• 제목/요약/키워드: Moving Joint

검색결과 241건 처리시간 0.025초

Automated Markerless Analysis of Human Gait Motion for Recognition and Classification

  • Yoo, Jang-Hee;Nixon, Mark S.
    • ETRI Journal
    • /
    • 제33권2호
    • /
    • pp.259-266
    • /
    • 2011
  • We present a new method for an automated markerless system to describe, analyze, and classify human gait motion. The automated system consists of three stages: I) detection and extraction of the moving human body and its contour from image sequences, ii) extraction of gait figures by the joint angles and body points, and iii) analysis of motion parameters and feature extraction for classifying human gait. A sequential set of 2D stick figures is used to represent the human gait motion, and the features based on motion parameters are determined from the sequence of extracted gait figures. Then, a k-nearest neighbor classifier is used to classify the gait patterns. In experiments, this provides an alternative estimate of biomechanical parameters on a large population of subjects, suggesting that the estimate of variance by marker-based techniques appeared generous. This is a very effective and well-defined representation method for analyzing the gait motion. As such, the markerless approach confirms uniqueness of the gait as earlier studies and encourages further development along these lines.

HEVC 기반 스케일러블 비디오 부호화의 개요 및 성능 분석 (Overview and Performance analysis of the HEVC based Scalable Video Coding)

  • 최진혁;최해철
    • 한국방송∙미디어공학회:학술대회논문집
    • /
    • 한국방송공학회 2013년도 추계학술대회
    • /
    • pp.190-192
    • /
    • 2013
  • 최근 HD(High Definition)화질 및 UHD(Ultra High Definition)화질과 같은 고품질 방송 서비스가 등장하고, 무선 네트워크 기술의 발달로 스마트폰, 태블릿PC 등과 같은 다양한 휴대용 멀티미디어 기기들이 존재함에 따라, 소비자들은 다양한 환경에서 고해상도 영상을 고품질로 사용하기를 원하고 있다. 따라서 스케일러빌러티의 현실적 필요성이 점점 대두되고 있으며, 이에 따라 ISO/IEC의 MPEG(Moving Picture Experts Group)와 ITU-T의 VCEG(Video Coding Experts Group)이 공동으로 결성한 Joint Collaborative Team on Video Coding(JCT-VC)에 의해 시간, 공간, 화질 등이 확장성을 제공하는 Scalable Video Coding(SVC)의 표준화가 진행되고 있다. 이에 본 논문은 공간적, 시간적, 화질적 스케일러빌러티(Scalability)를 제공하기 위한 SHVC의 표준 기술들에 대해 설명하고, 기존 단일 계층 부호화 방식(Single Video Coding)으로 서로 다른 해상도의영상을 Simulcast부호화한 결과와 비교하여 SHVC의 부호화한 결과와 비교하여 SHVC의 보호화 효율에 대한 성능을 분석 하였다.

  • PDF

International Collaboration in Library and Information Science Research in Korea

  • Noh, Younghee;Chang, Rosa
    • International Journal of Knowledge Content Development & Technology
    • /
    • 제9권2호
    • /
    • pp.91-110
    • /
    • 2019
  • This study sought to examine five theses from major journals concerning Korea's Library and Information Science, published from 1970 to 2018, so as to diagnose the current stage of International Research collaboration in the field of Korea's Library and Information Science which researchers from two or more different nations jointly conducted. Furthermore, it proposed measures for activating International Research collaboration in the field of Korea's Library and Information Science. First, related conferences should be held and education need to be offered in terms of elevating the awareness of the need and importance of international research collaboration. Second, relevant policies need to be developed and projects should be implemented to strengthen the practical international research collaboration. Third, collaboration with various countries should be pursued in the area of detailed majors of library and information science of greater diversity than now in terms of the detailed majors and countries. Fourth, a research environment supporting the collaboration with various research institutions overseas moving forward will need to be created around the universities.

