scholarly journals Motion Capture Research: 3D Human Pose Recovery Based on RGB Video Sequences

2019 ◽  
Vol 9 (17) ◽  
pp. 3613
Author(s):  
Xin Min ◽  
Shouqian Sun ◽  
Honglie Wang ◽  
Xurui Zhang ◽  
Chao Li ◽  
...  
Keyword(s):  
Motion Capture ◽  
Human Body ◽  
Video Data ◽  
Video Sequences ◽  
Video Streams ◽  
Generative Adversarial Network ◽  
Recovery Method ◽  
Pose Recovery ◽  
The Subject ◽  
Human Pose

Using video sequences to restore 3D human poses is of great significance in the field of motion capture. This paper proposes a novel approach to estimate 3D human action via end-to-end learning of deep convolutional neural network to calculate the parameters of the parameterized skinned multi-person linear model. The method is divided into two main stages: (1) 3D human pose estimation based on a single frame image. We use 2D/3D skeleton point constraints, human height constraints, and generative adversarial network constraints to obtain a more accurate human-body model. The model is pre-trained using open-source human pose datasets; (2) Human-body pose generation based on video streams. Combined with the correlation of video sequences, a 3D human pose recovery method based on video streams is proposed, which uses the correlation between videos to generate a smoother 3D pose. In addition, we compared the proposed 3D human pose recovery method with the commercial motion capture platform to prove the effectiveness of the proposed method. To make a contrast, we first built a motion capture platform through two Kinect (V2) devices and iPi Soft series software to obtain depth-camera video sequences and monocular-camera video sequences respectively. Then we defined several different tasks, including the speed of the movements, the position of the subject, the orientation of the subject, and the complexity of the movements. Experimental results show that our low-cost method based on RGB video data can achieve similar results to commercial motion capture platform with RGB-D video data.

scholarly journals MoVi: A large multi-purpose human motion and video dataset

PLoS ONE ◽  
2021 ◽  
Vol 16 (6) ◽  
pp. e0253157
Author(s):  
Saeed Ghorbani ◽  
Kimia Mahdaviani ◽  
Anne Thaler ◽  
Konrad Kording ◽  
Douglas James Cook ◽  
...  
Keyword(s):  
Motion Capture ◽  
Body Shape ◽  
Ground Truth ◽  
Shape Reconstruction ◽  
Human Motion ◽  
Video Data ◽  
Motion Capture Data ◽  
Optical Motion ◽  
Human Pose ◽  
Optical Motion Capture

Large high-quality datasets of human body shape and kinematics lay the foundation for modelling and simulation approaches in computer vision, computer graphics, and biomechanics. Creating datasets that combine naturalistic recordings with high-accuracy data about ground truth body shape and pose is challenging because different motion recording systems are either optimized for one or the other. We address this issue in our dataset by using different hardware systems to record partially overlapping information and synchronized data that lend themselves to transfer learning. This multimodal dataset contains 9 hours of optical motion capture data, 17 hours of video data from 4 different points of view recorded by stationary and hand-held cameras, and 6.6 hours of inertial measurement units data recorded from 60 female and 30 male actors performing a collection of 21 everyday actions and sports movements. The processed motion capture data is also available as realistic 3D human meshes. We anticipate use of this dataset for research on human pose estimation, action recognition, motion modelling, gait analysis, and body shape reconstruction.

Detecting “DeepFakes” in H.264 Video Data Using Compression Ghost Artifacts

2020 ◽  
Vol 2020 (4) ◽  
pp. 116-1-116-7
Author(s):  
Raphael Antonius Frick ◽  
Sascha Zmudzinski ◽  
Martin Steinebach
Keyword(s):  
Image Forensics ◽  
Video Data ◽  
Experimental Results ◽  
Video Sequences ◽  
The Internet ◽  
Video Content ◽  
High Quality ◽  
The Public

In recent years, the number of forged videos circulating on the Internet has immensely increased. Software and services to create such forgeries have become more and more accessible to the public. In this regard, the risk of malicious use of forged videos has risen. This work proposes an approach based on the Ghost effect knwon from image forensics for detecting forgeries in videos that can replace faces in video sequences or change the mimic of a face. The experimental results show that the proposed approach is able to identify forgery in high-quality encoded video content.

scholarly journals Research on college gymnastics teaching model based on multimedia image and image texture feature analysis

2021 ◽  
Vol 1 (1) ◽  
Author(s):  
Ying Wu ◽  
Jikun Liu
Keyword(s):  
Human Body ◽  
Rapid Development ◽  
Texture Feature ◽  
Texture Features ◽  
Dynamics Simulation ◽  
Image Texture ◽  
Whole Body ◽  
Database Modeling ◽  
Rigid Model ◽  
The Subject

AbstractWith the rapid development of gymnastics technology, novel movements are also emerging. Due to the emergence of various complicated new movements, higher requirements are put forward for college gymnastics teaching. Therefore, it is necessary to combine the multimedia simulation technology to construct the human body rigid model and combine the image texture features to display the simulation image in texture form. In the study, GeBOD morphological database modeling was used to provide the data needed for the modeling of the whole-body human body of the joint and used for dynamics simulation. Simultaneously, in order to analyze and summarize the technical essentials of the innovative action, this experiment compared and analyzed the hem stage of the cross-headstand movement of the subject and the hem stage of the 180° movement. Research shows that the method proposed in this paper has certain practical effects.

