Human Skeleton Model Research Articles

Real-Time Human Motion Capture Driven by a Wireless Sensor Network

The motion of a real object model is reconstructed through measurements of the position, direction, and angle of moving objects in 3D space in a process called “motion capture.” With the development of inertial sensing technology, motion capture systems that are based on inertial sensing have become a research hot spot. However, the solution of motion attitude remains a challenge that restricts the rapid development of motion capture systems. In this study, a human motion capture system based on inertial sensors is developed, and the real-time movement of a human model controlled by real people’s movement is achieved. According to the features of the system of human motion capture and reappearance, a hierarchical modeling approach based on a 3D human body model is proposed. The method collects articular movement data on the basis of rigid body dynamics through a miniature sensor network, controls the human skeleton model, and reproduces human posture according to the features of human articular movement. Finally, the feasibility of the system is validated by testing of system properties via capture of continuous dynamic movement. Experiment results show that the scheme utilizes a real-time sensor network-driven human skeleton model to achieve the accurate reproduction of human motion state. The system also has good application value.

Dark Environment Motion Analysis Using Scalable Model and Vector Angle Technique

Detecting human existence in video streams is a fundamental task in many video processing applications. In this paper, a novel procedure is produced to model, analyze and recognize human motions (jogging and walking in dark environment) in video streams. There are four major areas that are related in this project for human motion analysis: (1) developing human body structure based on human skeleton model, (2) tracking and data collecting human motion with side view, (3) recognizing human activities from image sequences, and (4) image processing technique using edge detection and vectors angle calculation. All algorithms are developed using MATLAB software. Segmentation is developed to reduce the amount of data and filters out the useless information. Two methods are proposed for angle calculation and activities classification. Results showed that angle between 153.76°-180° for method 1 and 49.64°-92.86° for method 2 is classified as walking while jogging is 95.17°-138.72° for method 1 and 22.62°-56.31° for method 2.

Research on Wearable Human Motion Capture and Virtual Control

This paper designed the posture initialization calibration method by the inertial sensor in human limb movement with any attitude toward. By initializing the target specific actions can be implemented to identify timing corresponding sensors and joint, and calculate the coordinate transformation relation of human skeletal coordinates corresponding to each inertial sensor's coordinate system and the 3D human skeleton model. Then through the coordinate conversion of inertial sensor attitude coordinates and depth first traversal calculation on human skeletal tree, real-time update of human motion body attitude data, driven simulation of human skeletal model by human motion, realize the real-time tracking of motion capture.

3-D Human Action Recognition by Shape Analysis of Motion Trajectories on Riemannian Manifold.

Recognizing human actions in 3-D video sequences is an important open problem that is currently at the heart of many research domains including surveillance, natural interfaces and rehabilitation. However, the design and development of models for action recognition that are both accurate and efficient is a challenging task due to the variability of the human pose, clothing and appearance. In this paper, we propose a new framework to extract a compact representation of a human action captured through a depth sensor, and enable accurate action recognition. The proposed solution develops on fitting a human skeleton model to acquired data so as to represent the 3-D coordinates of the joints and their change over time as a trajectory in a suitable action space. Thanks to such a 3-D joint-based framework, the proposed solution is capable to capture both the shape and the dynamics of the human body, simultaneously. The action recognition problem is then formulated as the problem of computing the similarity between the shape of trajectories in a Riemannian manifold. Classification using k-nearest neighbors is finally performed on this manifold taking advantage of Riemannian geometry in the open curve shape space. Experiments are carried out on four representative benchmarks to demonstrate the potential of the proposed solution in terms of accuracy/latency for a low-latency action recognition. Comparative results with state-of-the-art methods are reported.

Human Body Kinematics and the Kinect Sensor

For a good understanding of human body biomechanics scientist all over the world are using motion capture systems (MoCap). Such a system is mainly composed of one or multiple high performance cameras and a process unit for gathering key information. A low – cost solution for these systems is the Kinect sensor from Microsoft. The Kinect sensor is a depth camera that can be used for assessing full – body movements in terms of joint and/or segment positions and movement geometries. The resulting data can be used in the robotic industry, in clinical solutions, video gaming industries etc. The functionality of the equipment has been highly debated in many studies wherefrom result that the depth camera in question is accurate and reliable in studies such as human biomechanics. The aim of this paper is to explain the logics behind this equipment and its functionality. Therefore we present a new approach in constructing a 3D human skeleton model that can be used for assessing asymmetries by determining the human silhouette in 3D, the position of human body key points and joints, the angles between the track segments and full body kinematics.

The Research and Application of Computer Technology for the Sports Skilled Motion Characteristic Model

with the intense degree of sports competition strengthening and improvement of the application of computer technology, how to carry out skilled motion targeted training is one of the most important problems needed to be solved for athletes and coaches must face. In this article, by analyzing the sports linkage principle from the perspective of the human skeleton model, and based on computer Petri technology, it is combined with the feature of regular physical activity data to set up a sports skilled motion characteristic model excavating the association rules among the sports skilled motion, so as to shorten the development period of training and improve the level of the athletes, providing a scientific research method.

