Body Posture Estimation Research Articles

Attitude estimation for an all-rotating monocopter through attitude decomposition and MARG Sensor fusion

A monocopter is a biology-inspired aircraft based on samara. Due to the constant high spin during flight, attitude estimation is highly challenging. The difficulty of attitude estimation is extracting the effective gravity acceleration information from the large centripetal acceleration interference. Based on the characteristics of monocopters, our study proposes a method to accomplish monocopter attitude estimation through onboard sensor fusion. Our method decomposes the body attitude angles into two-disc attitude angles and three relative attitude angles. Through five steps (a priori body attitude estimation, relative attitude calculation, gravity acceleration information extraction, body attitude estimation through data fusion, and disc attitude estimation), a low-cost attitude determination method relying only on magnetic, angular rate, and gravity sensors is achieved. Finally, the performance of our proposed attitude estimation method is demonstrated through tests on a rotational platform and three degrees of freedom virtual flight testing of a monocopter. The test results show that the attitude estimation method has high precision and the ability for practical applications.

Feature-based multimodal registration framework for vertebral pose estimation

PurposeThe reliable estimation of the vertebral body posture helps to aid a safe and effective spine surgery. The proposed work aims to present an MR to X-ray image registration to assess the 3D pose of the vertebral body during spine surgery. The 3D assessment of vertebral pose assists in analyzing the position and orientation of the vertebral body to provide information during various clinical diagnosis conditions such as curvature estimation and pedicle screw insertion surgery.MethodsThe proposed feature-based registration framework extracted vertebral end plates to avoid the mismatch between the intensities of MR and X-ray images. Using the projection matrix, the segmented MRI is forward projected and then registered to the X-ray image using binary image matching similarity and the CMA-ES optimizer.ResultsThe proposed method estimated the vertebral pose by registering the simulated X-ray onto pre-operative MRI. To evaluate the efficacy of the proposed approach, a certain number of experiments are carried out on the simulated dataset.ConclusionThe proposed method is a fast and accurate registration method that can provide 3D information about the vertebral body. This 3D information is useful to improve accuracy during various clinical diagnoses.

A Practical Study of Basketball Teaching Reform in Colleges and Universities Based on Big Data

Abstract In this paper, the human body posture estimation algorithm is used to locate the key points of the human body in the RGB screen, and two human body multi-objective algorithms are used to predict the posture trajectory, and they can overcome the influence of the errors contained in the information recorded by the sensors to a certain extent. Secondly, the spatio-temporal graph convolutional neural network is used to identify human behavior and extract behavioral action features, and through the analysis of the action features, we understand the basketball skill level of the students and put forward the reform strategy of college basketball teaching. Sixty students from the basketball minor class at University Q’s College of Physical Education were selected as research subjects for teaching practice. The results show that the average scores of the students in spot-up shooting, half-court folding dribbling and marching one-handed over-the-shoulder shooting after the reform are higher than those before the reform by 1.80, 1.08, and 1.85, which indicates that the reform of basketball teaching based on big data can improve the students’ interest in learning and their training scores, and enhance the students’ basketball skill level.

Research on Multi-Person Pose Estimation Technology

Abstract Human pose estimation is a hot topic of computer research in recent years, which promotes the progress of society and brings many conveniences to people’s lives. Fom traditional methods to the mainstream deep learning-based methods, the primary approach in deep learning involves the use of convolutional neural networks to reduce computational complexity and improve network accuracy, but because the network structure is too deep to improve the accuracy, the trained model parameters are also very large, and it is very dependent on the input of hardware equipment. At this time, the lightweight human pose estimation can solve this problem very well. This paper mainly describes the knowledge of convolutional neural network in detail and compares it with traditional image algorithms. The OpenPose model is a classic model based on convolutional neural network that can well achieve single-person and multi-person human pose estimation model, but because the convolution kernel in its network structure is too large to increase the amount of calculation, this paper proposes three improvements to the network structure of the conventional OpenPose model. Finally, the precision of the model is improved by about 40%, which verifies the feasibility of lightweight human body posture estimation research.

A hybrid neural network-based intelligent body posture estimation system in sports scenes.

Body posture estimation has been a hot branch in the field of computer vision. This work focuses on one of its typical applications: recognition of various body postures in sports scenes. Existing technical methods were mostly established on the basis of convolution neural network (CNN) structures, due to their strong visual information sensing ability. However, sports scenes are highly dynamic, and many valuable contextual features can be extracted from multimedia frame sequences. To handle the current challenge, this paper proposes a hybrid neural network-based intelligent body posture estimation system for sports scenes. Specifically, a CNN unit and a long short-term memory (LSTM) unit are employed as the backbone network in order to extract key-point information and temporal information from video frames, respectively. Then, a semi-supervised learning-based computing framework is developed to output estimation results. It can make training procedures using limited labeled samples. Finally, through extensive experiments, it is proved that the proposed body posture estimation method in this paper can achieve proper estimation effect in real-world frame samples of sports scenes.

