• Title/Summary/Keyword: Posture Tracking

Search Result 63, Processing Time 0.025 seconds

Swimming Behavior Study of the Zooplankton(Copepod Calanus sinicus) by Using a Holographic Particle Tracking Velocimetry Technique (Digital Holographic Particle Tracking Velocimetry 기법을 사용한 동물성 플랑크톤(요각류 Calanus sinicus)의 헤엄침 양태 연구)

  • Sohn, Myong-Hwan;Park, Byung-Hwa;Choi, Yong-Seok;Lee, Sang-Joon;Kang, Young-Sil;Kang, Yang-Soon
    • Journal of the Korea Institute of Military Science and Technology
    • /
    • v.13 no.5
    • /
    • pp.941-949
    • /
    • 2010
  • The present study investigated the swimming pattern and appendage postures of a copepod species, Calanus sinicus, which prevails in the south-east sea of the Korean peninsula, by employing a digital holographic particle tracking velocimetry(PTV) technique. The results showed that the copepod Calanus sinicus had various swimming patterns such as hover, hop, sink, cruise, and downward cruise. Most frequent pattern was the 'hop and sink'. The average swimming speeds ranged from 1.1 to 45.7 body-lengths/s, and the corresponding flow Reynolds number ranged from $10^0$ to $10^2$.

Unified Detection and Tracking of Humans Using Gaussian Particle Swarm Optimization (가우시안 입자 군집 최적화를 이용한 사람의 통합된 검출 및 추적)

  • An, Sung-Tae;Kim, Jeong-Jung;Lee, Ju-Jang
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.18 no.4
    • /
    • pp.353-358
    • /
    • 2012
  • Human detection is a challenging task in many fields because it is difficult to detect humans due to their variable appearance and posture. Furthermore, it is also hard to track the detected human because of their dynamic and unpredictable behavior. The evaluation speed of method is also important as well as its accuracy. In this paper, we propose unified detection and tracking method for humans using Gaussian-PSO (Gaussian Particle Swarm Optimization) with the HOG (Histograms of Oriented Gradients) features to achieve a fast and accurate performance. Keeping the robustness of HOG features on human detection, we raise the process speed in detection and tracking so that it can be used for real-time applications. These advantages are given by a simple process which needs just one linear-SVM classifier with HOG features and Gaussian-PSO procedure for the both of detection and tracking.

Improvement of Plane Tracking Accuracy in AR Game Using Magnetic Field Sensor (자기장 센서를 사용한 AR 게임에서의 평면 추적 정확도 개선)

  • Lee, Won-Jun;Park, Jong-Seung
    • Journal of Korea Game Society
    • /
    • v.19 no.5
    • /
    • pp.91-102
    • /
    • 2019
  • In this paper, we propose an improved method of plane tracking in developing AR games for smartphones using magnetic field sensor. The previous method based on ARCore is a VIO method using a mixture of SLAM and IMU of smartphones. The disadvantages of accelerometers and gyroscopes in IMUs cause errors in tracking the plane. We propose an improved method of planar tracking by adding the magnetic field sensor as well as the existing IMU sensors. Experimental results shows that our method reduces the error of the smartphone posture estimation.

A Movement Tracking Model for Non-Face-to-Face Excercise Contents (비대면 운동 콘텐츠를 위한 움직임 추적 모델)

  • Chung, Daniel;Cho, Mingu;Ko, Ilju
    • KIPS Transactions on Computer and Communication Systems
    • /
    • v.10 no.6
    • /
    • pp.181-190
    • /
    • 2021
  • Sports activities conducted by multiple people are difficult to proceed in a situation where a widespread epidemic such as COVID-19 is spreading, and this causes a lack of physical activity in modern people. This problem can be overcome by using online exercise contents, but it is difficult to check detailed postures such as during face-to-face exercise. In this study, we present a model that detects posture and tracks movement using IT system for better non-face-to-face exercise content management. The proposed motion tracking model defines a body model with reference to motion analysis methods widely used in physical education and defines posture and movement accordingly. Using the proposed model, it is possible to recognize and analyze movements used in exercise, know the number of specific movements in the exercise program, and detect whether or not the exercise program is performed. In order to verify the validity of the proposed model, we implemented motion tracking and exercise program tracking programs using Azure Kinect DK, a markerless motion capture device. If the proposed motion tracking model is improved and the performance of the motion capture system is improved, more detailed motion analysis is possible and the number of types of motions can be increased.

Implementation of the Posture Stability Monitoring System using Balance Ability Method (균형능력 측정 기법을 이용한 자세안정도 모니터링 시스템 구현)

  • Cha, Sang-Hoon;Choi, Su-Bin;Park, Eun-Ji;Park, Jun-mo;Jeong, Do-Un
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2016.05a
    • /
    • pp.537-538
    • /
    • 2016
  • Recently, modern people a lot of frequency of work and seat life by academic is increased, addictive spine for the wrong attitude and the wrong habits are many pelvic disease occurrence. Therefore, in order to induce continuous correct posture to prevent this, the system that can be induced to determine the posture information based on the seating information is requested. In this paper, when the development and inappropriate attitude of the device that is capable of tracking measurement in order to evaluate the attitude stability is detected, let your users know, to correct their attitude through the real-time monitoring It was implemented of categorize to help application.

