• Title/Summary/Keyword: pose estimation

검색결과 388건 처리시간 0.026초

A Model-based 3-D Pose Estimation Method from Line Correspondences of Polyhedral Objects

  • Kang, Dong-Joong;Ha, Jong-Eun
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 2003년도 ICCAS
    • /
    • pp.762-766
    • /
    • 2003
  • In this paper, we present a new approach to solve the problem of estimating the camera 3-D location and orientation from a matched set of 3-D model and 2-D image features. An iterative least-square method is used to solve both rotation and translation simultaneously. Because conventional methods that solved for rotation first and then translation do not provide good solutions, we derive an error equation using roll-pitch-yaw angle to present the rotation matrix. To minimize the error equation, Levenberg-Marquardt algorithm is introduced with uniform sampling strategy of rotation space to avoid stuck in local minimum. Experimental results using real images are presented.

  • PDF

HSFE Network and Fusion Model based Dynamic Hand Gesture Recognition

  • Tai, Do Nhu;Na, In Seop;Kim, Soo Hyung
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제14권9호
    • /
    • pp.3924-3940
    • /
    • 2020
  • Dynamic hand gesture recognition(d-HGR) plays an important role in human-computer interaction(HCI) system. With the growth of hand-pose estimation as well as 3D depth sensors, depth, and the hand-skeleton dataset is proposed to bring much research in depth and 3D hand skeleton approaches. However, it is still a challenging problem due to the low resolution, higher complexity, and self-occlusion. In this paper, we propose a hand-shape feature extraction(HSFE) network to produce robust hand-shapes. We build a hand-shape model, and hand-skeleton based on LSTM to exploit the temporal information from hand-shape and motion changes. Fusion between two models brings the best accuracy in dynamic hand gesture (DHG) dataset.

반타원 표면균열 선단을 따른 참조응력 기반의 J-적분 예측 (Reference Stress Based J-Integral Estimates Along the Semi-Elliptical Surface Crack Front)

  • 김진수;심도준;김윤재;김영진
    • 대한기계학회논문집A
    • /
    • 제28권6호
    • /
    • pp.701-708
    • /
    • 2004
  • This paper discusses applicability of the enhanced reference stress method to estimate J-integral along the semi-elliptical surface crack front. It is found that angular variations of normalized J­integral are strongly dependent on the geometry, loading mode and loading magnitude. As application of the reference stress approach to semi-elliptical surface cracks implies proportional increases in the normalized J-integral, the present results pose a question in applicability of the reference stress approach. However, investigation of the error in the estimated J-integral in the present work suggests that the enhanced reference stress approach, recently proposed by authors, provides an effective engineering tool fur estimating crack driving force along the semi-elliptical surface crack front.

가상 페트와의 자연스러운 상호작용을 위한 손바닥 포즈 계산 및 손가락 움직임 추적 (Palm Pose Estimation and Finger Motion Tracking for Natural Interaction with Virtual Pet)

  • 최준영;한재혁;서병국;박한훈;박종일
    • 한국방송∙미디어공학회:학술대회논문집
    • /
    • 한국방송공학회 2008년도 추계학술대회
    • /
    • pp.243-246
    • /
    • 2008
  • 본 논문은 손을 이용하여 가상 객체와 상호작용이 가능한 모바일 증강현실 기술을 소개한다. 제안된 방법은 마커나 센서 없이 손바닥의 특징점만을 이용하여 손바닥 포즈(위치와 방향)를 계산하고, 손바닥 위에 가상 객체를 생성한다. 또한, 손가락 움직임을 추적하여 가상 객체와 자연스러운 상호작용을 가능하게 한다. 본 논문에서는 Ultra-Mobile PC (UMPC)를 이용하여 제안된 방법을 구현하고, 그 유용성을 검증한다.

  • PDF

자율 주행 로봇의 확률론적 자기 위치 추정기법을 위해 거리 센서를 이용한 센서 모델 설계 (Sensor Model Design of Range Sensor Based Probabilistic Localization for the Autonomous Mobile Robot)

  • 김경록;정우진;김문상
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
    • /
    • pp.27-29
    • /
    • 2004
  • This paper presents a sensor model design based on Monte Carlo Localization method. First, we define the measurement error of each sample using a map matching method by 2-D laser scanners and a pre-constructed grid-map of the environment. Second, samples are assigned probabilities due to matching errors from the gaussian probability density function considered of the sample's convergence. Simulation using real environment data shows good localization results by the designed sensor model.

