• 제목/요약/키워드: real self-image

검색결과 151건 처리시간 0.022초

퍼지기반 신경망모형을 이용한 대기행렬 검지 (Queue Detection using Fuzzy-Based Neural Network Model)

  • KIM, Daehyon
    • 대한교통학회지
    • /
    • 제21권2호
    • /
    • pp.63-70
    • /
    • 2003
  • 실시간 교차로의 대기행렬길이 검지는 지능형교통체계의 중요부분인 교통관제를 위해서 매우 중요하다. 특히 교통정보수집을 위한 영상기반 기술은 전통적인 루프검지기 또는 기타 타 검지기에 비하여 내재된 여러 이점 때문에 많은 연구가 진행되어 왔다. 그러나 현장 적용시 흔히 발생하는 영상에서의 잡음 및 주변 물체로부터 투영되는 음영 등에 의해 나타나는 차량의 오검지율을 줄이고 수집되는 교통정보의 신뢰도를 높이기 위해서는 보다 효과적인 알고리즘개발이 요구된다. 본 연구에서는 영상처리를 이용한 대기행렬길이 검지를 위한 알고리즘을 제시하였다. 실시간 데이터 수집 및 분석 그리고 패턴분석에 우수한 것으로 알려진 신경망 모형을 이용하였으며, 특히 시스템 신뢰성을 높이기 위하여 퍼지이론이 접목된 퍼지 뉴런모델인 Fuzzy ARTMAP을 모형에 도입하였다. 실험결과 본 연구에서 제시한 대기행렬 측정 방법은 매우 우수한 검지 능력을 보였으며, 대기행렬 검지뿐만 아니라 신뢰성 높은 차량검지 및 차종분류를 위해서도 활용할 수 있을 것으로 기대된다.

여중생의 체형인식 개선을 위한 영양교육 프로그램 개발(II);여중생 대상 영양교육 프로그램 개발 (The Development of Nutrition Education Program for Improvement of body Perception of Middle School Girls (II);Development of Nutrition Education Program)

  • 소혜경;이은주;최봉순
    • 한국식생활문화학회지
    • /
    • 제23권1호
    • /
    • pp.130-137
    • /
    • 2008
  • If we may practice the nutrition education planned on the basis which carefully grasped the inappropriate behavioral determinants of middle-school students, it might be an effective method achieving the change in perception and behavior improving the distorted perception about the ideal body shape, so we are to suggest the 8 week program of body shape perception improvement for successful nutrition education as follows. The body shape perception improvement program is a step-by-step group consulting program. At the introduction stage, we let them understand the meaning of true beauty and body change of teenage period and forming of sexual identity. At the stage of perception conversion, we let them have the opportunity to observe the status of body perception of the teenager and self-observation. At the stage of correction, we let them criticize the distorted body image in the society with mass media at the same time with the self-reflection. At the stage of maintenance and evaluation, we suggested the behavior guidance while preparing it. Setting this as the basis, we applied the contents such as the evaluations through cultural sharing events making somethings while directly participating. As the target groups to practice education were middle school students, we considered the learning level and behavioral features of the middle school students, and composed the programs including the methods such as role play, watching real things, media production, discussions and experiences. If the program of body shape perception improvement developed at this study could be utilized at the field of schools, the teenagers can change their ways of thought naturally avoiding the view about unified appearance rightly perceiving negative self-image that the teenagers can have and if the group consulting can be practiced regularly at each school, many students may experience the change in perception, so it might solicit the improvement of health of the families and local societies as well as that of the individual student.

Development of Left Turn Response System Based on LiDAR for Traffic Signal Control

  • Park, Jeong-In
    • 한국컴퓨터정보학회논문지
    • /
    • 제27권11호
    • /
    • pp.181-190
    • /
    • 2022
  • 이 논문에서 우리는 기존의 영상식 또는 루프식 좌회전 감응 시스템과는 달리 라이다(LiDAR)센서 및 영상 카메라를 이용하여, 좌회전 대기 차량을 2중으로 검지하고 좌회전 차선의 대기 길이에 대응하는 좌회전 교통신호체계를 효율적으로 부여할 수 있는 시스템을 소개하였다. LiDAR 센서에 의해 송수신된 LiDAR 신호에 대해서는 실시간으로 좌회전 대기 차량을 검지하고, 영상 카메라에 의한 영상에 대해서는 실시간 또는 일정한 주기별로 분석하도록 구성함으로써 불필요한 연산 처리를 절감시켜 실시간 감응 처리가 가능하도록 하였다. 실제 신호처리기를 이용한 교차로 시뮬레이션으로 1주일 동안 매일 5시간 성능 테스트를 해 본 결과 기존 방식에 비해 3%~5% 향상된 99.9%의 검지율을 기록하였다. 장점으로는 LiDAR 센서로 99.9% 좌회전 대기 차량이 검지되었으며 의도적인 검지 누락을 발생시키더라도, 영상에 의한 자체 보정을 통해 즉각적인 대응이 가능하여 좌회전 대기 차량의 과도한 대기시간을 조절시켜 교차로 내 모든 차선의 교통흐름을 원활하게 유도할 수 있었다. 또한 좌회전 차량이 뜸한 외곽의 교차로에 적용 시 불필요한 신호 비용을 줄이는 등 서비스 신뢰도 및 효율성을 높일 수 있다.

