comparative analysis shows that the proposed RBF neural networks produces model with higher accuracy as well as more superb predictive capability than other intelligent models presented previously.

• The Journal of Engineering Geology
• /
• v.24 no.1
• /
• pp.53-67
• /
• 2014

Numerical modeling is commonly used to reproduce the physical phenomena of dam-break and to compile resulting flood hazard maps. The accuracy of a dam-break model depends on the physical structure that describes the volume of storage, breach formation and progress, input variables, and model parameters. Model input and parameters are subjective in that they are prescribed; hence, caution is needed when interpreting the results. This study focuses on three parameters (breach degree ${\theta}$, shape factor P, and collapse rate k) used when the dam-break model is coupled with FLO-2D (a two-dimensional flood simulation model) to estimate flood coverage and depth etc. The results show that the simulation is sensitive to the shape factor P and the collapse rate k but not to the breach degree ${\theta}$. This study will contribute to reducing flood damage from dam-break disasters in the future.

• Journal of Broadcast Engineering
• /
• v.17 no.1
• /
• pp.73-80
• /
• 2012

Recently, medical equipments are developed and used for diagnosis or studies. In addition, demand of techniques which automatically deal with three dimensional medical images obtained from the medical equipments is growing. One of the techniques is automatic bone segmentation which is expected to enhance the diagnosis efficiency of osteoporosis, fracture, and other bone diseases. Although various researches have been proposed to solve it, they are unable to be used in practice since a size of the medical data is large and there are many low contrast boundaries with other tissues. In this paper, we present a fast and accurate automatic framework for bone segmentation based on multi-resolutions. On a low resolution step, a position of the bone is roughly detected using constrained branch and mincut which find the optimal template from the training set. Then, the segmentation and the registration are iteratively conducted on the multiple resolutions. To evaluate the performance of the proposed method, we make an experiment with femur and tibia from 50 test knee magnetic resonance images using 100 training set. The proposed method outperformed the constrained branch and mincut in aspect of segmentation accuracy and implementation time.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.6
• /
• pp.609-616
• /
• 2017

In this paper, we propose an algorithm to obtain more stable and high recognition rate by using left and right rotation information of input image in order to obtain a stable recognition rate in face recognition. The proposed algorithm uses the facial image as the input information in the web camera environment to reduce the size of the image and normalize the information about the brightness and color to obtain the improved recognition rate. We apply Principal Component Analysis (PCA) to the detected candidate regions to obtain feature vectors and classify faces. Also, In order to reduce the error rate range of the recognition rate, a set of data with the left and right $45^{\circ}$ rotation information is constructed considering the directionality of the input face image, and each feature vector is obtained with PCA. In order to obtain a stable recognition rate with the obtained feature vector, it is after scattered in the eigenspace and the final face is recognized by comparing euclidean distant distances to each feature. The PCA-based feature vector is low-dimensional data, but there is no problem in expressing the face, and the recognition speed can be fast because of the small amount of calculation. The method proposed in this paper can improve the safety and accuracy of recognition and recognition rate faster than other algorithms, and can be used for real-time recognition system.

• Journal of Advanced Navigation Technology
• /
• v.22 no.4
• /
• pp.271-278
• /
• 2018

For ionospheric correction of low earth orbiter (LEO) satellites using single frequency global navigation satellite system (GNSS) receiver, ionospheric scale factor should be applied to the ground-based ionosphere model. The ionospheric scale factor can be calculated by using a NeQuick model, which provides a three-dimensional ionospheric distribution. In this study, the ionospheric scale factor is calculated by using NeQuick G model during 2015, and it is compared with the scale factor computed from the combination of LEO satellite measurements and international GNSS service (IGS) global ionosphere map (GIM). The accuracy of the ionospheric delay calculated by the NeQuick G model and IGS GIM with NeQuick G scale factor is analyzed. In addition, ionospheric delay errors calculated by the NeQuick G model and IGS GIM with the NeQuick G scale factor are compared. The ionospheric delay error variations along to latitude and solar activity are also analyzed. The mean ionospheric scale factor from the NeQuick G model is 0.269 in 2015. The ionospheric delay error of IGS GIM with NeQuick G scale factor is 23.7% less than that of NeQuick G model.