• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.27 no.6
• /
• pp.726-735
• /
• 2003

A Process of 3-D Particle image velocimetry, called here, as '3-D volume PIV' was developed for the full-field measurement of 3-D complex flows. The present method includes the coordinate transformation from image to camera, calibration of camera by a calibrator based on the collinear equation, stereo matching of particles by the approximation of the epipolar lines, accurate calculation of 3-D particle positions, identification of velocity vectors by 3-D cross-correlation equation, removal of error vectors by a statistical method followed by a continuity equation criterior, and finally 3-D animation as the post processing. In principle, as two frame images only are necessary for the single instantaneous analysis 3-D flow field, more effective vectors are obtainable contrary to the previous multi-frame vector algorithm. An Experimental system was also used for the application of the proposed method. Three analog CCD camera and a Halogen lamp illumination were adopted to capture the wake flow behind a bluff obstacle. Among 200 effective particle s in two consecutive frames, 170 vectors were obtained averagely in the present study.

• Journal of Korea Multimedia Society
• /
• v.9 no.1
• /
• pp.11-22
• /
• 2006

Recently face detection has actively been researched due to its wide range of applications, such as personal identification and security systems. In this paper, a new face detection method based on the distribution map is proposed. Face-like regions are first extracted by applying the skin color map with the frequency to a color image and then, possible eye regions are determined by using the pupil color distribution map within the face-like regions. This enables the reduction of space for finding facial features. Eye candidates are detected by means of a template matching method using weighted window, which utilizes the correlation values of the luminance component and chrominance components as feature vectors. Finally, a cost function for mouth detection and location information between the facial features are applied to each pair of the eye candidates for face detection. Experimental results show that the proposed method can achieve a high performance.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.1E
• /
• pp.25-36
• /
• 1994

A problem of making a neural network learning self-adaptive to the training set supplied is addressed in this paper. This arises from the aspect in choice of an adequate stepsize for the update of the current weigh vectors according to the training pairs. Related issues in this attempt are raised and fundamentals in neural network learning are introduced. In comparison to the most popular back-propagation scheme, the usefulness and superiority of the proposed weight update algorithm are illustrated by examing the identification of unknown nonlinear systems only from measurements.

• Annual Conference of KIPS
• /
• 2016.10a
• /
• pp.611-614
• /
• 2016

최근 철도 산업의 비중이 증가함에 따라 열차의 안정적인 주행이 그 어느 때보다 중요한 이슈로 부각되고있다. 특히, 열차의 진로 변경을 위한 핵심 요소인 선로전환기의 결함은 열차의 사고와 직결되는 장비 중 하나로써, 그 이상 여부를 사전에 인지하여 선로전환기의 안정성을 확보하기 위한 유지보수의 지능화 시스템이 필요하다. 본 논문에서는 선로전환기의 작동 시 발생하는 소리정보를 활용하여 선로전환기의 비정상 상황을 분류하는 시스템을 제안한다. 제안하는 시스템은 먼저, 선로전환기의 상황별 소리를 수집하고, 다양한 소리정보를 추출하여 특징 벡터를 생성한다. 다음으로, 딥러닝 모델 중 하나인 DNN(Deep Neural Network)을 이용하여 선로전환기의 비정상 상황을 분류한다. 실제 선로전환기의 전환 시 발생하는 소리 데이터를 기반으로 DNN의 파라미터에 따른 다양한 실험을 수행한 결과, 약 93.10%의 정확도를 갖는 안정적인 DNN 모델을 설계하였다.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.719-724
• /
• 2003

This paper proposed a heuristic to enhance the speed of kNN without loss of its accuracy. The proposed heuristic minimizes the computation of the similarity between two documents which is the dominant factor in kNN. To do this, the paper proposes a method to calculate the upper limit of the similarity and to sort the training documents. The proposed heuristic was implemented on the existing framework of the text categorization, so called, AI :: Categorizer and it was compared with the conventional kNN with the well-known data, Router-21578. The comparisons show that the proposed heuristic outperforms kNN about 30∼40% with respect to the execution time.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.17 no.12
• /
• pp.1254-1261
• /
• 2007

The structure has several types of noise and booming noise of a vehicle is usually caused by the vibration of the vehicle's body transmitted from the engine through the mounting system. Vector synthesis analysis is performed to predict the booming noise when the characteristic of the engine mounting system is changed., i.e., when magnitudes and phases of vibratory forces after the mounts are altered. To use this method effectively, the concept of Multi-dimensional-analysis and Experimental Design are introduced to identify the contributions of each vibration sources and transmission paths to interior noise. It was used 3inputs/1output system and found the magnitudes and phases of the forces for minimizing the noise. Finally, the synthesized interior booming noise level is predicted by the vector synthesis diagram. It is shown that the vector synthesis method can be used to obtain the optimum design characteristic of the mounting system to control the interior booming noise of a vehicle.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.5
• /
• pp.688-693
• /
• 2010

Vision based object recognition in mobile robots has many issues for image analysis problems with neighboring elements in dynamic environments. SURF(Speeded Up Robust Features) is the local feature extraction method of the image and its performance is constant even if disturbances, such as lighting, scale change and rotation, exist. However, it has a difficulty of real-time processing caused by representation of high dimensional vectors. To solve th problem, execution of SURF in GPU(Graphics Processing Unit) is proposed and implemented using CUDA of NVIDIA. Comparisons of recognition rates and processing time for SURF between CPU and GPU by variation of robot velocity and image sizes is experimented.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.12
• /
• pp.2376-2385
• /
• 1994

In receiving the digital TV signal, both decoding delay and the channel hopping delay are very critical factors in applications. The intra-slice coding in the MPEG-2 SIMPLE PROFLE of No B-picture is one of the primary methods for short delay time in video decoding. It has the advantage of short decoding delay, but has the drawback of long channel hopping delay time. In this paper, we propose a method to reduce the channel delay with negligible loss in SNR performance. It is shown that dividing pictures into several regions of slices and adding some restriction in motion vector search for inter-frame coding. hence the random acess points are effectively increased. and the channel hopping delay is reduced.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.12 no.5
• /
• pp.519-526
• /
• 1987

An adaptive estimation system which operates propoerly in the environments corrupted by additive impulse noise in addition to the white Gaussian noise has been proposed. A feed forward loop is inserted into the adaptive estimator proposed by R. L. Moose for a system with an unknown measurement bias by which the improved adaptive estimator is processed successfully without the sum of the time varying weights being zero even when the measurement system is added impulue noise. Successfully processed adaptive estimator has been obtained under the large impulse noise in addition to randomly varying unknown biases condition by giving sufficient large value to the elements of discrete vector on the computer simulation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.3
• /
• pp.371-376
• /
• 2003

In this paper, we proposes a method for recognizing the facial expressions using ICA(Independent Component Analysis)-factorial representation method. Facial expression recognition consists of two stages. First, a method of Feature extraction transforms the high dimensional face space into a low dimensional feature space using PCA(Principal Component Analysis). And then, the feature vectors are extracted by using ICA-factorial representation method. The second recognition stage is performed by using the Euclidean distance measure based KNN(K-Nearest Neighbor) algorithm. We constructed the facial expression database for six basic expressions(happiness, sadness, angry, surprise, fear, dislike) and obtained a better performance than previous works.