• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.8
• /
• pp.114-125
• /
• 2014

In a conventional sonar system, which uses LFM signal for detecting targets with varying speed, the results of multiple LFM Doppler correlators are aligned and the maximum alined result are selected as a test cell for detecting targets. As the number of the LFM Doppler correlators are increased for accurate target detection, as the required computational complexity and the memory are also increased. This fact makes it difficult to implement the accurate LFM target detector. In this paper, we propose a new fast target detection which is robust for the variation of target speed. Because the proposed method uses the summation of alined results of large numbers of LFM Doppler correlators, the proposed method increase SNR and provide robust SNR for the variation of target speed. And the proposed method can provide very fast target detection by implementing the process, the summation of alined results of large numbers of LFM Doppler correlators, as one summation filter.

• Journal of the Korea Convergence Society
• /
• v.10 no.11
• /
• pp.79-84
• /
• 2019

Video image based technology is being used in various fields with continuous development. The demand for vision system technology that analyzes and discriminates image objects acquired through cameras is rapidly increasing. Image processing is one of the core technologies of vision systems, and is used for defect inspection in the semiconductor manufacturing field, object recognition inspection such as the number of tire surfaces and symbols. In addition, research into license plate recognition is ongoing, and it is necessary to recognize objects quickly and accurately. In this paper, propose a recognition model through the rotational alignment of objects after checking the angle value of the tilt of the object in the input video image for the recognition of inclined objects such as numbers or symbols marked on the surface. The proposed model can perform object recognition of the rotationally sorted image after extracting the object region and calculating the angle of the object based on the contour algorithm. The proposed model extracts the object region based on the contour algorithm, calculates the angle of the object, and then performs object recognition on the rotationally aligned image. In future research, it is necessary to study template matching through machine learning.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.05a
• /
• pp.231-235
• /
• 2001

순수한 부울 검색 시스템은 문서와 질의 사이의 유사도를 나타내는 문서값을 계산할 수 없기 때문에, 검색된 문서들을 질의를 만족하는 정보에 따라 정렬할 수 없다. 부울 검색 시스템의 이러한 단점을 보완하는 방법으로 MMM 모델, Paice 모델, P-norm 모델이 개발되었다. 본 논문에서는 높은 검색 효과를 제공하는 질의분해 적합성 피드백(QSRF) 모델을 제안한다. 질의 분해 적합성 피드백 모델의 연산 특성이 MMM, Paice, P-norm 모델보다 우수함을 설명하고, 또한 성능 비교를 통하여 이를 입증한다.

• Journal of Aerospace System Engineering
• /
• v.12 no.4
• /
• pp.64-74
• /
• 2018

Small high-resolution Earth observation satellites require precise optical alignment at the submicron level. However, misalignments can occur due to the influence of external factors during the launch and operation despite the sufficient alignment processes that take place before the launch. Thus, satellites need to realign their optical elements in orbit in what is known as a refocusing process to compensate for any misalignments. Refocusing algorithms developed for satellites have only considered de-space, which is the most sensitive factor with respect to image quality. However, the existing algorithms can cause correction error when inner and external forces generate tilt amount in an optical system. The present work suggests an improved online refocusing algorithm by considering the tilting effect for application in the case of a de-spaced and tilted optical system. In addition, the algorithm is considered to be efficient in terms of time and cost because it is designed to be used as an online method that does not require ground communication.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1233-1240
• /
• 2010

In the flat panel display and semiconductor industries, the visual alignment system is considered as a core technology which determines the productivity of a manufacturing line. It consists of the vision system to extract the centroids of alignment marks and the stage control system to compensate the alignment error. In this paper, we develop a Kalman filter algorithm to estimate the alignment mark postures and propose a coarse-fine alignment control method which utilizes both original fine images and reduced coarse ones in the visual feedback. The error compensation trajectory for the distributed joint servos of the alignment stage is generated in terms of the inverse kinematic solution for the misalignment in task space. In constructing the estimation algorithm, the equation of motion for the alignment marks is given by using the forward kinematics of alignment stage. Secondly, the measurements for the alignment mark centroids are obtained from the reduced images by applying the geometric template matching. As a result, the proposed Kalman filter based coarse-fine alignment control method enables a considerable reduction of alignment time.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.30 no.8
• /
• pp.37-45
• /
• 2002

A two-dimensional unsteady, inviscid flow solver has been developed for the simulation of airfoil-vortex interactions on unstructured dynamically adapted meshes. The Euler solver is based on a second-order accurate implicit time integration using a point Gauss-Seidel relaxation scheme and a dual time-step subiteration. A vertex-centered, finite-volume discretization is used in conjunction with the Roe's flux-difference splitting. An unsteady solution-adaptive dynamic mesh scheme is used by adding and deleting mesh points to take account of both spatial and temporal variations of the flow field. The effect of vortex interaction on the aeroelastic displacement of an airfoil attached to the idealized two degree-of-freedom spring system is investigated.

