• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.3
• /
• pp.91-98
• /
• 2016

Detection and classification of underwater objects in sonar imagery are challenging problems. This paper proposes a system that detects and identifies underwater objects at the sea floor level using a sonar image and image processing techniques. The identification process of underwater objects consists of two steps; detection of candidate regions and identification of underwater objects. The candidate regions of underwater objects are extracted by image registration through the detection of common feature points between the reference background image and the current scanning image. And then, underwater objects are identified as the closest pattern within the database using eigenvectors and eigenvalues as features. The proposed system is expected to be used in efficient securement of Q route in vessel navigation.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.4
• /
• pp.482-486
• /
• 2010

Recently, gesture recognition methods based on dynamic time warping (DTW) have been actively investigated as more mobile devices have equipped the accelerometer. DTW has no additional training step since it uses given samples as the matching templates. However, it is difficult to apply the DTW on mobile environments because of its computational complexity of matching step where the input pattern has to be compared with every templates. In order to address the problem, this paper proposes a gesture recognition method based on DTW that uses localized subset of templates. Here, the k-means clustering algorithm is used to divide each class into subclasses in which the most centered sample in each subclass is employed as the localized template. It increases the recognition speed by reducing the number of matches while it minimizes the errors by preserving the diversities of the training patterns. Experimental results showed that the proposed method was about five times faster than the DTW with all training samples, and more stable than the randomly selected templates.

• The Proceeding of the Korean Institute of Electromagnetic Engineering and Science
• /
• v.5 no.2
• /
• pp.46-54
• /
• 1994

In this paper, an analysis and design method is proposed, which is to improve the directivity of microstrip array antennas conformed to a cylindrical surface. In the case of forming an arc-array in the circumferential direction on a circula-cylinder surface, the circular-cylinder can be approximated to a polygonal-pillar and on each pillar-planes the sub-arrays, Dolph-Tschebyscheff array and uniform array with a beam steered in the desired direction, would make a sharp directivity for the total cylin- drical array antenna. And the radiation pattern according to the type of its sub arrays is analyzed and compared using the cylindrical-cavity codel. A cylindrical microstrip array antenna, with 12 elements and uniform arra as a sub-array which have an equal distance$\lambda_0$/2between the elements, is manufactured and conformed to a cylinder with radius of 6 The measured data of side lobe level, HPBW and FNBW are - 13dB, $9^{\circ}$, and $15{\circ}$, ,respectively. This result shows a good improvement on the directivity comparing with a linear array.

• The Journal of the Korea Contents Association
• /
• v.16 no.7
• /
• pp.689-699
• /
• 2016

As the demand for LCD increases, the importance of inspection equipment for improving the efficiency of LCD production is continuously emphasized. The pattern inspection apparatus is one that detects minute defects of pattern quickly using optical equipment such as line scan camera. This pattern inspection apparatus makes a decision on whether a pixel is a defect or not using a single threshold value in order to meet constraint of real time inspection. However, a method that uses an adaptive thresholding scheme with different threshold values according to characteristics of each region in a pattern can greatly improve the performance of defect detection. To apply this adaptive thresholding scheme it has to be known that a certain pixel to be inspected belongs to which region. Therefore, this paper proposes a region matching algorithm that recognizes the region of each pixel to be inspected. The proposed algorithm is based on the pattern matching scheme with the consideration of real time constraint of machine vision and implemented through GPGPU in order to be applied to a practical system. Simulation results show that the proposed method not only satisfies the requirement for processing time of practical system but also improves the performance of defect detection.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.4
• /
• pp.318-327
• /
• 2009

In this paper, we propose a 3-D geometric localization method for near-field broadband source in shallow water environments. According to the waveguide invariant theory, slope of the interference pattern which is seen in a sensor spectrogram directly proportional to a range of the source. The relative ratio of the range between source and sensors was estimated by matching of two interference patterns in spectrogram. Then this ratio is applied to the Apollonius's circle which shows the locus of a source whose range ratio from two sensors is constant. Two Apollonius's circles from three sensors make the intersection point that means the horizontal range and the azimuth angle of the source. And this intersection point is constant with source depth. Therefore the source depth can be estimated using 3-D hyperboloid equation whose range difference from two sensors is constant. To evaluate a performance of the proposed localization algorithm, simulation is performed using acoustic propagation program and analysis of localization error is demonstrated. From simulation results, error estimate for range and depth is described within 50 m and 15 m respectively.

