• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2008.11a
• /
• pp.113-116
• /
• 2008

본 논문에서는 다시점 비디오(multi-view video)에서 보다 다양한 시점을 제공하기 위한 가상 시점 비디오 생성 기법을 제안한다. 제안하는 가상 시점 비디오 생성 기법은 우선적으로 대칭적 신뢰 전파 기법(symmetric belief propagation)을 기반으로, 각 시점의 깊이 정보 및 폐색 영역(occlusion region)을 추출하기 위해서 에너지를 최소화한다. 추출된 깊이 정보 및 에너지를 이용하여 참조하는 시점 간의 가중치를 적용하여, 새로운 가상 시점의 비디오를 생성하고, 추출된 폐색 영역의 값을 이용하여, 가상 시점의 비디오를 보정하는 가상 시점 비디오 생성 기법을 제안한다. 또한 제안하는 알고리즘을 한정된 중간 시점 영상에서 임의의 가상 시점으로 확장하여, 임의의 두 시점 간의 자유로운 시점(free-view point)을 제공함을 확인한다. 실험을 통하여 제안하는 기법이 다시점 비디오에서 높은 화질의 가상 시점 비디오를 제공함을 확인한다.

• Journal of The Korean Astronomical Society
• /
• v.36 no.spc1
• /
• pp.101-107
• /
• 2003

The magnetosphere is often perturbed by impulsive input such as interplanetary shocks and solar wind discontinuities. We study how these initial perturbations are propagating within the magnetosphere over various latitude regions by adopting a three-dimensional numerical dipole model. We examine the wave propagation on a meridional plane in a time-dependent manner and compare the numerical results with multi-satellite and ground observations. The dipole model is used to represent the plasmasphere and magnetosphere with a realistic Alfven speed profile. It is found that the effects of refraction, which result from magnetic field curvature and inhomogeneous Alfven speed, are' found to become important near the plasmapause. Our results show that, when the disturbances are assumed at the subsolar point of the dayside magnetosphere, the travel time becomes smaller to the polar ionosphere compared to the equatorial ionosphere.

• Proceedings of the KIPE Conference
• /
• 2000.07a
• /
• pp.620-623
• /
• 2000

A very simple control approach using neural network for the robust position control of a Permanent Magnet Synchronous Motor(PMSM) is presented The linear quadratic controller plus feedforward neural network is employed to obtain the robust PMSM system approximately linearized using field-orientation method for an AC servo. The neural network is trained in on-line phases and this neural network is composed by a fedforward recall and error back-propagation training. Since the total number of nodes are only eight this system can be easily realized by the general microprocessor. During the normal operation the input-output response is sampled and the weighting value is trained multi-times by error back-propagation method at each sample period to accommodate the possible variations in the parameters or load torque. And the state space analysis is performed to obtain the state feedback gains systematically. IN addition the robustness is also obtained without affecting overall system response. This method is realized by a floating-point Digital Singal Processor DS1102 Board (TMS320C31) The basic DSP software is used to write C program which is compiled by using ANSI-C style function prototypes.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.28 no.3
• /
• pp.254-262
• /
• 2008

The objective of the proposed study is to produce a tool-condition monitoring (TCM) strategy that will lead to a more efficient and economical drilling tool usage. Drill-wear monitoring is an important attribute in the automatic cutting processes as it can help preventing damages of the tools and workpieces and optimizing the tool usage. This study presents the architectures of a multi-layer feed-forward neural network with back-propagation training algorithm for the monitoring of drill wear. The input features to the neural networks were extracted from the AE signals using the wavelet transform analysis. Training and testing were performed under a moderate range of cutting conditions in the dry drilling of steel plates. The results indicated that the extracted input features from AE signals to the supervised neural networks were effective for drill wear monitoring and the output of the neural networks could be utilized for the tool life management planning.