힘/모멘트 측정기능을 갖는 6축 로봇 베이스 플랫폼 개발 (Development of a 6-axis Robotic Base Platform with Force/Moment Sensing)

  • 정성훈;김한성
    • 한국산업융합학회 논문집
    • /
    • 제22권3호
    • /
    • pp.315-324
    • /
    • 2019
  • This paper present a novel 6-axis robotic base platform with force/moment sensing. The robotic base platform is made up of six loadcells connecting the moving plate to the fixed plate by spherical joints at the both ends of loadcells. The statics relation is derived, the robotic base platform prototype and the loadcell measurement system are developed. The force/moment calibrations in joint and Cartesian spaces are performed. The algorithm to detect external force applied at a working robot is derived, and using a 6-DOF robot mounted on the robotic base platform, force/moment measurement experiments have been performed.

360 VR 영상의 프로젝션 포맷 및 성능 평가 방식 (Projection format and quality metrics of 360 video)

  • 박성환;김규헌
    • 한국방송∙미디어공학회:학술대회논문집
    • /
    • 한국방송∙미디어공학회 2019년도 하계학술대회
    • /
    • pp.182-184
    • /
    • 2019
  • 최근 사용자에게 더욱 몰입감 있는 콘텐츠를 제공하기 위한 기술에 대한 관심이 증가하고 있으며 그 중 가장 대표적인 것이 360 VR 영상이라고 할 수 있다. 미디어 표준화 단체인 MPEG(Moving Picture Experts Group)에서는 MPEG-I(Immersive) 차세대 프로젝트 그룹을 이용하여 이러한 움직임에 대응하고 있다. MPEG-I는 2021년 말 6DoF VR 영상을 목표로 8개의 파트가 표준화를 진행중이다. 360 VR 영상의 경우 획득시 영상의 픽셀들이 3D 공간 상에 존재하게 되는데, 이를 처리 및 출력 하귀 위해서는 2D 영상으로 전환이 필요하며 이 때 사용되는 것이 Projection format이다. 현재 JVET(Joint Video Exploration Team)에서는 3D에서 2D로 전환이 이루어 질 때 손실을 최소화 하기 위한 Projection format들에 대한 연구가 이루어 지고 있다. 본 논문에서는 현재까지 제안된 다양한 Projection format들에 대하여 소개하고 이에 대한 성능 측정 방식에 대하여 소개한다.

  • PDF

다목적 비디오 부/복호화를 위한 다층 퍼셉트론 기반 삼항 트리 분할 결정 방법 (Multi-Layer Perceptron Based Ternary Tree Partitioning Decision Method for Versatile Video Coding)

  • 이태식;전동산
    • 한국멀티미디어학회논문지
    • /
    • 제25권6호
    • /
    • pp.783-792
    • /
    • 2022
  • Versatile Video Coding (VVC) is the latest video coding standard, which had been developed by the Joint Video Experts Team (JVET) of ITU-T Video Coding Experts Group (VCEG) and ISO/IEC Moving Picture Experts Group (MPEG) in 2020. Although VVC can provide powerful coding performance, it requires tremendous computational complexity to determine the optimal block structures during the encoding process. In this paper, we propose a fast ternary tree decision method using two neural networks with 7 nodes as input vector based on the multi-layer perceptron structure, names STH-NN and STV-NN. As a training result of neural network, the STH-NN and STV-NN achieved accuracies of 85% and 91%, respectively. Experimental results show that the proposed method reduces the encoding complexity up to 25% with unnoticeable coding loss compared to the VVC test model (VTM).

