• Title/Summary/Keyword: Skeleton joints

Search Result 48, Processing Time 0.024 seconds

An Accelerated IK Solver for Deformation of 3D Models with Triangular Meshes (삼각형 메쉬로 이루어진 3D 모델의 변형을 위한 IK 계산 가속화)

  • Park, Hyunah;Kang, Daeun;Kwon, Taesoo
    • Journal of the Korea Computer Graphics Society
    • /
    • v.27 no.5
    • /
    • pp.1-11
    • /
    • 2021
  • The purpose of our research is to efficiently deform a 3D models which is composed of a triangular mesh and a skeleton. We designed a novel inverse kinematics (IK) solver that calculates the updated positions of mesh vertices with fewer computing operations. Through our user interface, one or more markers are selected on the surface of the model and their target positions are set, then the system updates the positions of surface vertices to construct a deformed model. The IK solving process for updating vertex positions includes many computations for obtaining transformations of the markers, their affecting joints, and their parent joints. Many of these computations are often redundant. We precompute those redundant terms in advance so that the 3-nested loop computation structure was improved to a 2-nested loop structure, and thus the computation time for a deformation is greatly reduced. This novel IK solver can be adopted for efficient performance in various research fields, such as handling 3D models implemented by LBS method, or object tracking without any markers.

Using Maya Walking Motion Analysis in the Changing Environment of the Ground and Implement Realistic Character Animation (마야를 이용한 지형변화 환경에서의 보행동작 분석과 현실적 캐릭터 애니메이션 구현)

  • Yoon, Yeo-Geun;Song, Teuk-Seob
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2012.05a
    • /
    • pp.521-523
    • /
    • 2012
  • In the field of virtual reality and game production with realistic, real-time character's behavior is frequently used. In this paper, the terrain changes or other actions on the surrounding environment by implementing adaptive any action that is the most natural and can be adapted to analyze real-time character animation is implemented. For this purpose, in order to control the various movements of the character of the human body, by highlighting the major joints Kinematic dummy character animation is to create a way. Changes in terrain height difference of the two stairs that could cause analysis of the behavior in the environment and the other on the surrounding environment by adapting behavior to analyze the behavior of the slope climbing Based on this, the character animation is implemented.

  • PDF

Real-time Human Pose Estimation using RGB-D images and Deep Learning

  • Rim, Beanbonyka;Sung, Nak-Jun;Ma, Jun;Choi, Yoo-Joo;Hong, Min
    • Journal of Internet Computing and Services
    • /
    • v.21 no.3
    • /
    • pp.113-121
    • /
    • 2020
  • Human Pose Estimation (HPE) which localizes the human body joints becomes a high potential for high-level applications in the field of computer vision. The main challenges of HPE in real-time are occlusion, illumination change and diversity of pose appearance. The single RGB image is fed into HPE framework in order to reduce the computation cost by using depth-independent device such as a common camera, webcam, or phone cam. However, HPE based on the single RGB is not able to solve the above challenges due to inherent characteristics of color or texture. On the other hand, depth information which is fed into HPE framework and detects the human body parts in 3D coordinates can be usefully used to solve the above challenges. However, the depth information-based HPE requires the depth-dependent device which has space constraint and is cost consuming. Especially, the result of depth information-based HPE is less reliable due to the requirement of pose initialization and less stabilization of frame tracking. Therefore, this paper proposes a new method of HPE which is robust in estimating self-occlusion. There are many human parts which can be occluded by other body parts. However, this paper focuses only on head self-occlusion. The new method is a combination of the RGB image-based HPE framework and the depth information-based HPE framework. We evaluated the performance of the proposed method by COCO Object Keypoint Similarity library. By taking an advantage of RGB image-based HPE method and depth information-based HPE method, our HPE method based on RGB-D achieved the mAP of 0.903 and mAR of 0.938. It proved that our method outperforms the RGB-based HPE and the depth-based HPE.

The Implementation of Visualization Tool for Snowboard Using Kinect Sensor Data (키넥트 센서 데이터를 이용한 스노보드 동작 시각화 도구의 구현)

  • Park, Young-Nam;Seo, Se-Mi;Park, Myeong-Chul
    • Journal of the Korea Society of Computer and Information
    • /
    • v.18 no.5
    • /
    • pp.53-60
    • /
    • 2013
  • This paper proposed visualization tool for motion of snowboarding using Skeleton data obtained by the Microsoft's Kinect sensor. The BBP(Balanced Body Position) posture is a most basic motion in the Snowboarding. This posture is the primary technology for stable turns. The implementation of visualization tool to analyse the BBP posture of snowboard. comparative analysis with standard postures to the ankles, knees, hips and spine angle of joints and body tracking using coordinate information obtained by the Kinect Sensor. Analysis of the final results of the screen through the OpenGL library. This research result could be used to analysis for turn postures of snowboarding.