문학 작품을 통한 향토 음식 콘텐츠 개발 - 충무공 '현충(顯忠) 밥상', 추사 김정희 '추사(秋史) 밥상' (Development on Native Local Food Contents through Literature)

  • 김미혜;정혜경
    • 동아시아식생활학회지
    • /
    • 제20권5호
    • /
    • pp.639-654
    • /
    • 2010
  • This study attempted to research the local food of various regions at a personal level by discovering how food has developed das part of a region's culture base. Discovery of the characteristic story behind the making of a region's characteristic food as local delicacies can inspire self-esteem in the culture, and enhance the real-life image as appropriate to a region, and thereby be made a part of local tourism and thus contributing to the local economy. For this reason, the native foods of the region of Chungcheongnam-do were researched in terms of the cultural sensibilities that inform the unique history of that region. The study was designed so as to aid in understanding food's characteristic value in Chungcheongnam-do and to give a historical representation of Chungcheongnam-do's image by means of storytelling techniques; thus, the local food's character can be presented alongside a story that appeals to the five senses. For this purpose, Chungcheongnam-do's representative native rice table was cast as the 'Hyunchoong rice meal table' - after the figure of admiral Yi Sun Shin of Asan area region, a representative image of Chungcheongnam-do - and 'Choosa rice meal table', after the figure of 'Choosa' Kim Jeong Hee of Yesan region, of which various literary works form a representative image of Chungcheongnam-do. 'Hyunchoong rice meal table' was composed of a health food centered menu which could supply sufficient nutrition as a food ration in times of war or winter shortage, thus providing an image of nutrition and power as appropriate to these situations. Also, to assess the health effectiveness of each rice table, the functionality of the ingredients were investigated as reported in 'Sik-ryo-chan-yo : a dietary treatment' which was published by Soon-Ui Cheon in the Chosun era and by which the foods of the early Chosun era won recognition as being both healthy profitable.

부분 top-view 영상을 이용한 차선 이탈 검출 (Lane Departure Detection Using a Partial Top-view Image)

  • 박한동;오정수
    • 한국정보통신학회논문지
    • /
    • 제21권8호
    • /
    • pp.1553-1559
    • /
    • 2017
  • 본 논문은 자동차 전방에 장착된 단일 카메라를 이용한 차선 이탈 검출 알고리즘을 제안한다. 제안된 알고리즘은 카메라에 의해 취득된 영상으로부터 top-view 공간에 지정된 작은 관심 영역을 위한 부분 top-view 영상을 생성하고, 작은 부분 top-view 영상에서 차선을 검출하고, 미리 지정된 가상 자동차와 검출된 차선들의 겹침을 조사해 차선 이탈을 결정한다. 또한 제안된 알고리즘은 차선 사이에서 차선 이탈 검출을 방해하는 도로 표기 (잡음)에 의한 직선들의 제거와 이전 프레임의 차선 정보를 이용한 손실된 차선의 예측을 포함한다. 실제 주행 동영상을 이용한 차선 이탈 검출 실험에서 제안된 알고리즘은 차선 유지 상태에서 99.0%, 차선 이탈 상태에서 94.7%를 정상적으로 검출한다.

ROV Manipulation from Observation and Exploration using Deep Reinforcement Learning

  • Jadhav, Yashashree Rajendra;Moon, Yong Seon
    • Journal of Advanced Research in Ocean Engineering
    • /
    • 제3권3호
    • /
    • pp.136-148
    • /
    • 2017
  • The paper presents dual arm ROV manipulation using deep reinforcement learning. The purpose of this underwater manipulator is to investigate and excavate natural resources in ocean, finding lost aircraft blackboxes and for performing other extremely dangerous tasks without endangering humans. This research work emphasizes on a self-learning approach using Deep Reinforcement Learning (DRL). DRL technique allows ROV to learn the policy of performing manipulation task directly, from raw image data. Our proposed architecture maps the visual inputs (images) to control actions (output) and get reward after each action, which allows an agent to learn manipulation skill through trial and error method. We have trained our network in simulation. The raw images and rewards are directly provided by our simple Lua simulator. Our simulator achieve accuracy by considering underwater dynamic environmental conditions. Major goal of this research is to provide a smart self-learning way to achieve manipulation in highly dynamic underwater environment. The results showed that a dual robotic arm trained for a 3DOF movement successfully achieved target reaching task in a 2D space by considering real environmental factor.