Capturing Human Motion based on Modified Hidden Markov Model in Multi-View Image Sequences

Human motion capturing is of great importance in video information retrieval, hence, in this paper, we propose a novel approach to effectively capturing human motions based on modified hidden markov model from multi-view image sequences. Firstly, the structure of the human skeleton model is illustrated, which is extended from skeleton root and spine root, and this skeleton consists of right leg, left leg and spine. Secondly, our proposed human motion capturing system is made up of data training module and human motion capturing module. In the data training module, multi-views motion information is extracted from a human motion database, and feature database of human motion capturing is constructed through combining multi-views motions. In the human motion capturing module, results of motion capturing can be achieved through motion classification based on a modified hidden markov model. Thirdly, the modified hidden markov model is designed by utilizing the fuzzy measure, fuzzy integer, and fuzzy intersection operator through a scaling process. Finally, a standard motion capture dataset- MPI08_Database is utilized to make performance evaluation. Compared with the existing methods, the proposed approach can effectively capture human motions with high precision

Interactive indoor environment mapping through visual tracking of human skeleton

This paper presents a novel human-robot interaction approach to grid mapping of an indoor environment based on a 3D kinect sensor and the grid-based mapping algorithm. It mainly includes three modules: skeleton tracking, robot control and GMapping. Firstly, the skeleton tracking module builds a human skeleton model, extracts the skeleton joints’ position information from 3D visual data and generates digital signals through identifying some simple motions and events. Then according to different digital signals and joints’ position information, the robot control module enables the robot to take different actions such as following the person, stop and so on. Finally, the grid map of the environment is built through GMapping algorithm based on odometry and laser data, which is improved by Rao-Blackwellised particle filters. The proposed approach has been implemented successfully in several different buildings and can be applied to service robots. Compared with traditional roaming for mapping, human guiding the robot for mapping is more efficient and takes less time in a complicated environment. Meanwhile, compared with wearable motion sensors attached to the human body, this approach is more convenient and make the user more comfortable.

基于手形的骨骼手语库构建研究<br>Study of Skeleton Sign Language Based on the Hand Shape

手语词库的构建是手语识别与合成的基础。本文通过分析中国手语的特点，提出了一种基于扩展Kinect人体骨骼模型，以手形组合构建骨骼手语库的方法。通过采集手语表达过程当中的关键状态，记录手形、位置和方向等数据，形成手语词关键帧数据，实现了一个中文骨骼手语编辑系统，有效的提高手语词汇的合成效率。生成的数据通过关键帧插值算法可实现手语词的动态组合，为基于骨骼手语库的手语识别及合成奠定了基础。 Building of sign language thesaurus is the basis of sign language recognition and synthesis. Through analyzing the characteristics of Chinese sign language, this paper proposes a human skeleton model which is based on expansion Kinect, and built skeleton sign language thesaurus with a combination of hand shape. It achieves an editing system of Chinese skeleton sign language by acquisition of the key state in sign language expression, then recording data of hand shapes, positions and orientations, and forming key frame data of sign language at last. It effectively improves synthesis efficiency for sign language. Data generates from which can make dynamic combination through the key frame interpolation algorithm, and lays the foundation for the recognition and synthesis of sign language thesaurus.

Video-Based Human Motion Analysis

In the analysis of human motion, movement was divided into regular motion (such as walking and running) and random motion (such as falling down).Human skeleton model is used in this paper to do the video-based analysis. Key joints on human body were chosen to be traced instead of tracking the entire human body. Shape features like mass center trajectory were used to describe the movement, and to classify human motion. desired results achieved.

IK and Biomechanical Model of Human Skeleton for Motion Simulation

Zhijun Song, Changle Zhou, Kunhui Lin 1, First The Cognitive Science Department, Xiamen University, Xiamen, China and Fujian Key Laboratory of the Brain-like Intelligent Systems, Xiamen, China, jason@xmu.edu.cn *2,Corresponding The Cognitive Science Department, Xiamen University, dozero@xmu.edu.cn The Software School, Xiamen University, Xiamen, Fujian, China, khlin@xmu.edu.cn doi : 10.4156/aiss.vol3.issue7.36

Reconstruction of Human Skeleton Model Based on Selective Laser Sintering

Based on CT data of the lesion of an orthopedic patient with knee, Mimics13.1, Magics9.5 can be used for the medical image processing. The CT image data were filtered, interpolated, sharpen, the interest region was extracted by the application of threshold segmentation method and was grown. The three dimension model of patient’s skeleton is reconstructed. Based on selective laser sintering, the digit model of patient’s skeleton reconstructed can be accurately transformed into the object model of the individual matching skeleton. The results indicated that the contour of reconstructed knee-joint bone object model were very coincident, and symmetric with knee-joint bone defect.

Flexible multibody approach in forward dynamic simulation of locomotive strains in human skeleton with flexible lower body bones

A method for bone strain estimation is examined in this article. The flexibility of a single bone in an otherwise rigid human skeleton model has been studied previously by various authors. However, in the previous studies, the effect of the flexibility of multiple bones on the musculoskeletal model behavior was ignored. This study describes a simulation method that can be used to estimate the bone strains at both tibias and femurs of a 65-year-old Caucasian male subject. The verification of the method is performed by the comparison of the results with other studies available in literature. The results of the study show good correlation with the results of previous empirical studies. A damping effect of the flexible bones on the model is also studied in this paper.