Design of an Arm Gesture Recognition System Using Feature Transformation and Hidden Markov Models (특징 변환과 은닉 마코프 모델을 이용한 팔 제스처 인식 시스템의 설계)

  • Heo, Se-Kyeong;Shin, Ye-Seul;Kim, Hye-Suk;Kim, In-Cheol
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.2 no.10
    • /
    • pp.723-730
    • /
    • 2013
  • This paper presents the design of an arm gesture recognition system using Kinect sensor. A variety of methods have been proposed for gesture recognition, ranging from the use of Dynamic Time Warping(DTW) to Hidden Markov Models(HMM). Our system learns a unique HMM corresponding to each arm gesture from a set of sequential skeleton data. Whenever the same gesture is performed, the trajectory of each joint captured by Kinect sensor may much differ from the previous, depending on the length and/or the orientation of the subject's arm. In order to obtain the robust performance independent of these conditions, the proposed system executes the feature transformation, in which the feature vectors of joint positions are transformed into those of angles between joints. To improve the computational efficiency for learning and using HMMs, our system also performs the k-means clustering to get one-dimensional integer sequences as inputs for discrete HMMs from high-dimensional real-number observation vectors. The dimension reduction and discretization can help our system use HMMs efficiently to recognize gestures in real-time environments. Finally, we demonstrate the recognition performance of our system through some experiments using two different datasets.

A Study of Transient Liquid Phase Bonding with Ni-foam/Sn-3.0Ag-0.5Cu Composite Solder for EV Power Module Package Application (Ni-foam/Sn-3.0Ag-0.5Cu 복합 솔더 소재를 이용한 EV 파워 모듈 패키지용 천이 액상 확산 접합 연구)

  • Young-Jin Seo;Min-Haeng Heo;Jeong-Won Yoon
    • Journal of the Microelectronics and Packaging Society
    • /
    • v.30 no.1
    • /
    • pp.55-62
    • /
    • 2023
  • In this study, Sn-3.0Ag-0.5Cu (wt.%, SAC305) solder dipping process was performed between Ni-foam skeleton with different pore per inch (PPI) to fabricate Ni-foam/SAC305 composite solder, and then applied to the transient liquid phase (TLP) bonding process to evaluate the microstructure and mechanical properties of the bonded joint. The Ni-foam/SAC305 composite solder preform consisted of Ni-foam and SAC305, and an intermetallic compound (IMC) having a (Ni,Cu)3Sn4 composition was formed at the Ni-foam interface. During TLP bonding process, the IMC at the Ni-foam interface was converted to (Ni,Cu)3Sn4+Au, and as the bonding time increased, the Ni-foam and SAC305 continuously reacted, and the bonded joint was converted into an IMC. And it was confirmed that the 130 PPI Ni-foam/SAC305 composite solder joint was converted into an IMC at the fastest rate. As a result of performing a shear test to confirm the effect of Ni-foam on mechanical properties, solder joints under all conditions exhibited excellent mechanical properties of 50 MPa or more in the early stages of the TLP bonding process, and the shear strength tends to increase as the bonding time increases.

MRI study of temporomandibular joint disorder in orthodontic patients (교정환자에서 MRI를 이용한 측두하악관절 장애의 연구)

  • Kim, Tae-Woo;Byun, Eun-Sun;Baek, Seung-Hak;Chang, Young-Il;Nahm, Dong-Seok;Yang, Won-Sik
    • The korean journal of orthodontics
    • /
    • v.30 no.2 s.79
    • /
    • pp.235-243
    • /
    • 2000
  • Magnetic resonance imaging(MRI) of the temporomandibular joint(TMJ) is very useful method to diagnose internal derangement of the TMJ because of its high specificity foy identification of condyle-disc relationships. The purpose of this study was to evaluate the existence, incidence and severity o』 internal derangement o』 the TMJ by the MRI of Patients who are suspected to have TMJ disorder. MRI sample was composed of 50 subjects(10 males, 40 females) and the mean age was 22.9 years. 43 subjects of the sample were found to have positive findings. $56\%$ of the subjects with positive findings had ADD(anterior disc displacement) without reduction, and $65\%$ had internal derangement of bilateral joints. Distributions in the types of malocclusion in patients with positive findings, the Angle's classification had shown : the largest $41.9\%$ for Cl II ($39.6\%$ for Cl II div 1 and $2.3\%$ for Cl II div 2), $37.2\%$ for Cl I, $18.6\%$ for Cl III, and $2.3\%$ for the unidentified. $8.6\%$ of the subjects with positive findings had facial asymmetry and $55.8\%$ had openbite. We can conclude that the percentage of Cl II is the highest in patients with internal derangement of the TMJ. Openbite or facial asymmetry is considered to be uncompensated or compensated deformity which results from facial skeleton remodeling in the process of degenerative joint disease(DJD) due to TMJ degeneration. Therefore it is recommended to screen the patients with facial asymmetry or openbite by MRI before the beginning of orthodontic treatment. Differential diagnosis is essential because the tendency of relapse is high after the orthodontic treatment and continuous observation of TMJ is needed in patients with TMJ disorder.

