• 제목/요약/키워드: Eye location

검색결과 148건 처리시간 0.032초

실내 가시광 통신 시스템에서 성능에 영향을 주는 요인에 관한 연구 (A Study About Fact Influence on Performance at Indoor Visible Light Communication)

  • 이창우;최덕재;김한필
    • 조명전기설비학회논문지
    • /
    • 제27권10호
    • /
    • pp.1-8
    • /
    • 2013
  • Wireless Visible Light Communication is the technology that enables communication using LED illumination Infrastructure instead of existing illumination such as incandescent lamp or fluorescent light. Because VLC uses light for communication, it has no problem of frequency permission and is harmless to human body. It is also possible to check the communication through eye. So VLC can be used as a supplement to the Radio Frequency communication, Infrared in indoor environment. So far, researchers on the LED Visible light communication have focused on the increasing transmission speed, transmission distance, modulation method. However, there is few research of main factors that influence on system performance. System performance has been mainly predicted through simulation. In this paper, I recognized that these factors such as outside light noise, obstacle, LED panel position or emitted angle have a great impact on wireless communication system. So I experimented VLC system by changing distance and position to discover location suitable for BER regulation.

Facal motion 예측 및 영역 검출을 위한 칼만 필터 알고리즘 (A Study on the Facal motion and for Detection of area Using Kalman Fillter algorithm)

  • 석경휴;박부연
    • 한국전자통신학회논문지
    • /
    • 제6권6호
    • /
    • pp.973-980
    • /
    • 2011
  • 본 논문에서는 기존의 문제점인 얼굴 움직임이 있을 시 시선 식별이 어려운 점과 사용자에 따른 교정작업이 필요하다는 점을 해결하고자 새로운 시선 식별 시스템을 제안한다. Kalman필터를 사용하여 현재 머리의 위치정보를 이용하여 미래위치를 추정하였고 얼굴의 진위 여부를 판단하기 위해서 얼굴의 특징요소를 구조적 정보와 비교적 처리시간이 빠른 수평, 수직 히스토그램 분석법을 이용하여 얼굴의 요소를 검출한다. 그리고 적외선 조명기를 구성하여 밝은 동공효과를 얻어 동공을 실시간으로 검출, 추적하였고 동공-글린트 벡터를 추출한다.

Study on the Environmental Design Principles and Cultural Landscape of the Yangdong Traditional Village

  • Shin, Snag-Sup
    • 한국환경과학회지
    • /
    • 제12권2호
    • /
    • pp.101-109
    • /
    • 2003
  • Yangdong village is located at Kangdong-myun, Kyungju, Kyungsangbuk-do, Korea. There are two major families, the Sons of Wallsung beginned from Son, So(1433∼1484) and the Lees of Yeohkang the descendant of Lee, Unjeok. They are lived together under check and help for 500 years. The village located on the hill of Ankang plain. There are Homyung mountain and Sonaiu peak in front of it and Solchang mountain on the back. 47 shaped ridges form Blue dragon to the east, and White tiger to the west. Ahnrockchon flows from north Joined Hyungsan river and flows into Youngilman. Therefore the village is located at mountain on it's back and along with stream. Buildings are deployed on the valley between hills, it is not easily detected, but it give it's atmosphere of mountain village. Village location and space composition combined with natural environment, folk belief, feng-shui, and social system of confucianism. Blended buildings affected between ruling and ruled classes or among different families shown environmental design accomplishing united cultural space. The prospect of Yangdong village, a mountain village, expressed two sides of visible scenery of open inside and invisible from outside. Observation point such as head family house, pavilion, and village school are deployed at the point taking bird's-eye view, which striving mental stability.

