• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.7
• /
• pp.1672-1686
• /
• 2013

In this paper, we propose a hybrid super-resolution algorithm robust to cut-change. Existing single-frame based super-resolution algorithms are usually fast, but quantity of information for interpolation is limited. Although the existing multi-frame based super-resolution algorithms generally robust to this problem, the performance of algorithm strongly depends on motions of input video. Furthemore at boundary of cut, applying of the algorithm is limited. In the proposed method, we detect a define boundary of cut using cut-detection algorithm. Then we adaptively apply a single-frame based super-resolution method to detected cut. Additionally, we propose algorithms of normalizing motion vector and analyzing pattern of edge to solve various problems of existing super-resolution algorithms. The experimental results show that the proposed algorithm has better performance than other conventional interpolation methods.

• Journal of KIISE:Software and Applications
• /
• v.26 no.10
• /
• pp.1143-1155
• /
• 1999

셀룰러 방식의 이동통신 시스템에서 전파의 유효신호 도달범위를 예측하기 위해서는 전파전파 모델을 이용한 예측기법이 주로 사용된다. 그러나, 전파과정에서 주변 지형지물에 의해 발생하는 전파손실은 매우 복잡한 비선형적인 특성을 가지며 수식으로는 정확한 표현이 불가능하다. 본 논문에서는 신경회로망의 함수 근사화 능력을 이용하여 전파손실 예측모델을 생성하는 방법을 제안한다. 즉, 전파손실을 송수신 안테나간의 거리, 송신안테나의 특성, 장애물 투과영향, 회절특성, 도로, 수면에 의한 영향 등과 같은 전파환경 변수들의 함수로 가정하고, 신경회로망 학습을 통하여 함수를 근사화한다. 전파환경 변수들이 신경회로망 입력으로 사용되기 위해서는 3차원 지형도와 벡터지도를 이용하여 전파의 반사, 회절, 산란 등의 물리적인 특성이 고려된 특징 추출을 통해 정량적인 수치들을 계산한다. 이와 같이 얻어진 훈련데이타를 이용한 신경회로망 학습을 통해 전파손실 모델을 완성한다. 이 모델을 이용하여 서울 도심 지역의 실제 서비스 환경에 대한 타 모델과의 비교실험결과를 통해 제안하는 모델의 우수성을 보인다.Abstract In cellular mobile communication systems, wave propagation models are used in most cases to predict cell coverage. The amount of propagation loss induced by the obstacles in the propagation path, however, is a highly non-linear function, which cannot be easily represented mathematically. In this paper, we introduce the method of producing propagation loss prediction models by function approximation using neural networks. In this method, we assume the propagation loss is a function of the relevant parameters such as the distance from the base station antenna, the specification of the transmitter antenna, obstacle profile, diffraction effect, road, and water effect. The values of these parameters are produced from the field measurement data, 3D digital terrain maps, and vector maps as its inputs by a feature extraction process, which takes into account the physical characteristics of electromagnetic waves such as reflection, diffraction and scattering. The values produced are used as the input to the neural network, which are then trained to become the propagation loss prediction model. In the experimental study, we obtain a considerable amount of improvement over COST-231 model in the prediction accuracy using this model.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.1A
• /
• pp.8-16
• /
• 2012

Recent work has been shown that cognitive radio systems with multiple antenna at both transmitter and receiver are able to improve performance of secondary users. In such system, the main drawback is the increased complexity and raised cost as the number of antennas increase. It is desirable to apply antenna selection which select a subset of the available antennas so as to solve these problems. In this paper, we consider antenna selection method for cognitive radio systems in correlated channel from the IEEE 802.11n. For a multiple-input multiple-output(MIMO) system with more antennas at transmitter than the receiver, we select the same number of transmit antennas as that of receive antennas. The exhaustive search for optimal antenna becomes impractical. We present criterion for selecting subset in terms of projection of channel correlation vector to increase performance of secondary user with decreasing interference at primary user.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.2
• /
• pp.149-154
• /
• 2004

In this research, we selected the speech recognition to implement the electric wheelchair system as a method to control it by only using the speech and used DTW (Dynamic Time Warping), which is speaker-dependent and has a relatively high recognition rate among the speech recognitions. However, it has to have small memory and fast process speed performance under consideration of real-time. Thus, we introduced VQ (Vector Quantization) which is widely used as a compression algorithm of speaker-independent recognition, to secure fast recognition and small memory. However, we found that the recognition rate decreased after using VQ. To improve the recognition rate, we applied ART2 (Adaptive Reason Theory 2) algorithm as a post-process algorithm to obtain about 5% recognition rate improvement. To utilize ART2, we have to apply an error range. In case that the subtraction of the first distance from the second distance for each distance obtained to apply DTW is 20 or more, the error range is applied. Likewise, ART2 was applied and we could obtain fast process and high recognition rate. Moreover, since this system is a moving object, the system should be implemented as an embedded one. Thus, we selected TMS320C32 chip, which can process significantly many calculations relatively fast, to implement the embedded system. Considering that the memory is speech, we used 128kbyte-RAM and 64kbyte ROM to save large amount of data. In case of speech input, we used 16-bit stereo audio codec, securing relatively accurate data through high resolution capacity.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.586-591
• /
• 2009