• Proceedings of the KIEE Conference
• /
• 2007.11c
• /
• pp.83-87
• /
• 2007

Correlation Propagation Neural Networks is proposed for On-line interpolation. The proposed neural network technique is the real time computation method through the inter-node diffusion. In the network, a node corresponds to a state in the quantized input space. Each node is composed of a processing unit and fixed weights from its neighbor nodes as well as its input terminal. Information propagates among neighbor nodes laterally and inter-node interpolation is achieved. Through several simulation experiments, real time reconstruction of the nonlinear image information is processed. 1-D CPNN hardware has been implemented with general purpose analog ICs to test the interpolation capability of the proposed neural networks. Experiments with static and dynamic signals have been done upon the CPNN hardware.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2001.10a
• /
• pp.59-64
• /
• 2001

The objectives of the thesis are to propose a pattern classification method for remote sensing data using artificial neural network. First, we apply the error back propagation algorithm to classify the remote sensing data. In this case, the classification performance depends on a training data set. Using the training data set and the error back propagation algorithm, a layered neural network is trained such that the training pattern are classified with a specified accuracy. After training the neural network, some pixels are deleted from the original training data set if they are incorrectly classified and a new training data set is built up. Once training is complete, a testing data set is classified by using the trained neural network. The classification results of Landsat TM data show that this approach produces excellent results which are more realistic and noiseless compared with a conventional Bayesian method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.4
• /
• pp.306-314
• /
• 2013

Automatic tracking in cluttered environment requires the initiation and maintenance of tracks, and track existence probability of true track is kept by Markov Chain Two model of target existence propagation. Unlike Markov Chain One model for target existence propagation, Markov Chain Two model is made up three hypotheses about target existence event which are that the target exist and is detectable, the target exists and is non-detectable through occlusion, and the target does not exist and is non-detectable according to non-existing target. In this paper we present multi-scan single target tracking algorithm based on the target existence, which call the Integrated Track Splitting algorithm with Markov Chain Two model in imaging sensor.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.4E
• /
• pp.9-13
• /
• 1996

We developed an iterative algorithm which could improve the resolution of reconstructed tomograms having random attenuation patterns and analyzed the limitation of this algorithm. The simple back-and forth propagation algorithm has depth resolution about four wavelengths. An iterative algorithm, based on back-and-forth propagation, can be used to improve the resolution of reconstructed tomograms. We analyzed the wavefield for multi-layered specimen and programmed iterative algorithm using Clanguage. Simulation results show that the images get clearer as the number of iterations increases. Also, unambiguous images can be reconstructed using this algorithm even when the layer separation is only two wavelengths. However, this iteration algorithm comes up with an incorrect solution for the number of projections less than five.

• Journal of Environmental Health Sciences
• /
• v.28 no.3
• /
• pp.19-25
• /
• 2002

In this paper, the water quality forecast was performed on the BOD of the Chungju Dam using the ARIMA model, which is a nonlinear statistics model, and the artificial neural network model. The monthly data of water quality were collected from 1991 to 2000. The most appropriate ARIMA model for Chungju dam was found to be the multiplicative seasonal ARIMA(1,0,1)(1,0,1)$_{12}$, model. While the artificial neural network model, which is used relatively often in recent days, forecasts new data by the strength of a learned matrix like human neurons. The BOD values were forecasted using the back-propagation algorithm of multi-layer perceptrons in this paper. Artificial neural network model was com- posed of two hidden layers and the node number of each hidden layer was designed fifteen. It was demonstrated that the ARIMA model was more appropriate in terms of changes around the overall average, but the artificial neural net-work model was more appropriate in terms of reflecting the minimum and the maximum values.s.

• Proceedings of the KSME Conference
• /
• 2003.04a
• /
• pp.678-683
• /
• 2003

Ultrasonic method using SH(shear horizontal) wave has been developed to determine the surface damage in fatigued material. Fatigue damages based on propagation energy were analyzed by multiregression analysis and phase measurement in interrupted fatigue test specimen including CrMoV and 12Cr alloy steel. From the test results, as the fatigue damage increased the propagation time of the launched waves increased and amplitude of wavelet decreased. Also, analysis for the waveform modulation showed a reliable estimation, with confidence limit of 97% for 12Cr steel and 95% for CrMoV steel, respectively. Therefore, It is thought that SH ultrasonic wave technique can be applied to determine fatigue damage of in-service component nondestructively.