• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.331-334
• /
• 2002

In this paper, we present two types of vision algorithm that mobile robot has CCD camera. for obstacle avoidance. This is simple algorithm that compare with grey level from input images. Also, The mobile robot depend on image processing and move command from PC host. we has been studied self controlled mobile robot system with CCD camera. This system consists of digital signal processor, step motor, RF module and CCD camera. we used wireless RF module for movable command transmitting between robot and host PC. This robot go straight until recognize obstacle from input image that preprocessed by edge detection, converting, thresholding. And it could avoid the obstacle when recognize obstacle by line histogram intensity. Host PC measurement wave from various line histogram each 20 Pixel. This histogram Is ( x , y ) value of pixel. For example, first line histogram intensity wave from ( 0, 0 ) to ( 0, 197 ) and last wave from ( 280, 0 ) to ( 280, 197 ). So we find uniform wave region and nonuniform wave region. The period of uniform wave is obstacle region. we guess that algorithm is very useful about moving robot for obstacle avoidance.

• 제어로봇시스템학회논문지
• /
• 제17권5호
• /
• pp.490-498
• /
• 2011

In this paper, we present a two-stage vision-based approach to detect multi views of pedestrian in road scene images. The first stage is HG (Hypothesis Generation), in which potential pedestrian are hypothesized. During the hypothesis generation step, we use a vertical, horizontal edge map, and different colors between road background and pedestrian's clothes to determine the leg position of pedestrian, then a novel symmetry peaks processing is performed to define how many pedestrians is covered in one potential candidate region. Finally, the real candidate region where pedestrian exists will be constructed. The second stage is HV (Hypothesis Verification). In this stage, all hypotheses are verified by Support Vector Machine for classification, which is robust for multi views of pedestrian detection and recognition problems.

• Journal of Magnetics
• /
• 제21권2호
• /
• pp.168-172
• /
• 2016

$BiMnO_3$ has been a promising candidate as a magnetoelectric multiferroic while there have been many controversial reports on its ferroelectricity. The detailed analysis of its film growth, especially the growth of thin film having monoclinic symmetry has not been reported. We studied the effect of miscut angle, the substrate surface, and film thickness on the symmetry of $BiMnO_3$ thin film. A flat $SrTiO_3$ (110) substrate resulted in a thin film with three domains of $BiMnO_3$ and 1 degree miscut in the $SrTiO_3$ (110) substrate resulted in dominant domain preference in the $BiMnO_3$ thin film. The larger miscut resulted in a nearly perfect detwinned $BiMnO_3$ film with a monoclinic phase. This strong power of domain selection due to the step edge of the substrate was efficient even for the thicker film which showed a rather relaxed growth behavior along the $SrTiO_3$ [1-10] direction.

• 한국통신학회논문지
• /
• 제15권3호
• /
• pp.252-259
• /
• 1990

本 論文은 기존 LOCOS工程의 張點을 모두 겸비한 側面璧 SWAMI 技術에 대한 새로운 構造를 提示한다. 새로운 SWAMI공정은 순수 窒化膜 壓力과 體積 膨腸에 기인한 壓力을 크게 줄이기 위해서 側面璧 주위에 얇은 질화막과 反應性이온 飾刻으로 기울어진 실리콘 측면벽을 結合시켰따. 製作된 結果에 의하면, 缺陷이 없는 완전히 새부리 모양이 形成되지 않는 局地的 酸化 공정은 기울어진 面의 異方性 산화 隔離에 의해 實現시킬 수 있었다. 추가적인 마스크 段階는 要求되지 않는다. 이 工程에서 PN 다이오드의 漏泄電流는 기존 LOCOS 공정 보다 減少되었다. 한편 가장자리 部位는 漏泄電流 密度에서 평편한 接合 부위 보다 높게 分析되었다.

• 한국게임학회 논문지
• /
• 제20권3호
• /
• pp.45-54
• /
• 2020

현재 수기로 진행하는 오프라인 바둑 대국의 기보 입력 자동화를 위해서, 대국 현장에서 직접 사용할 전용 임베디드 보드를 이용한 시스템이 필요하다. 본 논문은 임베디드 보드의 영상처리 환경에서 조명에 강건한 처리를 위하여 물체의 형태 정보와 색상 정보를 통합하여 사용하며, 물체 추출을 위해서는 연결 성분 분석, 에지 정보, 색상 정보를 결합해서 사용하고, 영상 처리 각 단계에서 바둑판의 고유 정보를 이용하여 연산단계를 줄였다. 결과적으로 임베디드 환경에서 연산을 최소화하여 실제 실시간 대국 환경에서도 신뢰성 높은 기보를 자동으로 저장할 수 있도록 구현하였다.

