• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.10
• /
• pp.4968-4986
• /
• 2017

In this paper, we primarily address the difficulty of automatic generation of a plausible depth map from a single image in an unstructured environment. The aim is to extrapolate a depth map with a more correct, rich, and distinct depth order, which is both quantitatively accurate as well as visually pleasing. Our technique, which is fundamentally based on a preexisting DepthTransfer algorithm, transfers depth information at the level of superpixels. This occurs within a framework that replaces a pixel basis with one of instance-based learning. A vital superpixels feature enhancing matching precision is posterior incorporation of predictive semantic labels into the depth extraction procedure. Finally, a modified Cross Bilateral Filter is leveraged to augment the final depth field. For training and evaluation, experiments were conducted using the Make3D Range Image Dataset and vividly demonstrate that this depth estimation method outperforms state-of-the-art methods for the correlation coefficient metric, mean log10 error and root mean squared error, and achieves comparable performance for the average relative error metric in both efficacy and computational efficiency. This approach can be utilized to automatically convert 2D images into stereo for 3D visualization, producing anaglyph images that are visually superior in realism and simultaneously more immersive.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.11
• /
• pp.1608-1618
• /
• 2016

In this paper we introduce a graph theory approach to solve the frequency assignment problem(FAP) for military communication network. Prior algorithms are implemented adaptively to the problem, and enhanced algorithms are proposed to show that their results approximately approached the optimum performance. We also proposed polarization assignment algorithms to enhance the FAP performances.

• International Journal of Highway Engineering
• /
• v.15 no.3
• /
• pp.103-115
• /
• 2013

PURPOSES: The purpose of this study is to develop a method for distribution between superelevation and side friction factor by increasing design speed. METHODS: First of all, a method for distribution between superelevation and side friction factor and a theory for the functional formula of side friction factor in compliance with horizontal radius applied in South Korea and the United States are considered. Especially, design speed of 140km/h and numerical value of design elements are applied to the theory for the functional formula of side friction factor in AASHTO's methods. Also, the anxiety EEG upon running speed is measured to reflect ergonomic characteristics through field experiments at seven curve sections of the West Coast Freeway, and this data is applied to graph for the functional formula of side friction factor. RESULTS : Matching side friction factor against the anxiety EEG, the results that a critical points of driver's anxiety EEG sharply increase locate under existing parabola are figured out. CONCLUSIONS : Therefore, we could get a new type of the functional formula that driver's driving comfortability is guaranteed if the existing the functional formula of side friction factor goes down under boundary of the critical points of the anxiety EEG.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2001.09a
• /
• pp.23-27
• /
• 2001

Making the safety situation from the various work system is very important in the industrial fields. The proposed neural network technique is the real titre computation method based theory of inter-node diffusion for searching the safety distances from the sudden appearance-objests during the work driving. The main steps of the distance computation using the theory of stereo vision like the eyes of man is following steps. One is the processing for finding the corresponding points of stereo images and the other is the interpolation processing of full image data from nonlinear image data of obejects. All of them request much memory space and titre. Therefore the most reliable neural-network algorithm is drived for real time recognition of obejects, which is composed of a dynamic programming algorithm based on sequence matching techniques. And the real time reconstruction of nonlinear image information is processed through several simulations. I-D LIPN hardware has been composed, and the real time reconstruction is verified through the various experiments.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.10 s.181
• /
• pp.2487-2495
• /
• 2000

The acoustic characteristics of expansion chamber will be changed with the variation of inlet/outlet location due to the higher order acoustic mode in a high frequency in which the plane wave theory is not available. In this paper, the acoustic performance of reactive type expansion chamber with circular cross-section is analyzed by using the modified mode matching theory. The sensitivity analysis of four-pole parameters with respect to the location of inlet and outlet is also suggested to increase the acoustic performance. The acoustic power transmission coefficient is used as cost function, and the location of inlet and outlet is used as design variables. The steepest descent method and SUMT algorithm are used for optimization technique. Several results showed that the expansion chamber with optimally located inlet/outlet had better acoustic performance than concentric expansion chamber.