  • PDF

A Study on the Degree of Need of Human Structure and Function Knowledge in Clinical Nurses (기초간호자연과학의 인체구조와 기능 내용별 필요도에 대한 연구)

  • Choe, Myoung-Ae;Byun, Young-Soon;Seo, Young-Sook;Hwang, Ae-Ran;Kim, Hee-Seung;Hong, Hae-Sook;Park, Mi-Jung;Choi, Smi;Lee, Kyung-Sook;Seo, Wha-Sook;Shin, Gi-Soo
    • Journal of Korean Biological Nursing Science
    • /
    • v.1 no.1
    • /
    • pp.1-24
    • /
    • 1999
  • The purpose of this study was to define the content of requisite human structure and function knowledge needed for clinical knowledge of nursing practice. Subjects of human structure and function were divided into 10 units, and each unit was further divided into 21 subunits, resulting in a total of 90 items. Contents of knowledge of human structure and function were constructed from syllabus of basic nursing subjects in 4 college of nursing, and textbooks published by nurse scholars prepared with basic nursing sciences. The degree of need of 90 items was measured with a 4 point scale. The subjects of this study were college graduated 136 nurses from seven university hospitals in Seoul and three university hospitals located in Chonnam Province, Kyungbook Province, and Inchon. They have been working at internal medicine ward, surgical ward, intensive care unit, obstetrics and gynecology ward, pediatrics ward, opthalmology ward, ear, nose, and throat ward, emergency room, rehabilitation ward, cancer ward, hospice ward, and their working period was mostly under 5 years. The results were as follows: 1. The highest scored items of human structure and function knowledge necessary for nursing practice were electrolyte balance, blood clotting mechanism and anticoagulation mechanism, hematopoietic function, body fluid balance, function of plasma, and anatomical terminology in the order of importance. The lowest scored items of human structure and function knowledge necessary for nursing practice was sexual factors of genetic mutation. 2. The highest order of need according to unit was membrane transport in the living unit, anatomical terminology in movement and exercise unit, mechanism of hormone function in regulation and integration unit, component and function of blood in oxygenation function unit, structure and function of digestive system in digestive and energy metabolism unit, temperature regulation in temperature regulation unit electrolyte balance in body fluid and electrolyte unit, concept of immunity in body resistance unit, and genetics terminology in genetics unit. The highest order of importance according to subunit was membrane transportation in cell subunit, classification of tissues in tissue unit, function of skin and skin in skin subunit, anatomical derivatives of the skeleton subunit, classification of joints in joint subunit, an effect of exercise on muscles in muscle subunit, function of brain in nervous system subunit, special sense in sensory subunit mechanism of hormone function in endocrine subunit, structure and function of female reproductive system in reproductive system unit, structure and function of blood in blood unit, structure of heart, electrical and mechanical function in cardiovascular system unit, structure of respiratory system in respiratory system subunit, structure and function of digestive system in digestive system subunit, hormonal regulation of metabolism in nutrition and metabolism subunit, function of kidney in urologic system subunit, electolyte balance in body fluid, electolyte and acid-base balance subunit. 3. The common content of human structure and function knowledge need for all clinical areas in nursing was structure and function of blood, hematopoietic function, function of plasm, coagulation mechanism and anticoagulation mechanism, body fluid, electrolyte balance, and acid-base balance. However, the degree of need of each human structure and function knowledge was different depending on clinical areas. 4. Significant differences in human structure and function knowledge necessary for nursing practice such as skin and derivatives of the skin, growth and development of bone, classification of joint, classification of muscle, structure of muscle, function of muscle, function of spinal cord, peripheral nerve, structure and function of pancrease, component and function of blood, function of plasma, structure and function of blood, hemodynamics, respiratory dynamics, gas transport, regulation of respiration, chemical digestion of foods, absorption of foods, characteristics of nutrients, metabolism and hormonal regulation, body energy balance were demonstrated according to the duration of work. 5. Significant differences in human structure and function knowledge necessary for nursing practice such as classification of tissue, classification of muscles, function of muscles, muscle metabolism, classification of skeletal muscles, classification of nervous system, neurotransmitters, mechanism of hormone function, pituitary and pituitary hormone, structure and function of male reproductive organ, structure and function of female reproductive organ, component and function of blood, function of plasma, coagulation mechanism and anticoagulation mechanism, gas exchange, gas transport, regulation of respiration, characteristics of nutrients, energy balance, function of kidney, concept of immunity, classification and function of immunity were shown according to the work area. Based on these findings, all the 90 items constructed by Korean Academic Society of Basic Nursing Science should be included as contents of human structure and function knowledge.

  • PDF