In this paper, we propose the mobile object tracking algorithm based on the feature vector using particle filter. To do this, first, we detect the movement area of mobile object by using RGB color model and extract the feature vectors of the input image by using the KLT-algorithm. And then, we get the first feature vectors by matching extracted feature vectors to the detected movement area. Second, we detect new movement area of the mobile objects by using RGB and HSI color model, and get the new feature vectors by applying the new feature vectors to the snake algorithm. And then, we find the second feature vectors by applying the second feature vectors to new movement area. So, we design the mobile object tracking algorithm by applying the second feature vectors to particle filter. Finally, we validate the applicability of the proposed method through the experience in a complex environment.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.40 no.7
• /
• pp.574-581
• /
• 2012

Because of the exposed blade, the UAV using the rotors entail the risks during operation. While a wrapped duct around the fan blades reduces risks, it is a higher thrust performance than the same power load rotor. In this paper, for applying advantages of a ducted fan, the tri-ducted fan air vehicle configuration is proposed. The vehicle has three ducted fans. Two of them are the same shape and size and the third one is the smaller. It is possible to control a rapid attitude stability using thrust vector control. The equations of motion of the tri-ducted fan were derived. Lyapunov control input was applied to the system and stable inputs were derived. A nonlinear simulation was fulfilled by using parameters of a prototype vehicle. It verified a stable attitude and analyzed results.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.3C
• /
• pp.419-425
• /
• 2004

This paper presents a new method which is calculated to use only three vanishing points in order to compute the dimensions of object and its pose from a single image of perspective projection taken by a camera. Our approach is to only compute three vanishing points without informations such as the focal length and rotation matrix from images in the case of perspective projection. We assume that the object can be modeled as a linear function of a dimension vector v. The input of reconstruction is a set of correspondences between features in the model and features in the image. To minimize each the dimensions of the parameterized models, this reconstruction of optimization can be solved by standard nonlinear optimization techniques with a multi-start method which generates multiple starting points for the optimizer by sampling the parameter space uniformly.

• Journal of Sensor Science and Technology
• /
• v.10 no.5
• /
• pp.329-336
• /
• 2001

This paper describes the steering control and geomagnetism cancellation for an autonomous vehicle using an MR sensor. The magneto-resistive (MR) sensor obtains the vector summation of the magnetic fields from embedded magnets and the Earth. The vehicle is controlled by the magnetic fields from embedded magnets. So, geomagnetism is the disturbance in the steering control system. In this paper, we propose a new method of the sensor arrangement in order to remove the geomagnetism and vehicle body interference. The proposed method uses two MR sensors located in a level plane and the steering controller has been developed. The controller has three input variables ($dB_x$, $dB_y$, $dB_z$) using the measured magnetic field difference, and an output variable (the steering angle). A simulation program was developed to acquire the data to teach the neural network, in order to test the ability of a neural network to learn the steering control process. Also, the computer simulation of the vehicle (including vehicle dynamics and steering) was used to verify the steering performance of the vehicle controller using the neural network. From the simulation and field test, good result was obtained and we confirmed the robustness of the neural network controller in a real autonomous vehicle.

• Journal of Korea Game Society
• /
• v.17 no.6
• /
• pp.113-120
• /
• 2017

With the development of virtual reality technology, in recent years, user-friendly hand gesture interface has been more studied for natural interaction with a virtual 3D object. Most earlier studies on the hand-gesture interface are using relatively simple hand gestures. In this paper, we suggest an intuitive hand gesture interface for interaction with 3D object in the virtual reality applications. For hand gesture recognition, first of all, we preprocess various hand data and classify the data through the binary decision tree. The classified data is re-sampled and converted to the chain-code, and then constructed to the hand feature data with the histograms of the chain code. Finally, the input gesture is recognized by MCSVM-based machine learning from the feature data. To test our proposed hand gesture interface we implemented a 'Virtual Block' game. Our experiments showed about 99.2% recognition ratio of 16 kinds of command gestures and more intuitive and user friendly than conventional mouse interface.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.2C
• /
• pp.213-221
• /
• 2004

A new method for design of two-channel finite-impulse response(FIR) quadrature mirror-image filter(QMF) banks with low reconstruction delay using weighting function is proposed. The weighting function used in this paper is calculated from the previous updated filter coefficients vector which is adjusted from iteration to iteration in the design of QMF banks. In this paper, passband and stopband edge frequency are used in design of QMF banks with low delay characteristic in time domain instead of specific frequency interval where the artifacts occur in conventional design method. The investigation of specific frequency interval where artifacts occur can not be required by using passband and stopband edge frequency. Some comparisons of performance are made with other existing design method to demonstrate the proposed method for QMF bank design. and it was observed that the proposed method using the weighted function and passband and stopband edge frequency improves the peak reconstruction error by 0.001 [dB], the peak-to-peak passband ripple by 0.003[dB], SNR with a white noise by 7[dB] and SNR with a step input by 32[dB], but with a reduction of the computational efficiency because of updating the weighting function over the conventional method in Ref [11].