  • PDF

지능형 로봇 시스템에서 하이브리드 실루엣 추출 방법을 이용한 인간의 몸 추출 (Extraction of Human Body Using Hybrid Silhouette Extraction Method in Intelligent Robot System)

  • 김문환;주영훈;박진배;조영조;지수영;김혜진
    • 한국지능시스템학회:학술대회논문집
    • /
    • 한국퍼지및지능시스템학회 2005년도 추계학술대회 학술발표 논문집 제15권 제2호
    • /
    • pp.257-260
    • /
    • 2005
  • This paper discusses a human body extraction method for mobile robot system. The skeleton features are used to analyze human motion and pose estimation. The intelligent robot system requires more robust silhouette extraction method because it has internal vibration and low resolution. The new hybrid silhouette extraction method is proposed to overcome this constrained environment. Finally, the experimental results show the superiority of the Proposed method.

  • PDF

배출가스 부과금에 따른 항공사 네트워크의 변화에 관한 연구 (A Study on Airlines Network Changes by Emission Charges)

  • 김백재;최진영
    • 한국항공운항학회지
    • /
    • 제25권4호
    • /
    • pp.178-186
    • /
    • 2017
  • Air travel has become an essential part of the global society and its sustainable development is expected. Airlines profit structure and network operation will be influenced by internalization of external costs like emission charge. This additional cost of the airlines will be directly pose air ticket fare increase and demand of air passenger will be decreased. EU-ETS is a part of environmental binding to airlines fly to EU territory airports. This study analyzes the impact of emission charges by application of EU-ETS on airlines network change. For long-term forecast, a reliable estimation of the future price of carbon dioxide (CO2) will be used.

유비쿼터스 로봇과 휴먼 인터액션을 위한 제스쳐 추출 (Gesture Extraction for Ubiquitous Robot-Human Interaction)

  • 김문환;주영훈;박진배
    • 제어로봇시스템학회논문지
    • /
    • 제11권12호
    • /
    • pp.1062-1067
    • /
    • 2005
  • This paper discusses a skeleton feature extraction method for ubiquitous robot system. The skeleton features are used to analyze human motion and pose estimation. In different conventional feature extraction environment, the ubiquitous robot system requires more robust feature extraction method because it has internal vibration and low image quality. The new hybrid silhouette extraction method and adaptive skeleton model are proposed to overcome this constrained environment. The skin color is used to extract more sophisticated feature points. Finally, the experimental results show the superiority of the proposed method.

검사용 로봇을 위한 원기둥형 물체의 자세 추정 방법 (Pose Estimation of a Cylindrical Object for an Inspection Robot)

  • 정규원
    • 한국공작기계학회논문집
    • /
    • 제12권1호
    • /
    • pp.8-15
    • /
    • 2003
  • The cylindrical object such as a water pipe or an oil pipeline are widely used in the infrastructure. Those pipes should be inspected periodically by human or a robot. However, since there is no edge or vertex in the pipe, it is very difficult for the robot to navigate along the pipe. In this paper in order to guide the robot along the axis of the pipe, an algorithm which find the axis using the measured range data from the robot to the pipe wall is developed The algorithm is verified using both the simulated range data and the measured one.

강인한 SLAM을 이용한 무한궤도형 이동로봇의 모션 추정 (The Motion Estimation of Caterpilla-type Mobile Robot Using Robust SLAM)

  • 변성재;이석규;박주현
    • 전기학회논문지
    • /
    • 제58권4호
    • /
    • pp.817-823
    • /
    • 2009
  • This paper proposes a robust method for mapping of a caterpillar-type mobile robot which inherently has uncertainty in its modeling by compensating for the estimated pose error of the robot. In general, a caterpillar type robot is difficult to model, which results in inaccuracy in Simultaneous Localization And Mapping(SLAM). To enhance the robustness of the SLAM for a caterpillar-type mobile robot, we factorize the SLAM posterior, where we used particle filter to estimate the position of the robot and Extended Kalman Filter(EKF) to map the environment. The simulation results show the effectiveness and robustness of the proposed method for mapping.