어안 이미지의 배경 제거 기법을 이용한 실시간 전방향 장애물 감지 (Real time Omni-directional Object Detection Using Background Subtraction of Fisheye Image)

  • 최윤원;권기구;김종효;나경진;이석규
    • 제어로봇시스템학회논문지
    • /
    • 제21권8호
    • /
    • pp.766-772
    • /
    • 2015
  • This paper proposes an object detection method based on motion estimation using background subtraction in the fisheye images obtained through omni-directional camera mounted on the vehicle. Recently, most of the vehicles installed with rear camera as a standard option, as well as various camera systems for safety. However, differently from the conventional object detection using the image obtained from the camera, the embedded system installed in the vehicle is difficult to apply a complicated algorithm because of its inherent low processing performance. In general, the embedded system needs system-dependent algorithm because it has lower processing performance than the computer. In this paper, the location of object is estimated from the information of object's motion obtained by applying a background subtraction method which compares the previous frames with the current ones. The real-time detection performance of the proposed method for object detection is verified experimentally on embedded board by comparing the proposed algorithm with the object detection based on LKOF (Lucas-Kanade optical flow).

터널 건설 예정지구에서의 전기비저항 탐사와 전자탐사의 적용을 통한 연약대 탐지에 대한 사례 연구 (A case histories on the detection of weak zone using electrical resistivity and EM surveys in planned tunnel construction site)

  • 권형석;송윤호;이명종;정호준;오세영;김기석
    • 한국지반공학회:학술대회논문집
    • /
    • 한국지반공학회 2002년도 봄 학술발표회 논문집
    • /
    • pp.63-70
    • /
    • 2002
  • In tunnel construction, the information on the rock quality and the location of fault or fracture are crucial for economical design of support pattern and for safe construction of the tunnel. The grade of rock is commonly estimated through the observation with the naked eye of recovered cores in drilling or from physical parameters obtained by their laboratory test. Since drilling cost is quite expensive and terrains of planned sites for tunnel construction are rough in many cases, however, only limited information could be provided by core drilling Electrical resistivity and EM surveys may be a clue to get over this difficulty. Thus we have investigated electrical resistivity and EM field data providing regional Information of the rock Quality and delineating fault and fracture over a rough terrain. In this paper, we present some case histories using electrical resistivity and EM survey for the site investigation of tunnel construction. Through electrical resistivity and EM survey, the range and depth of coal seam was clearly estimated, cavities were detected in limestone area, and weak zones such as joint, fault and fracture have been delineated.

  • PDF

인공지능 피난유도설비 적용에 따른 최적 대피시뮬레이션 연구 (A Study for Optimal Evacuation Simulation by Artificial Intelligence Evacuation Guidance Application)

  • 장재순;공일천;이동호
    • 한국안전학회지
    • /
    • 제28권3호
    • /
    • pp.118-122
    • /
    • 2013
  • For safe evacuation in the fire disaster, the evacuees must find the exit and evacuate quickly. Especially, if the evacuees don't know the location of the exit, they have to depend on the evacuation guidance system. Because the more smoke spread, the less visibility is decreasing, it is difficult to find the way to the exit by the naked eye. For theses reasons, the evacuation guidance system is highly important. However, the evacuation guidance system without change of direction has the risk that introduce to the dangerous area. In the evacuation safety assessment scenario by the evacuation simulation has the same problem. Because the evacuee in the simulation evacuate by the shortest route to the exit, the simulation result is same like the evacuation without the evacuation guidance system. In this study, it was used with MAS (Multi Agent System)-based simulation program including the evacuation guidance system to implement the change of evacuation by fire. Using this method, confidence of evacuation safety assessment can be increase.

스테레오 영상을 이용한 얼굴 포즈 추정 (Face Pose Estimation using Stereo Image)

  • 소인미;강선경;김영운;이지근;정성태
    • 한국컴퓨터정보학회논문지
    • /
    • 제11권3호
    • /
    • pp.151-159
    • /
    • 2006
  • 본 논문에서는 두 대의 카메라 영상으로부터 얼굴의 포즈를 추정하는 방법을 제안한다. 제안된 방법은 먼저 두 얼굴 영상으로부터 대응되는 눈썹, 눈, 입의 특징점을 추출한 다음, 스테레오 비전의 삼각법에 의해 특징점에 대한 3차원 위치를 계산한다. 그 다음에는 특징점으로 부터 삼각형을 생성하고 그 삼각형에 수직 방향을 계산함으로써 얼굴의 포즈를 계산한다. 계산된 얼굴의 포즈를 3D 얼굴 모델에 적용해 본 결과 본 논문에서 제안된 방법이 정확한 얼굴 포즈를 추정할 수 있음을 알 수 있었다.

