scholarly journals [Papers] Multi-view video synchronization using motion rhythms of human joints

2020 ◽  
Vol 8 (2) ◽  
pp. 100-110
Author(s):  
Siqi Sun ◽  
Kosuke Takahashi ◽  
Dan Mikami ◽  
Mariko Isogawa ◽  
Yoshinori Kusachi

2021 ◽  
Vol 160 ◽  
pp. 107030
Author(s):  
David Rebenda ◽  
Martin Vrbka ◽  
David Nečas ◽  
Evgeniy Toropitsyn ◽  
Seido Yarimitsu ◽  
...  
Keyword(s):  


Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1356
Author(s):  
Linda Christin Büker ◽  
Finnja Zuber ◽  
Andreas Hein ◽  
Sebastian Fudickar

With approaches for the detection of joint positions in color images such as HRNet and OpenPose being available, consideration of corresponding approaches for depth images is limited even though depth images have several advantages over color images like robustness to light variation or color- and texture invariance. Correspondingly, we introduce High- Resolution Depth Net (HRDepthNet)—a machine learning driven approach to detect human joints (body, head, and upper and lower extremities) in purely depth images. HRDepthNet retrains the original HRNet for depth images. Therefore, a dataset is created holding depth (and RGB) images recorded with subjects conducting the timed up and go test—an established geriatric assessment. The images were manually annotated RGB images. The training and evaluation were conducted with this dataset. For accuracy evaluation, detection of body joints was evaluated via COCO’s evaluation metrics and indicated that the resulting depth image-based model achieved better results than the HRNet trained and applied on corresponding RGB images. An additional evaluation of the position errors showed a median deviation of 1.619 cm (x-axis), 2.342 cm (y-axis) and 2.4 cm (z-axis).



2021 ◽  
Vol 17 (3) ◽  
pp. 1-19
Author(s):  
Xin Li ◽  
Dawei Li

Forecasting human poses given a sequence of historical pose frames has several important applications, especially in the domain of smart home safety. Recently, computer vision-based human pose forecasting has made a breakthrough using deep learning technology. However, to implement a practical system deployed on an IoT edge environment, there are still two issues to be addressed. First, existing methods on pose forecasting fail to model the coherent structural information of connected human joints and thus cannot achieve satisfactory prediction accuracy, especially for long-term predictions. Second, a general and static pre-trained prediction model may not perform well in the deployment environment due to the visual domain shift problem. In this article, we propose a hybrid cloud-edge system called GPFS to solve those issues. Specifically, we first introduce a novel graph convolutional neural network (GCN)-based sequence-to-sequence learning method, which enhances the sequence encoder by using a graph to represent both the spatial and temporal connections of the human joints in the input frames. The GCN improves the forecasting accuracy by capturing the motion pattern of each joint as well as the correlations among different human joints over time. Second, to address the domain shift issue and protect data privacy, we extend the system to perform online learning on the IoT edge to adapt the cloud trained general model with online collected on-site domain data. Extensive evaluation on Human 3.6M and Penn Action datasets demonstrates the superiority of our proposed system.





1971 ◽  
Vol 10 (1) ◽  
pp. 21-27 ◽  
Author(s):  
M. A. M. A. Younes ◽  
P. S. Walker ◽  
P. C. Seller ◽  
D. Dowson ◽  
V. Wright


2005 ◽  
Vol 102 (24) ◽  
pp. 8698-8703 ◽  
Author(s):  
C. H. Evans ◽  
P. D. Robbins ◽  
S. C. Ghivizzani ◽  
M. C. Wasko ◽  
M. M. Tomaino ◽  
...  


1981 ◽  
Vol 10 (1) ◽  
pp. 39-43 ◽  
Author(s):  
M Nissan

The internal equilibrium of human joints has been dealt with by many investigators, either as a means for better understanding and treating joint diseases or as a basis for prosthetic design. In all cases there is less information than needed for an accurate solution, and the investigators have to use simplifying geometry and restricting assumptions. In this work a permutation method was used, which takes advantage of big computer facilities in order to reduce the number of assumptions needed. The method was used for the case of the knee joint. The results were compared to those available using a regular method, showing the permutation one to be superior.



Author(s):  
Shaoli Wu ◽  
Philip A. Voglewede

This paper develops an improvement to an existing forward dynamic human gait model. A human gait model was developed previously to assist virtual testing prostheses and orthoses. The model consists of a plant model and a controller model. The central tenet to the model is the model predictive control (MPC) algorithm, which is a highly robust controller. In the previous model, however, there are several drawbacks. First, the anthropometric and mechanical parameters in the parts of the model are specific to one person. Second, the simulation result of ground reaction force (GRF) is not realistic. In this paper, the anthropometric parameters are calculated based on commonly used models that approximate an average person’s size. As for the mechanical parameters, the spring and damper coefficients in the human joints and ground reaction force (GRF) system are estimated by using the parameter estimation module in MATLAB based on the experimental subject data. The paper concludes with a simulation results between the new improved model and the previous developed model.



Orthopedics ◽  
1987 ◽  
Vol 10 (3) ◽  
pp. 441-449
Author(s):  
Ejovo N Ohwovoriole
Keyword(s):  


Sign in / Sign up

Export Citation Format

Share Document