Micro-sensor driven human model for 3D real-time movement

A human model for the human motion capture and reconstruction was set up and the real-time movement of human model controlled by real people's movement was realized. According to the features of the system of the human motion capture and reconstruction,the authors proposed a method of constructing a sensor data-driven layered human motion model and a method of polygon grouping to achieve skin deformation. The methods are based on biomechanics. The joints of human body were categorized according to the motion characteristics. Motion parameters estimated from sensor data were used to control the movement of human skeleton model and the deformation of skin model,and consequently reconstruct the human body motion in real-time animation. The experimental results show that the proposed model is suitable for sensor data-driven virtual-human in real-time animation and has good biomechanics characteristics in representing human motion.

Estimate 3D Arm Motion with Hierarchical Limb Model

Focusing on the problem of low computation efficiency in the process of tracking human 3D motion, an algorithm for Estimating 3D arm motion with Hierarchy Limb Model (HLM) is proposed. In our algorithm, the Hierarchy Limb Model (HLM) is proposed based on the human 3D skeleton model. Facilitated by graph decomposition, the arm motion state space, modeled by Hierarchy Limb Model (HLM), can be discomposed into low dimension subspaces. The Top-Down search strategy and the Particle Filter are used to tracking the arm motion, thus the amount of particle in tracking can be reduced. To handle server self-occlusions, the weighted color histogram and image contour are used to modeling the observation likelihood function. The result of experiment shows that our algorithm can advance the computation efficiency and handle effectively self-occlusions.

Using Rao-Blackwellised Particle Filter Track 3D Arm Motion based on Hierarchical Limb Model

For improving the efficiency of human 3D tracking, we present an algorithm to track 3D Arm Motion. First, the Hierarchy Limb Model (HLM) is proposed based on the human 3D skeleton model. Second, via graph decomposition, the arm motion state space, modeled by HLM, can be discomposed into two low dimension subspaces: root nodes and leaf nodes. Finally, Rao-Blackwellised Particle Filter is used to estimate the 3D arm motion. The result of experiment shows that our algorithm can advance the computation efficiency.

HUMAN POSTURE RECONSTRUCTION AND ANIMATION FROM MONOCULAR IMAGES BASED ON GENETIC ALGORITHMS

The paper aims to propose a new approach towards human posture reconstruction and animation from monocular video sequences that contain any kind of human postures and movements. This is a way towards low cost motion capture and at the same time it avoids many limitations of those classical methods. A parameterized human skeleton model based on anatomy is adopted where the angular constraints are encoded in the joints. Criterion Function is defined to represent the residuals between feature points in the monocular image and the corresponding points resulted from projecting the human model to the projection plane. By transforming each segment of the human model to achieve the minimum value of the Criterion Function, the proper human posture that resembles the one represented by the monocular image can be generated. Different kinds of adjustments are utilized to adjust the body parts into the proper locations and orientations in 3D space without camera calibration. In order to find the optimal solution effectively in a high-dimensional parameter space by considering all the parameters simultaneously, the method of Genetic Algorithms is proposed. A procedure is developed to recover the whole body posture, and then a human animation system is developed to animate a series of human movements from monocular image sequences, during which information between consecutive frames is considered to improve the accuracy. Our technique makes it feasible to reconstruct any possible human postures, and experimental results from many monocular images and video sequences are encouraging.

Skeletal effects of aging and menopausal status in female rhesus macaques.

To further define the nonhuman primate as a model of the adult human skeleton, we explored the impact of growth, natural menopause, and osteoarthritis on bone mass, serum markers of bone turnover (osteocalcin and C-terminal telopeptide of type I collagen) and measures of skeletal relevance (PTH, 25-hydroxyvitamin D, total alkaline phosphatase, calcium, phosphorus, creatinine, and albumin). Fifty-eight female (aged 4-30 yr) rhesus macaques were defined as growing (G; n = 12; < or = 10 yr old), adult premenopausal (APre; n = 30; > 10 yr old; eumenorrheic, high serum estradiol and low FSH), or postmenopausal (Post; n = 16; amenorrheic for at least 1 yr, with low serum estradiol and high FSH). Total body and posterior-anterior spinal bone masses were lower in G than APre animals (P < 0.05). Post females had lower total body, distal radius, and spinal bone mass than premenopausal animals (P < 0.05). Osteocalcin was higher in Post than APre animals (P < 0.01). Other measures showed no relationship with menopausal status. In older monkeys, spinal osteoarthritis became common, causing increased dual-energy x-ray absorptiometry-measured bone mass in the lumbar spinal posterior-anterior projection. In conclusion, after natural menopause, rhesus monkeys have lower bone mass and higher skeletal turnover without alteration of the calcium-vitamin D axis. As such, they are an excellent model of human estrogen-depletion bone loss.