• Journal of Advanced Navigation Technology
• /
• v.12 no.5
• /
• pp.494-501
• /
• 2008

In this paper, to merge whole 3D information of an occluded body from view point, the new image merging algorithm is introduced after obtaining images of body on the turn table from 4 directions. The two images represented by polygon meshes are merged using weight bipartite matching method with different weights according to coordinates and axes based on minimum distance since two images merged don't present abrupt variation of 3D coordinates and scan direction is one direction. To obtain entire 3D information of body, these steps are repeated 3 times since the obtained images are 4. This proposed method has advantage 200 - 300% searching time reduction rather than conventional branch and bound, dynamic programming, and hungarian method though the matching accuracy rate is a little bit less than these methods.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10d
• /
• pp.586-590
• /
• 2006

본 논문에서는 다이아몬드 탐색(diamond search, DS)과 효율적인 3 단계 탐색(efficient three-step search, E3SS) 등의 블록 정합 기법(block matching algorithm, BMA)들에서 이용된 작은 다이아몬드(small diamond) 패턴을 광역 탐색에 적합하도록 확장시킨 고속의 움직임 추정 알고리즘을 제안한다. 제안된 알고리즘에서는 탐색 윈도우(search window)의 중앙으로부터 설치된 정사각형 패턴의 크기가 내부에서 대수적으로 감소되며 작은 다이아몬드 탐색(small diamond search, SDS) 기법에 의해 탐색이 완료된다. 실험 결과는 제안된 알고리즘이 DS 보다 평균 3개의 탐색 점을 더 적게 사용하고 E3SS에 비하여 약 5개 정도의 탐색 점 수에 대한 이득을 보이지만 움직임 추정상의 정확도는 다른 고속 BMA들과 거의 동일한 수준을 유지하는 것으로 확인된다.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2006.05a
• /
• pp.205-210
• /
• 2006

본 논문에서는 간섭계와 직렬 위상 카드를 이용한 광 보안 시스템을 제안하였다. 먼저 원영상을 암호화하기 위해 원영상을 암호화하는 것이 아니라 원영상에 대한 이진 위상 컴퓨터형성홀로그램을 반복 알고리즘을 이용하여 구하고, 이진 위상 컴퓨터형성홀로그램과 무작위 생성된 위상 키 영상과의 XOR 연산을 통해 암호화된 영상을 구한다. 홀로그램의 복호화 과정은 암호화된 영상과 암호화시에 사용된 무작위 위상 영상 키를 직렬 정합시킨 후, 기준파와의 간섭에 의해 수행된다. 이때, 간섭패턴은 주위 환경에 상당히 민감하다. 그래서 광굴절매질의 자기위상공액성질을 이용하여 안정된 간섭패턴을 얻는다. 그리고 원영상은 복원된 홀로그램을 위상 변조한 후, 역푸리에 변환하여 최종적으로 구한다. 제안된 시스템에서는 암호화시에 사용된 무작위 키 영상 정보가 없으면 전혀 복원이 되지 않고, 키 영상을 달리함에 따라 복원되는 홀로그램의 패턴을 달리할 수 있으므로 차별화된 인증 시스템에 활용할 수 있다. 그리고 홀로그램의 성질에 의해 암호화된 영상이 일부 절단되더라도 원래의 영상을 복원할 수 있다.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2735-2737
• /
• 2001

비젼 검사시스템에서 기판에 존재하는 납 형상의 패턴을 분류함으로써 사전에 불량을 줄일 수 있다. 이러한 경우 대부분의 불량은 부정확한 납의 위치 및 두께로 인해 발생하게 되는데, 이러한 문제를 해결하기 위해 주어진 경계 내에 불분명하게 형성된 납의 형태 및 두께를 정상과 불량으로 분류하기 위해 무게중심점에 기초한 정합과 XOR연산을 이용한 비젼 검사시스템을 제안하였다. 제안한 비젼 검사시스템을 인쇄회로기판상의 납땜형상 패턴에 적용하여 제안한 방법의 성능을 검증하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.238-241
• /
• 2019

본 연구에서는 사회인들의 정해진 패턴을 IoT를 기반으로 AI 기술을 활용하여 Deep Learning 기술을 적용하여 행동패턴을 자동으로 시스템에 업로드 한다. 업로드된 데이터는 Deep Learnig 기술을 통해 유의미한 데이터를 추출하고 이를 각종 가전제품에 제공한다. 데이터의 정합도를 높이기 위해서 초기 데이터는 사용자가 입력한 정해진 생활 패턴을 바탕으로 하며 가우시안 분포를 따르는 난수를 생성하여 training data set으로 사용하여 실제 학습에 적용시켰다. 실생활에서 자동으로 데이터를 활용하기 위해서 IoT기기를 연결하여 AI 학습을 진행하였다. 사회인들은 이 시스템을 통해 집에 들어올 때와 집 밖에 외출할 때 댁내에 있는 편리한 서비스를 제공받을 수 있다.