소형 초전도 부상자석의 특성 연구 (Study on the Characteristics of a Small Scale HTSC Levitation Magnet)

  • 조흥제;배덕권;이종민;고태국
    • 한국초전도ㆍ저온공학회논문지
    • /
    • 제9권1호
    • /
    • pp.76-81
    • /
    • 2007
  • This paper deals with the characteristics of a small scale $high-T_c$ superconducting(HTSC) levitation system. The levitation tester. which models after electrodynamic suspension(EDS) maglev, consists of one HTSC magnet, a reaction plate, and force measuring components. Instead of moving magnet, AC current was applied to the fixed HTSC magnet. The magnet also has persistent current switch(PCS). The inductance of the magnet was 18.5 mH and total joint resistance of the magnet was $5.74{\times}10^{-7}\Omega$. AC current was applied into the HTSC magnet with various frequencies and the levitation force was calculated and measured. According to the increase of the vehicle speed, the levitation force was saturated.

VVC 행렬가중 화면내 예측(MIP) 학습기법 분석 (Analysis of Training Method for Matrix Weighted Intra Prediction (MIP) in VVC)

  • 박도현;권형진;정세윤;김재곤
    • 한국방송∙미디어공학회:학술대회논문집
    • /
    • 한국방송∙미디어공학회 2020년도 추계학술대회
    • /
    • pp.148-150
    • /
    • 2020
  • 최근 VVC(Versatile Video Coding) 표준 완료 이후 JVET(Joint Video Experts Team)은 인공신경망 기반의 비디오 부호화를 위한 AhG(Ad-hoc Group) 구성하고 인공지능을 이용한 비디오 압축 기술들을 검증하고 있으며, MPEG(Moving Picture Experts Group)에서는 DNNVC(Deep Neural Network based Video Coding) 활동을 통해 딥러닝 기반의 차세대 비디오 부호화 표준 기술을 탐색하고 있다. 본 논문은 VVC 에 채택된 신경망 기반의 기술인 MIP(Matrix Weighted Intra Prediction)를 참조하여, MIP 모델의 학습에서 손실함수가 예측 성능에 미치는 영향을 분석한다. 즉, 예측의 왜곡(MSE)만을 고려한 경우와 예측오차의 부호화 비용도 함께 반영한 손실함수를 비교한다. 실험을 위해 HEVC(High Efficiency Video Coding) 화면내 예측 대비 평균적인 PSNR 향상 정도를 나타내는 성능 지표(��PSNR)를 정의한다. 실험결과 예측오차의 부호화 특성을 반영하는 손실함수를 이용한 학습이 MSE 만 고려한 학습 대비 ��PSNR 기준 평균 0.4dB 향상됨을 보였다.

  • PDF

경호원의 삼단봉 머리치기 동작의 운동학적 분석 (Kinemetic analysis of a thumping security motion with an expandable barton)