Estimation of upper body posture while riding a bicycle based on load measurement

Estimation of upper body posture while riding a bicycle based on load measurement

Asymptotically stable optimal multi-rate rigid body attitude estimation based on lagrange-d'alembert principle

<abstract><p>The rigid body attitude estimation problem is treated using the discrete-time Lagrange-d'Alembert principle. Three different possibilities are considered for the multi-rate relation between angular velocity measurements and direction vector measurements for attitude: 1) integer relation between sampling rates, 2) time-varying sampling rates, 3) non-integer relation between sampling rates. In all cases, it is assumed that angular velocity measurements are sampled at a higher rate compared to the inertial vectors. The attitude determination problem from two or more vector measurements in the body-fixed frame is formulated as Wahba's problem. At instants when direction vector measurements are absent, a discrete-time model for attitude kinematics is used to propagate past measurements. A discrete-time Lagrangian is constructed as the difference between a kinetic energy-like term that is quadratic in the angular velocity estimation error and an artificial potential energy-like term obtained from Wahba's cost function. An additional dissipation term is introduced and the discrete-time Lagrange-d'Alembert principle is applied to the Lagrangian with this dissipation to obtain an optimal filtering scheme. A discrete-time Lyapunov analysis is carried out to show that the optimal filtering scheme is asymptotically stable in the absence of measurement noise and the domain of convergence is almost global. For a realistic evaluation of the scheme, numerical experiments are conducted with inputs corrupted by bounded measurement noise. These numerical simulations exhibit convergence of the estimated states to a bounded neighborhood of the actual states.</p></abstract>

Researches Advanced in Human Pose Estimation Based on Deep Learning

Human pose estimation has always been a popular research topic in the discipline of computer vision, which aims to predict the spatial position of the human body’s key points (parts/joints) from a given image or video. Benefiting from the powerful feature representation ability of the convolutional neural networks, the pose estimation methods based on the deep learning have become the mainstream framework of this task, which obtain the human pose estimation results by extracting the human pose feature information at different scales with specific neural networks and using the corresponding methods to process it. This paper, based on the depth study of human body posture estimation can be divided into single-task and multi-person missions. The time and method of correlation are classified and summarized, respectively from the network architecture, algorithm and feature extraction of performance that are analyzed. The current problems existing in the research field and methods are summarized, and the research prospect for the future has been prospected.

Determining human upper limb postures with a developed inverse kinematic method

AbstractBody posture determination methods have many applications, including product design, ergonomic workplace design, human body simulation, virtual reality, and animation industry. Initiated in robotics, inverse kinematic (IK) method has been widely applied to proactive human body posture estimation. The analytic inverse kinematic (AIK) method is a convenient and time-saving type of IK methods. It is also indicated that, based on AIK methods, a specific body posture can be determined by the optimization of an arbitrary objective function. The objective of this paper is to predict the postures of human arms during reaching tasks. In this research, a human body model is established in MATLAB, where the middle rotation axis analytic kinematic method is accomplished, based on this model. The joint displacement function and joint discomfort function are selected to be initially applied in this AIK method. Results show that neither the joint displacement function nor the joint discomfort function predicts postures that are close enough to natural upper limb postures of human being, during reaching tasks. Therefore, a bi-criterion objective function is proposed by integrating the joint displacement function and joint discomfort function. The accuracy of the arm postures, predicted by the proposed objective function, is the most satisfactory, while the optimal value of the coefficient, in the proposed objective function, is determined by golden section search.

Application of Human Posture Recognition Based on the Convolutional Neural Network in Physical Training Guidance.

The application of sports game video analysis in athlete training and competition analysis feedback has attracted extensive attention, but the traditional sports human body posture estimation method has a large error between the athlete's human body posture estimation results and the actual results in the complex environment and the athlete's body parts are blocked. Therefore, this study proposes a convolutional neural network for athlete pose estimation in sports game video. Based on the improved model, multiscale model, and large perception model, a superimposed hourglass network is constructed, and the gradient disappearance problem of the convolutional neural network is solved using intermediate supervision. The experimental results show that the athlete pose estimation model based on the convolutional neural network can improve the accuracy of athlete pose estimation and reduce the negative impact of occlusion environment on athlete pose estimation to a certain extent. In addition, compared with other athletes' standing posture estimation methods, the model has competitive advantages and high accuracy under widely used standard conditions.