• 정보과학회 논문지
• /
• 제42권1호
• /
• pp.33-43
• /
• 2015

최근 특허영상의 중요도가 높아지면서 특허영상 검색에 대한 연구의 필요성이 커지고 있다. 그러나 지금까지 대부분의 특허검색은 이진 영상에서 에지 특징을 추출하는 방법을 주로 사용하고 있어서 영상 전처리 과정에서 에지 검출 결과에 따라 검색 성능이 영향을 받는 단점이 있다. 이러한 문제점을 해결하기 위해, 본 논문에서는 영상의 형태적 특징을 표현하는 SURF를 사용하여 특허영상의 특징을 표현하고 검색하는 방법을 제안한다. 제안하는 방법은 영상에서 SURF를 계산하여 관심점과 방향을 추출하고 영역별 히스토그램을 구한다. 제안하는 방법의 우수성을 평가하기 위해서 제안하는 방법을 2000 이진 특허 영상 데이터베이스에 적용하였고, 에지 정보가 일부 손실되더라도 검색 결과가 매우 뛰어남을 보여주었다.

• 한국산학기술학회논문지
• /
• 제13권8호
• /
• pp.3654-3659
• /
• 2012

능동 윤곽 모델 혹은 스네이크는 영상처리 및 컴퓨터 비전 분야에서 널리 사용되는 분할 방법이다. 능동 윤곽 모델의 가장 큰 문제점은 초기에 설정하는 폐쇄 점들의 개수와 위치에 매우 민감하기 때문에 초기 설정에 따라 결과가 극명하게 달라진다는 것이다. 특히 풍선 형태의 능동 윤곽 모델의 경우 작은 크기에서 시작하여 윤곽선을 만날 때까지 발산하여 그 영역을 넓혀 가기 때문에 초기의 폐쇄 점들의 영역보다 훨씬 커질 경우 더욱 큰 문제점을 보일 수 있다. 본 논문에서는 이러한 문제를 해결하기 위해 폐쇄 점들 간의 거리에 따라 폐쇄 점들의 개수를 변화시킬 수 있는 새로운 알고리즘을 제안한다.

• Advances in Energy Research
• /
• 제3권2호
• /
• pp.117-124
• /
• 2015

In this paper, we have reported an enhancement in thermoelectric properties of un-doped zinc oxide (ZnO) grown by molecular beam epitaxy (MBE) on silicon (001) substrate by annealing treatment. The grown ZnO thin films were annealed in oxygen environment at $500^{\circ}C-800^{\circ}C$, keeping a step of $100^{\circ}C$ for one hour. Room temperature Seekbeck measurements showed that Seebeck coefficient and power factor increased from 222 to $510{\mu}V/K$ and $8.8{\times}10^{-6}$ to $2.6{\times}10^{-4}Wm^{-1}K^{-2}$ as annealing temperature increased from 500 to $800^{\circ}C$ respectively. This observation was related with the improvement of crystal structure of grown films with annealing temperature. X-ray diffraction (XRD) results demonstrated that full width half maximum (FWHM) of ZnO (002) plane decreased and crystalline size increased as the annealing temperature increased. Photoluminescence study revealed that the intensity of band edge emission increased and defect emission decreased as annealing temperature increased because the density of oxygen vacancy related donor defects decreased with annealing temperature. This argument was further justified by the Hall measurements which showed a decreasing trend of carrier concentration with annealing temperature.

• 동아시아경상학회지
• /
• 제10권2호
• /
• pp.105-113
• /
• 2022

Purpose - An increase in automation has been as a result of digital technologies. The data will be instrumental in the determination of the services that are more necessary so that more resources can be allocated for them. The purpose of the current research is to investigate how big data utilization will help increase the profitability in the industry 4.0 era. Research design, Data, and methodology - The present research has conducted the comprehensive literature content analysis. Quantitative approaches allow respondents to decide, but qualitative methods allow them to offer more information. In the next step, respondents are given data collection equipment, and information is collected. Result - The According to qualitative literature analysis, there are five ways in which big data utilization will help increase the profitability in the industry 4.0 era. The five solutions are (1) Better Customer Insight, (2) Increased Market Intelligence, (3) Smarter Recommendations and Audience Targeting, (4) Data-driven innovation, (5) Improved Business Operations. Conclusion - Modern companies have been seeking a competitive advantage so that they can have the edge over other companies in the same industries providing the same services and products. Big data is that technology that businesses have always wanted for an extended period of time to revolutionize their operations, making their businesses more profitable.

• 4차산업연구
• /
• 제2권1호
• /
• pp.9-17
• /
• 2022

Purpose -In general, elementary school is the time to take the first social step away from family relationships with parents or siblings. Recently, AI technology has been widely used in everyday life and society. The purpose of this study is to propose a program that can cultivate AI literacy and self-expression for elementary school students according to the trend of the times. Research design, data, and methodology - In this study, prior to developing a self-expression class program for cultivating AI literacy, we looked at the related literature on what AI literacy is. In addition, the digital learning program was analyzed considering that the current AI literacy is based on the cutting edge of digital technology and is located in the same area as digital literacy. Result -This study developed a curriculum for self-expression and AI literacy cultivation. The main feature of this study is that the education program of this study allows 3rd, 4th, and 5th graders of elementary school to express themselves and to express their career problems by combining culture and art with AI programs. Conclusion -Self-expression activity education for cultivating AI literacy should be oriented toward holistic education and should be education as a way to express oneself in order to improve the quality of life of learners