  • PDF

Assessment of discomfort in elbow motion from driver posture (운전자 자세에 따른 팔꿈치 동작의 불편도 평가)

  • Tak, Tae-Oh;Lee, Pyoung-Rim
    • Journal of Industrial Technology
    • /
    • v.21 no.B
    • /
    • pp.265-272
    • /
    • 2001
  • The human arm is modeled by three rigid bodies(the upper arm, the forearm and the hand)with seven degree of freedom(three in the shoulder, two in the elbow and two in the wrist). The objective of this work is to present a method to determine the three-dimensional kinematics of the human elbow joint using a magnetic tracking device. Euler angle were used to determine the elbow flexion-extension, and the pronation-supination. The elbow motion for the various driving conditions is measured through the driving test using a simulator. Discomfort levels of elbow joint motions were obtained as discomfort functions, which were based on subjects' perceived discomfort level estimated by magnitude estimation. The results showed that the discomfort posture of elbow joint motions occurred in the driving motion.

  • PDF

The Posture Control of One-wheel Unicyle Robot Using Partial Feedback Linearization (부분 피드백 선형화를 이용한 One-wheel Unicycle Robot의 자세 제어)

  • Kim, Jin-Seok;Cho, Young-Jin;Kim, Young-Tark
    • Journal of the Korean Society for Precision Engineering
    • /
    • v.24 no.4 s.193
    • /
    • pp.68-75
    • /
    • 2007
  • In this study, the ultimate goal is to acquire stability when turning around efficiently by using the controller which is applied partial feedback linearization of One-wheel Unicycle Robot. When moving around, linear controller could result in unstable factor according to widening operation range. So in order to reduce instability, 1 have developed Non-linear Controller using Partial Feedback Linearization. Compared with linear controller, Non-linear Controller guarantees the superiority of Regulating Control and Tracking Control in direct and also revolution motion of Robot. I'm sure of the Non-linear controller performance through many experiments.

A Fuzzy PID Control of Nonholonomic Mobile Robot (Nonholonomic 모바일 로봇의 퍼지 PID제어)

  • Kim, Do-Won;Yang, Hai-Won;Jung, Won-Chul;Hwang, Yong-Ho;Kim, Hong-Phil
    • Proceedings of the KIEE Conference
    • /
    • 2000.07d
    • /
    • pp.2756-2759
    • /
    • 2000
  • In this paper. A PID motion controller based on the fuzzy concept is discussed for nonholonomic mobile robot. The difficulties in controlling such a Mobile robot vehicle lies in the fact that it usually has only two degrees of freedom for motion control in a tracking mode. It makes the control of speed and steering possible to decompose the error between the reference posture and the current posture. The Gyro compass is used to measure the position of robot. The proposed nonholonomic mobile robot is shown to follow the reference trajectory and compensate the dynamics. Simulation results are provided to validate the proposed controller. Experiments have been used to verify the effectiveness and robustness of the motion controller.

  • PDF

Trajectory Tracking Performance Analysis of Underwater Manipulator for Autonomous Manipulation

  • Chae, Junbo;Yeu, Taekyeong;Lee, Yeongjun;Lee, Yoongeon;Yoon, Suk-Min
    • Journal of Ocean Engineering and Technology
    • /
    • v.34 no.3
    • /
    • pp.180-193
    • /
    • 2020
  • In this study, the end-effector tracking performance of a manipulator installed on a remotely operated vehicle (ROV) for autonomous underwater intervention is verified. The underwater manipulator is an ARM 7E MINI model produced by the ECA group, which consists of six joints and one gripper. Of the six joints of the manipulator, two are revolute joints and the other four are prismatic joints. Velocity control is used to control the manipulator with forward and inverse kinematics. When the manipulator approaches a target object, it is difficult for the ROV to maintain its position and posture, owing to various disturbances, such as the variation in both the center of mass and the reaction force resulting from the manipulator motion. Therefore, it is necessary to compensate for the influences and ensure the relative distance to the object. Simulations and experiments are performed to track the trajectory of a virtual object, and the tracking performance is verified from the results.

Double Sliding Surfaces based on a Sliding Mode Control for a Tracking Control of Mobile Robots (이동 로봇의 추종 제어를 위한 이중 슬라이딩 표면에 기반한 슬라이딩 모드 제어)

  • Lee, Jun Ku;Choi, Yoon Ho;Park, Jin Bae
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.19 no.6
    • /
    • pp.495-500
    • /
    • 2013
  • This paper proposes a double sliding surfaces based on a sliding mode control for a tracking control of nonholonomic mobile robots in the Cartesian coordinates. In order to remove sliding surface constraints, we design the additional sliding surface for the heading angle with respect to the newly defined coordinates. Then, we define the switching law based on the posture error to combine the designed sliding surface with the previous one. By using the double sliding surfaces and the switching law, we obtain the control law for arbitrary trajectories. It is proved that the position tracking error and the heading direction error asymptotically converge to zero, respectively, with the Lyapunov stability theory. Finally, through computer simulations, we demonstrate the effectiveness of the proposed control system.