• Korean Journal of Optics and Photonics
• /
• v.17 no.2
• /
• pp.120-126
• /
• 2006

A grating-assisted fiber coupler(GAFC), which consists of a thin-film waveguide with grating and circular optical fiber, is proposed and the optimized power coupling is evaluated by using a technique amenable to rigorous longitudinal modal transmission-line theory(L-MTLT). In addition, novel criteria to couple an optical signal incident through the grating waveguide to a single-mode optical fiber are proposed. The numerical result reveals that the optimized power coupling occurs at minimum-gap condition between rigorous modes rather than for the conventional phase-matching condition.

• Journal of the Korean Society for Railway
• /
• v.10 no.3 s.40
• /
• pp.264-270
• /
• 2007

Two modulus, strain modulus $(E_v)$ and subgrade reaction modulus $(K_{30})$ are being used as a standard for bearing stiffness in Korea Railroad design. The first is used in Europe and the other is used in Japan. The methodologies to obtain the two modulus are similar in using plate. But testing methods are different in loading to plate. Therefore, according to soil strain range, there should be large gap in not only computations of deformation modulus but also the necessary time to test. At first, this paper focuses on the two kinds of test methods to evaluate bearing stiffness. Secondly, based on elastic theory, the theory to obtain the two coefficients are studied thoroughly. Finally, the correlations between the two coefficients were analyzed and evaluated based on the field test results more than 38 places. The matching values for subgrade and ground between $K_{30}$ and $E_{v2}$ are proposed with the consideration of the proposed strain reduction factor (1.5 for subgrade and 3 for ground) and safety factor, respectively.

• Geotechnical Engineering
• /
• v.10 no.4
• /
• pp.17-28
• /
• 1994

It is well known that human brain has the advantage of handling disperse and parallel distributed data efficiently. On the basic of this fact, artificial neural networks theory was developed and has been applied to various fields of science successfully. In this study, error back propagation algorithm which is one of the teaching technique of artificial neural networks is applied to predict ultimate bearing capacity of pile foundations. For the verification of applicability of this system, a total of 28 data of model pile test results are used. The 9, 14 and 21 test data respectively out of the total 28 data are used for training the networks, and the others are used for the comparison between the predicted and the measured. The results show that the developed system can provide a good matching with model pile test results by training with data more than 14. These limited results show the possibility of utilizing the neural networks for pile capacity prediction problems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.8
• /
• pp.2833-2850
• /
• 2014

This paper proposes a novel framework for traffic video classification based on chaotic features. First, each pixel intensity series in the video is modeled as a time series. Second, the chaos theory is employed to generate chaotic features. Each video is then represented by a feature vector matrix. Third, the mean shift clustering algorithm is used to cluster the feature vectors. Finally, the earth mover's distance (EMD) is employed to obtain a distance matrix by comparing the similarity based on the segmentation results. The distance matrix is transformed into a matching matrix, which is evaluated in the classification task. Experimental results show good traffic video classification performance, with robustness to environmental conditions, such as occlusions and variable lighting.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.29A no.11
• /
• pp.19-24
• /
• 1992

In this paper, a high frequency method is developed which combines the uniform Geometrical Theory of Diffraction(GTD) and the Aperture Integration(AI) to analyze electromagnetic plane wave scattering by a perfectly-conducting, open-ended, semi-infinite parallel plate waveguide with a uniform layer of absorbing material on its inner wall, and with a slanted planar termination inside. In this method, first, the field of an arbitary point inside the paraller plate waveguide is computed by the GTD. Second, the field scattered into exterior region by the waveguide is found using the equivalent current, which can be obtaind from the aperture field of the waveguide and using the AI. Numerical results based on this GTD method are presented and compared with those based on the mode matching method.