scholarly journals Modeling and evaluating beat gestures for social robots

2021 ◽  
Author(s):  
Unai Zabala ◽  
Igor Rodriguez ◽  
José María Martínez-Otzeta ◽  
Elena Lazkano
Keyword(s):  
Motion Capture ◽  
Motion Capture System ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Desirable Feature ◽  
Quantitative Results ◽  
Path Lengths ◽  
End Effectors ◽  
The One ◽  
Made In

AbstractNatural gestures are a desirable feature for a humanoid robot, as they are presumed to elicit a more comfortable interaction in people. With this aim in mind, we present in this paper a system to develop a natural talking gesture generation behavior. A Generative Adversarial Network (GAN) produces novel beat gestures from the data captured from recordings of human talking. The data is obtained without the need for any kind of wearable, as a motion capture system properly estimates the position of the limbs/joints involved in human expressive talking behavior. After testing in a Pepper robot, it is shown that the system is able to generate natural gestures during large talking periods without becoming repetitive. This approach is computationally more demanding than previous work, therefore a comparison is made in order to evaluate the improvements. This comparison is made by calculating some common measures about the end effectors’ trajectories (jerk and path lengths) and complemented by the Fréchet Gesture Distance (FGD) that aims to measure the fidelity of the generated gestures with respect to the provided ones. Results show that the described system is able to learn natural gestures just by observation and improves the one developed with a simpler motion capture system. The quantitative results are sustained by questionnaire based human evaluation.

scholarly journals I. The Croonian Lecture. On the structure and uses of the membrana tympani of the ear

1800 ◽  
Vol 90 ◽  
pp. 1-21 ◽  
Keyword(s):  
Human Body ◽  
Comparative Anatomy ◽  
Large Field ◽  
The Subject ◽  
Muscular Action ◽  
Satisfactory Manner

The subject of inquiry appointed by the Croonian Institution, has been greatly elucidated at different times by ingenious members of this learned Society. A large field, however, still remains open; and, respecting future investigations, I shall have occasion to offer a fresh proof of the aid to be derived from comparative anatomy, in ascertaining the structure of parts which, from their minuteness and situation in the human body, admit with much difficulty of being explored. The principal object of the present lecture is to communicate a discovery of the structure of the membrana tympani; which, in some respects, affords a new and very curious instance of the application of muscular action, and may conduce to account for certain phaenomena in the sense of hearing, in a more satisfactory manner than has hitherto been proposed.

Towards Statistically Provable Geometric 3D Human Pose Recovery

2021 ◽  
Vol 14 (1) ◽  
pp. 246-270
Author(s):  
Jianqiao Wangni ◽  
Dahua Lin ◽  
Ji Liu ◽  
Kostas Daniilidis ◽  
Jianbo Shi
Keyword(s):  
Pose Recovery ◽  
Human Pose

scholarly journals Pembelajaran Mandri Berbasis Video 3GP

2018 ◽  
Vol 16 (2) ◽  
pp. 135-148
Author(s):  
Barnawi Barnawi
Keyword(s):  
Data Analysis ◽  
Learning Model ◽  
Research Field ◽  
Video Data ◽  
Effective Learning ◽  
Model Based ◽  
Research Population ◽  
The Subject ◽  
Simulation Learning ◽  
Self Learning

Abstract: Potency of the high absorption obtained if learning in effective. Effective learning occurs when students are placed as individual active and direct contact with the subject matter. This research aims to reduce the limitations of the tool (a computer or laptop) and maximizing existing facilities (hand phone) with the aim of achieving effective learning that puts students as subjects of learning. This study is a research field for conducting comparative academic performance of two models of learning. The first learning model is simulation learning and the second model is self-learning via mobile facility. Self-learning materials in this research is the material in the form of video 3GP and transferred to the student’s mobile. The research population is 85 students and a sample taken by 70 students. The data in this study is the performance of students from simulation learning model and self- learning model based 3GP video. Data analysis using inferential statistical, namely the t-test. Data analysis was performed after the fulfillment of the requirements for normality of data. The results of hypothesis testing obtained the results as following: The value t count bigger than t table (5.957> 2.025). Thus Ha is received and Ho is rejected (significance below or equal to 0.05 so Ha is received). Means that there are significant differences between simulation learning model and self-learning model based 3GP video. Keywords: Learning Media, 3GP Video.

scholarly journals Product innovation design and its method: From the perspective of embodiment cognition

2021 ◽  
Vol 236 ◽  
pp. 04057
Author(s):  
Shengfang Peng ◽  
Baoying Peng ◽  
Xiaoxuan Li
Keyword(s):  
Cognitive Psychology ◽  
Embodied Cognition ◽  
Human Body ◽  
Product Innovation ◽  
Natural Interaction ◽  
New Approach ◽  
The Subject ◽  
Body Complex ◽  
The Mind ◽  
The Brain

In recent years, embodied cognition has become a new approach in the field of cognitive psychology. The shift in cognitive psychology from a focus on the brain to a focus on the human body，just as from the disembodied cognition to the embodied cognition is valuable for many fields related to cognitive science including product design and its method. With Gibson’s theory of affordances, embodied cognition is a perfect explanation of today’s products guided by the idea of intuitive design and its logic. On the premise of embodied cognition, it is the “Mind-Body complex” that serves as the subject of behavior and interaction, the basis of “natural interaction” in Intelligent age, and the foundation for building a more complete theory of “user experience”. Based on the embodied cognitive, the method of design and its research should put more emphasis on specific tools.

Sign in / Sign up

Export Citation Format

Share Document