  • 김용학;김신혜;정성배
    • 시큐리티연구
    • /
    • 제36호
    • /
    • pp.93-109
    • /
    • 2013
  • 본 연구에서는 경호, 경비현장에서 이루어지는 대치상황에서 경호, 경비원의 장비 중 삼단봉을 선택하여 머리치기 동작의 운동학적 분석을 실시하였다. H대학교 경호학과 학생 출신10명을 대상으로 연구를 실시하였다. 숙련자 그룹에서 삼단봉 교육 프로그램 실시하였고, 숙련자그룹과 비숙련자 그룹으로 연구 하였다. 구간별 소요시간은 숙련자 (e2) 0.428sec 비숙련자 0.435 sec, (e3) 에서는 숙련지 0.230 sec 비숙련자 0.232 sec 소요되었으며, 비숙련자 그룹에서 소요시간이 많이 소요된 것으로 나타났다. 신체중심 이동 변위는 좌, 우 숙련자$2.16{\pm}0.95cm$, $3.78{\pm}1.42cm$, 전체적으로 $5.94{\pm}2.03cm$ 변화를 보였다. 비숙련자 $2.97{\pm}1.01cm$, $4.56{\pm}1.57cm$, 전체적으로 $7.53{\pm}2.13cm$ 변화를 보였고, 전, 후 이동에서는 숙련자$32.48{\pm}3.86cm$, $35.21{\pm}4.64cm$, 전체적으로 $69.36{\pm}5.72cm$ 변화를 보였다. 비숙련자 $34.50{\pm}6.12cm$, $37.04{\pm}3.70cm$, 전체적으로 $71.46{\pm}7.17cm$ 변화를 보였다. 그리고 상, 하 이동변위에서는 숙련자 $5.62{\pm}2.49cm$, $4.54{\pm}1.87cm$, 전체적으로 $10.11{\pm}1.57cm$ 변화를 보였다. 비숙련자 $6.33{\pm}1.78cm$, $4.86{\pm}1.85cm$, 전체적으로 $10.68{\pm}1.81cm$ 변화를 보였다. 손목관절의 각도 변화에서 손목각도이며, 숙련자e1, $114.62{\pm}7.13$, e2 $68.27{\pm}6.37$, e3 $131.64{\pm}6.27$, 비숙련자 e1, $112.62{\pm}6.13$, e2 $66.28{\pm}7.38$, e3 $137.42{\pm}4.28$ 팔꿉치 관절의 각도 변화이며, 숙련자 e1, $132.31{\pm}6.55$, e2 $117.92{\pm}8.42$, e3 $144.41{\pm}6.32$, 비숙련자 e1, $133.58{\pm}8.56$, e2 $114.45{\pm}8.21$, e3 $139.89{\pm}4.38$ 어깨관절의 각도 변화이며, 숙련자 e1, $13.55{\pm}3.85$, e2 $131.42{\pm}11.24$, e3 $78.32{\pm}6.28$, 비숙련자 e1, $9.45{\pm}1.23$, e2 $136.74{\pm}13.21$, e3 $79.75{\pm}4.24$, 각 변화를 보였다.

  • PDF

Kinematic and Dynamic Analyses of Human Arm Motion

  • Kim, Junghee;Cho, Sungho;Lee, Choongho;Han, Jaewoong;Hwang, Heon
    • Journal of Biosystems Engineering
    • /
    • 제38권2호
    • /
    • pp.138-148
    • /
    • 2013
  • Purpose: Determining an appropriate path is a top priority in order for a robot to maneuver in a dynamically efficient way especially in a pick-and-place task. In a non-standardized work environment, current robot arm executes its motion based on the kinematic displacements of joint variables, though resulting motion is not dynamically optimal. In this research we suggest analyzing and applying motion patterns of the human arm as an alternative to perform near optimum motion trajectory for arbitrary pick-and-place tasks. Methods: Since the motion of a human arm is very complicated and diverse, it was simplified into two links: one from the shoulder to the elbow, and the other from the elbow to the hand. Motion patterns were then divided into horizontal and vertical components and further analyzed using kinematic and dynamic methods. The kinematic analysis was performed based on the D-H parameters and the dynamic analysis was carried out to calculate various parameters such as velocity, acceleration, torque, and energy using the Newton-Euler equation of motion and Lagrange's equation. In an attempt to assess the efficacy of the analyzed human motion pattern it was compared to the virtual motion pattern created by the joint interpolation method. Results: To demonstrate the efficacy of the human arm motion mechanical and dynamical analyses were performed, followed by the comparison with the virtual robot motion path that was created by the joint interpolation method. Consequently, the human arm was observed to be in motion while the elbow was bent. In return this contributed to the increase of the manipulability and decrease of gravity and torque being exerted on the elbow. In addition, the energy required for the motion decreased. Such phenomenon was more apparent under vertical motion than horizontal motion patterns, and in shorter paths than in longer ones. Thus, one can minimize the abrasion of joints by lowering the stress applied to the bones, muscles, and joints. From the perspectives of energy and durability, the robot arm will be able to utilize its motor most effectively by adopting the motion pattern of human arm. Conclusions: By applying the motion pattern of human arm to the robot arm motion, increase in efficiency and durability is expected, which will eventually produce robots capable of moving in an energy-efficient manner.