Research on Real-Time Detection of Safety Harness Wearing of Workshop Personnel Based on YOLOv5 and OpenPose

Wearing safety harness is essential for workers when carrying out work. When posture of the workers in the workshop is complex, using real-time detection program to detect workers wearing safety harness is challenging, with a high false alarm rate. In order to solve this problem, we use object detection network YOLOv5 and human body posture estimation network OpenPose for the detection of safety harnesses. We collected video streams of workers wearing safety harnesses to create a dataset, and trained the YOLOv5 model for safety harness detection. The OpenPose algorithm was used to estimate human body posture. Firstly, the images containing different postures of workers were processed to obtain 18 skeletal key points of the human torso. Then, we analyzed the key point information and designed the judgment criterion for different postures. Finally, the real-time detection program combined the results of object detection and human body posture estimation to judge the safety harness wearing situation within the current screen and output the final detection results. The experimental results prove that the accuracy rate of the YOLOv5 model in recognizing the safety harness reaches 89%, and the detection method of this study can ensure that the detection program accurately recognizes safety harnesses, and at the same time reduces the false alarm rate of the output results, which has high application value.

Anti-swaying self-alignment method based on observation vector inertia for SINS under latitude uncertainty

The self-alignment of strapdown inertial navigation system that does not depend on any external aid still has huge application requirements. This study presents an anti-swaying self-alignment method based on the inertia tensor of gravity observation vectors and aims to improve the accuracy and efficiency of the latitude and attitude estimation by making full use of inertial measurements. The time-varying attitude matrix is decomposed first to isolate the swaying interference and gravity observation vectors are reconstructed to smooth the measurement noise. Then the body attitude estimation with unknown latitude is defined as an extended Wahba problem, which is solved by eigenvalue decomposition based on the inertia tensor of gravity observation vectors. Simulation and experiments verify the effectiveness of the proposed method and two common methods are used for comparison, which show that the proposed method has faster convergence speed, stronger anti-interference ability, and higher accuracy of the latitude and attitude estimation.

Joint Position Estimation for Body Pressure Images during Sleep: An Extension for CPM Using Body Area and Posture Estimation Mashups

Joint Position Estimation for Body Pressure Images during Sleep: An Extension for CPM Using Body Area and Posture Estimation Mashups

Discrete pointvv 3D reconstruction algorithm based human pose estimation

The traditional method of human pose estimation lacks depth label in depth image, which leads to the low generalization ability of model due to single pose. A novel method of human pose estimation based on discrete point 3D reconstruction algorithm is proposed. Several cameras are placed around each other, and the internal parameters of the camera are calibrated by the classical calibration method , and the external parameters of the camera group are obtained. According to the two-dimensional skeleton, the human body region model is established, and the contour is matched with the human body model, so that the contour region is segmented, and then the three-dimensional human body model is constructed. According to the principle of discrete point 3D reconstruction algorithm, principal component analysis is used to transform the original data, eliminate the redundant correlation between the original human body posture data, establish the human body posture model, obtain 10 individual voxel sets, and estimate the 3D information of each point in the voxel set. In the process of feature extraction, two-dimensional attitude prediction, two-dimensional fusion layer and final conversion, the human body attitude estimation is realized. Experimental results show that this method can reduce the influence of image shadow on image recognition, and the estimation results are more accurate.

Fast and Robust Algorithm for Detecting Body Posture Using Wrist-Worn Accelerometers

Background: The increasing popularity of wrist-worn accelerometers introduces novel challenges to the research on physical activity and sedentary behavior. Estimation of body posture is one such challenge. Methods: The authors proposed an approach called SedUp to differentiate between sedentary (sitting/lying) and standing postures. SedUp is based on the logistic regression classifier, using the wrist elevation and the motion variability extracted from raw accelerometry data collected on the axis parallel to the forearm. The authors developed and tested our method on data from N = 45 community-dwelling older adults. All subjects wore ActiGraph GT3X+ accelerometers on the left and right wrist, and activPAL was placed on the thigh in the free-living environment for 7 days. ActivPAL provided ground truth about body posture. The authors reported SedUp’s classification accuracy for each wrist separately. Results: Using the data from the left wrist, SedUp estimated the standing posture with median true positive rate = 0.83 and median true negative rate = 0.91. Using the data from the right wrist, SedUp estimated the standing posture with median true positive rate = 0.86 and median true negative rate = 0.93. Conclusions: SedUp provides accurate classification of body posture using wrist-worn accelerometers. The separate validation for each wrist allows for the application of SedUp in a wide spectrum of free-living studies.