평판 디스플레이 결함 검출을 위한 자기 참조 PCSR-G 기법 (Self-Reference PCSR-G Method for Detecting Defect of Flat Panel Display)

  • 김진형;이태영;고윤호
    • 한국멀티미디어학회논문지
    • /
    • 제18권3호
    • /
    • pp.312-322
    • /
    • 2015
  • In this paper a new defect detection method for flat panel display that does not require any separately prepared reference images and shows robustness against problems with regard to pixel tolerance and nonuniform illumination condition is proposed. In order to perform defect detection under any magnification value of camera, the proposed method automatically obtains the value of pattern interval through an image analysis. Using the information for pattern interval, an advanced PCSR-G method presented in this paper utilizes neighboring patterns as its reference images instead of utilizing any separately prepared reference images. Also this paper proposes a scheme to improve the performance of the conventional PCSR-G method by extracting and applying additional information for pixel tolerance and intensity distribution considering the value of pattern interval. Simulation results show that the performance of the proposed method utilizing pixel tolerance and intensity distribution is superior to that of the conventional method. Also, it is proved that the proposed method that is implemented using parallel technique based on GPGPU can be applied to real system.

패션블로그에서 퍼스널 스타일 표현형식 (Representation Forms of Personal Style on the Fashion Blogs)

  • 서성은
    • 한국의류산업학회지
    • /
    • 제16권5호
    • /
    • pp.689-697
    • /
    • 2014
  • This study aims to analyze the representation forms of bloggers' personal style on the fashion blogs and enlighten their values which can be actively applied to design and marketing in fashion industry. Image representation of fashion bloggers is reflected by the characteristics in the digital environment, which are the creative manipulation of expression and the production of virtual and fantastic images by taking advantage of the composite medium such as images, music, videos, articles, etc. Also real time updates in blog indicate the latest trends in terms of the representation of image as the actual currency. The study conducted case studies of 5 women's personal fashion blogs through the verification of a variety of global fashion media and blog ranking sites: Style Bubble, Style Rookie, The Cherry Blossom Girl, The Blond Salad, and Fashion Toast. Research findings are as follows. First, the application of creative design elements is indicated as symbolic items, self-made designs, DIY, and various mix and match emphasizing design elements such as color, patterns, proportion, etc. Second, the virtual representation is very highlighted on the story telling applied by film like production or digital effect. Third, the commercial application with mainly sponsored wardrobe and designer collaboration indicates promoting a updated trend as well as a specific brand or designer to make their business profits.

STM 이미지와 산소 흡탈착 그리고 N-docosyl-N'-methyl viologen의 흡착으로부터 구한 다결정 금 전극 표면의 거칠기의 비교 (Comparison of Roughnesses of Polycrystalline Gold Electrode Calculated from STM Images, Oxygen Adsorption-Desorption and Adsorption of N-Docosyl-N'-methyl Viologen)

  • 이치우;장재만
    • 전기화학회지
    • /
    • 제3권2호
    • /
    • pp.104-108
    • /
    • 2000
  • 전기화학에 있어서 전극 물질의 실제 거칠기(real roughness)를 아는 것은 매우 중요하다. 그러나 여러 가지 이유 때문에 전극 물질의 절대적인 거칠기를 아는 것은 불가능하다. 여기에서는 scanning tunneling microscopy (STM), 순환전압전류법을 이용하여 전기화학에서 자주 사용하는 다결정 금 전극의 거칠기를 구하여 Au(111), HOPG로부터 구한 거칠기와 비교해 보았다. STM으로부터 얻은 다결정 금전극의 거칠기는 $1.1(\pm0.1)$,산소의 탈착으로부터는 $2.4(\pm0.7)$, N-docosyl-N'-methyl viologen의 흡착으로부터 는 $1.6(\pm0.1)$이 얻어졌다.

A Study on Kohenen Network based on Path Determination for Efficient Moving Trajectory on Mobile Robot

  • Jin, Tae-Seok;Tack, HanHo
    • International Journal of Fuzzy Logic and Intelligent Systems
    • /
    • 제10권2호
    • /
    • pp.101-106
    • /
    • 2010
  • We propose an approach to estimate the real-time moving trajectory of an object in this paper. The object's position is obtained from the image data of a CCD camera, while a state estimator predicts the linear and angular velocities of the moving object. To overcome the uncertainties and noises residing in the input data, a Extended Kalman Filter(EKF) and neural networks are utilized cooperatively. Since the EKF needs to approximate a nonlinear system into a linear model in order to estimate the states, there still exist errors as well as uncertainties. To resolve this problem, in this approach the Kohonen networks, which have a high adaptability to the memory of the inputoutput relationship, are utilized for the nonlinear region. In addition to this, the Kohonen network, as a sort of neural network, can effectively adapt to the dynamic variations and become robust against noises. This approach is derived from the observation that the Kohonen network is a type of self-organized map and is spatially oriented, which makes it suitable for determining the trajectories of moving objects. The superiority of the proposed algorithm compared with the EKF is demonstrated through real experiments.