  • PDF

레이더 자료를 이용한 기하학적 태풍중심 탐지 기법 개선 (Improvement of a Detecting Algorithm for Geometric Center of Typhoon using Weather Radar Data)

  • 정우미;석미경;최윤;김광호
    • 대기
    • /
    • 제30권4호
    • /
    • pp.347-360
    • /
    • 2020
  • The automatic algorithm optimized for the Korean Peninsula was developed to detect and track the center of typhoon based on a geometrical method using high-resolution retrieved WISSDOM (WInd Syntheses System using DOppler Measurements) wind and reflectivity data. This algorithm analyzes the center of typhoon by detecting the geometric circular structure of the typhoon's eye in radar reflectivity and vorticity 2D field data. For optimizing the algorithm, the main factors of the algorithm were selected and the optimal thresholds were determined through sensitivity experiments for each factor. The center of typhoon was detected for 5 typhoon cases that approached or landed on Korean Peninsula. The performance was verified by comparing and analyzing from the best track of Korea Meteorological Administration (KMA). The detection rate for vorticity use was 15% higher on average than that for reflectivity use. The detection rate for vorticity use was up to 90% for DIANMU case in 2010. The difference between the detected locations and best tracks of KMA was 0.2° on average when using reflectivity and vorticity. After the optimization, the detection rate was improved overall, especially the detection rate more increased when using reflectivity than using vorticity. And the difference of location was reduced to 0.18° on average, increasing the accuracy.

Development of a Non-contact Input System Based on User's Gaze-Tracking and Analysis of Input Factors

  • Jiyoung LIM;Seonjae LEE;Junbeom KIM;Yunseo KIM;Hae-Duck Joshua JEONG
    • 한국인공지능학회지
    • /
    • 제11권1호
    • /
    • pp.9-15
    • /
    • 2023
  • As mobile devices such as smartphones, tablets, and kiosks become increasingly prevalent, there is growing interest in developing alternative input systems in addition to traditional tools such as keyboards and mouses. Many people use their own bodies as a pointer to enter simple information on a mobile device. However, methods using the body have limitations due to psychological factors that make the contact method unstable, especially during a pandemic, and the risk of shoulder surfing attacks. To overcome these limitations, we propose a simple information input system that utilizes gaze-tracking technology to input passwords and control web surfing using only non-contact gaze. Our proposed system is designed to recognize information input when the user stares at a specific location on the screen in real-time, using intelligent gaze-tracking technology. We present an analysis of the relationship between the gaze input box, gaze time, and average input time, and report experimental results on the effects of varying the size of the gaze input box and gaze time required to achieve 100% accuracy in inputting information. Through this paper, we demonstrate the effectiveness of our system in mitigating the challenges of contact-based input methods, and providing a non-contact alternative that is both secure and convenient.

머신비전 기반의 가전제품 표면결함 자동검출 시스템 (Automatic detection system for surface defects of home appliances based on machine vision)

  • 이현준;정희자;이장군;김남호
    • 스마트미디어저널
    • /
    • 제11권9호
    • /
    • pp.47-55
    • /
    • 2022
  • 스마트팩토리 제조공정에서의 품질관리는 중요한 요소이다. 현재, 금형 공정으로 생산되는 생활가전 제조부품의 품질검사는 대부분 작업자의 육안으로 진행되고 있으며 이로 인한 검사의 오류율이 높은 실정이다. 이러한 품질공전 개선을 위하여 결함 자동검출 시스템을 설계하여 구현하였다. 제안 시스템은 특정 위치에서 고성능 스캔 카메라로 대상물을 촬영하여 영상을 획득하고, 비전검사 알고리즘에 따라 긁힘, 찍힘, 이물질에 의한 불량품을 판독한다. 본 연구에서는 긁힘에 대한 불량 인식율을 높이기 위하여 깊이 정보 기반 분기 판단 알고리즘(Depth-based branch decision algorithm, DBD)을 개발하여 정확도를 높였다.