A REAL-TIME PHOTOGRAMMETRIC SYSTEM FOR MONITORING HUMAN MOVEMENT DYNAMICS

Abstract. The human body posture is rich with dynamic information that can be captured by algorithms, and many applications rely on this type of data (e.g., action recognition, people re-identification, human-computer interaction, industrial robotics). The recent development of smart cameras and affordable red-green-blue-depth (RGB-D) sensors has enabled cost-efficient estimation and tracking of human body posture. However, the reliability of single sensors is often insufficient due to occlusion problems, field-of-view limitations, and the limited measurement distances of the RGB-depth sensors. Furthermore, a large-scale real-time response is often required in certain applications, such as physical rehabilitation, where human actions must be detected and monitored over time, or in industries where human motion is monitored to maintain predictable movement flow in a shared workspace. Large-scale markerless motion-capture systems have therefore received extensive research attention in recent years.In this paper, we propose a real-time photogrammetric system that incorporates multithreading and a graphic process unit (GPU)-accelerated solution for extracting 3D human body dynamics in real-time. The system includes a stereo camera with preliminary calibration, from which left-view and right-view frames are loaded. Then, a dense image-matching algorithm is married with GPU acceleration to generate a real-time disparity map, which is further extended to a 3D map array obtained by photogrammetric processing based on the camera orientation parameters. The 3D body features are acquired from 2D body skeletons extracted from regional multi-person pose estimation (RMPE) and the corresponding 3D coordinates of each joint in the 3D map array. These 3D body features are then extracted and visualised in real-time by multithreading, from which human movement dynamics (e.g., moving speed, knee pressure angle) are derived. The results reveal that the process rate (pose frame-rate) can be 20 fps (frames per second) or above in our experiments (using two NVIDIA 2080Ti and two 12-core CPUs) depending on the GPU exploited by the detector, and the monitoring distance can reach 15 m with a geometric accuracy better than 1% of the distance.This real-time photogrammetric system is an effective real-time solution to monitor 3D human body dynamics. It uses low-cost RGB stereo cameras controlled by consumer GPU-enabled computers, and no other specialised hardware is required. This system has great potential for applications such as motion tracking, 3D body information extraction and human dynamics monitoring.

Machine-Learning Estimation of Body Posture and Physical Activity by Wearable Acceleration and Heartbeat Sensors

Machine-Learning Estimation of Body Posture and Physical Activity by Wearable Acceleration and Heartbeat Sensors

Machine-Learning Estimation of Body Posture and Physical Activity by Wearable Acceleration and Heartbeat Sensors

Machine-Learning Estimation of Body Posture and Physical Activity by Wearable Acceleration and Heartbeat Sensors

Volumetric reconstruction of thermal-depth fused 3D models for occluded body posture estimation

Abstract Reliable and effective occluded skeletal posture estimation is a challenging problem for vision-based modalities that do not provide inter-surface imaging. These include both visible-light and depth-based devices that all existing pose estimation techniques are derived from. This fundamental limitation in skeletal tracking is due to the inability of these techniques to penetrate occluding surface materials to derive joint configurations that are not directly visible to the camera. In this work, we present a new method of estimating skeletal posture in occluded applications using both depth and thermal imaging through volumetric modeling and introduce a new occluded ground-truth tracking method inspired by modern motion capture solutions for tracking occluded joint positions. Using this integrated volumetric model, we utilize Convolutional Neural Networks to characterize and identify volumetric thermal distributions that match trained skeletal posture estimates which includes disconnected skeletal definitions and allows correct posture estimation in highly ambiguous cases. We demonstrate this approach by accurately identifying common sleep postures that present challenging cases for current skeletal joint estimation techniques and evaluate the use of volumetric thermal models for various sleep-study related applications.

Numerical algorithm for rigid body position estimation using the quaternion approach

This paper deals with rigid body attitude estimation on the basis of the data obtained from an inertial measurement unit mounted on the body. The aim of this work is to present the numerical algorithm, which can be easily applied to the wide class of problems concerning rigid body positioning, arising in aerospace and marine engineering, or in increasingly popular robotic systems and unmanned aerial vehicles. Following the considerations of kinematics of rigid bodies, the relations between accelerations of different points of the body are given. A rotation matrix is formed using the quaternion approach to avoid singularities. We present numerical procedures for determination of the absolute accelerations of the center of mass and of an arbitrary point of the body expressed in the inertial reference frame, as well as its attitude. An application of the algorithm to the example of a heavy symmetrical gyroscope is presented, where input data for the numerical procedure are obtained from the solution of differential equations of motion, instead of using sensor measurements.