• Korean Journal of Optics and Photonics
• /
• v.14 no.5
• /
• pp.535-544
• /
• 2003

The sensitivity analysis of a middle wave infrared optical system with 20: 1 zoom ratio is performed to analyze manufacturing and alignment tolerances, and to establish the alignment logic and the focus control strategy. The characteristics of the sensitivities of Zernike coefficients are investigated to all mechanical displacements and several zoom positions using Code-V Macro. From this result, the tolerances of manufacturing and alignment of the optical system are derived and the effective alignment logic is established. Futhermore, an effective focus control strategy is established to make the system simple and compact.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.1A
• /
• pp.54-61
• /
• 2010

We propose a subspace interference alignment by orthogonalization of reference vectors. The proposed method improves the sum-rate capacity degradation due to the channel decomposition error and channel estimation error in the real environment. Using the proposed method, each cell uses the reference vector that is orthogonal to the adjacent cells. Then the residual interference produced by the channel decomposition error and the channel estimation error is decreased. The simulation results demonstrate that the proposed method achieves the enhanced sum-rate capacity.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.398-401
• /
• 2018

본 연구에서는 심충 합성곱 신경망(Deep CNN)과 Connectionist Temporal Classification (CTC) 알고리즘을 사용하여 강제정렬 (force-alignment)이 이루어진 코퍼스 없이도 학습이 가능한 음소 인식 모델을 제안한다. 최근 해외에서는 순환 신경망(RNN)과 CTC 알고리즘을 사용한 딥 러닝 기반의 음소 인식 모델이 활발히 연구되고 있다. 하지만 한국어 음소 인식에는 HMM-GMM 이나 인공 신경망과 HMM 을 결합한 하이브리드 시스템이 주로 사용되어 왔으며, 이 방법 은 최근의 해외 연구 사례들보다 성능 개선의 여지가 적고 전문가가 제작한 강제정렬 코퍼스 없이는 학습이 불가능하다는 단점이 있다. 또한 RNN 은 학습 데이터가 많이 필요하고 학습이 까다롭다는 단점이 있어, 코퍼스가 부족하고 기반 연구가 활발하게 이루어지지 않은 한국어의 경우 사용에 제약이 있다. 이에 본 연구에서는 강제정렬 코퍼스를 필요로 하지 않는 CTC 알고리즘을 도입함과 동시에, RNN 에 비해 더 학습 속도가 빠르고 더 적은 데이터로도 학습이 가능한 합성곱 신경망(CNN)을 사용하여 딥 러닝 모델을 구축하여 한국어 음소 인식을 수행하여 보고자 하였다. 이 모델을 통해 본 연구에서는 한국어에 존재하는 49 가지의 음소를 추출하는 세 종류의 음소 인식기를 제작하였으며, 최종적으로 선정된 음소 인식 모델의 PER(phoneme Error Rate)은 9.44 로 나타났다. 선행 연구 사례와 간접적으로 비교하였을 때, 이 결과는 제안하는 모델이 기존 연구 사례와 대등하거나 조금 더 나은 성능을 보인다고 할 수 있다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.78-83
• /
• 2014

Recently, a rapid growth of wind power system as a leading renewable energy source has compelled a number of companies to develop intelligent monitoring and diagnostic system. Such systems can detect early mechanical faults, which prevents from costly repairs. Generally, fault diagnostic system for wind turbines is based on vibration and process signal analysis. In this work, different type of mechanical faults such as mass unbalance and shaft misalignment which can always happen in wind turbine system is considered. The proposed intelligent fault diagnostic algorithm utilizes artificial neural network and Wavelet transform. In order to verify the feasibility of the proposed algorithm, mechanical fault generation experimental system manufactured by Gaon corporation is utilized.