scholarly journals Evaluation of 3D markerless motion capture accuracy using OpenPose with multiple video cameras

2019 ◽  
Author(s):  
Nobuyasu Nakano ◽  
Tetsuro Sakura ◽  
Kazuhiro Ueda ◽  
Leon Omura ◽  
Arata Kimura ◽  
...  
Keyword(s):  
Motion Capture ◽  
Human Movement ◽  
Absolute Error ◽  
Motor Tasks ◽  
3D Pose Estimation ◽  
Video Cameras ◽  
Markerless Motion Capture ◽  
Optical Motion ◽  
Optical Motion Capture ◽  
Capture Technique

AbstractThere is a need within human movement sciences for a markerless motion capture system, which is easy to use and suffciently accurate to evaluate motor performance. This study aims to develop a 3D markerless motion capture technique, using OpenPose with multiple synchronized video cameras, and examine its accuracy in comparison with optical marker-based motion capture. Participants performed three motor tasks (walking, countermovement jumping, and ball throwing), with these movements measured using both marker-based optical motion capture and OpenPose-based markerless motion capture. The differences in corresponding joint positions, estimated from the two different methods throughout the analysis, were presented as a mean absolute error (MAE). The results demonstrated that, qualitatively, 3D pose estimation using markerless motion capture could correctly reproduce the movements of participants. Quantitatively, of all the mean absolute errors calculated, approximately 47% were less than 20 mm and 80% were less than 30 mm. However, 10% were greater than 40 mm. The primary reason for mean absolute errors exceeding 40mm was that OpenPose failed to track the participant’s pose in 2D images owing to failures, such as recognition of an object as a human body segment, or replacing one segment with another depending on the image of each frame. In conclusion, this study demonstrates that, if an algorithm that corrects all apparently wrong tracking can be incorporated into the system, OpenPose-based markerless motion capture can be used for human movement science with an accuracy of 30mm or less.

scholarly journals Use of computer innovative technologies in improving the dartsmen training

2020 ◽  
Vol 26 ◽  
pp. 00061
Author(s):  
Elina Makarova ◽  
Vladislav Dubatovkin ◽  
Nataliya Berezinskaya ◽  
Lyudmila Barkhatova ◽  
Elena Oleynik
Keyword(s):  
Motion Capture ◽  
Body Parts ◽  
Visual Material ◽  
Video Cameras ◽  
Dart Throwing ◽  
Optical Motion ◽  
Optical Motion Capture ◽  
Effective Use ◽  
Near Future ◽  
Motion Capture Systems

The research is focused on studying the possibility of effective use of the dart grip system, the work of the athlete’s hand, to prepare the dartsman for competitions using the MOSAR complex. The experiment uses optical motion capture systems, a set of video cameras, led parameter sensors, and devices that allow to record the movement of body parts and a dart. This method of training and controlling dart throwing can serve as educational and visual material for training future athletes. The use of such motion capture systems in the near future may become one of the main aspects of training, both beginners and professionals, in many sports.

DEVELOPMENT OF MOTION CAPTURE SYSTEM USING DUAL VIDEO CAMERAS FOR THE GAIT DESIGN OF A BIPED ROBOT

2011 ◽  
Vol 08 (02) ◽  
pp. 275-299 ◽  
Author(s):  
JUNG-YUP KIM ◽  
YOUNG-SEOG KIM
Keyword(s):  
Motion Capture ◽  
Human Walking ◽  
Human Gait ◽  
Motion Capture System ◽  
System Calibration ◽  
Walking Gait ◽  
Video Cameras ◽  
Optical Motion ◽  
Optical Motion Capture ◽  
Motion Capture Systems

This paper, describes the development of a motion capture system with novel features for biped robots. In general, motion capture is effectively utilized in the field of computer animation. In the field of humanoid robotics, the number of studies attempting to design human-like gaits by using expensive optical motion capture systems is increasing. The optical motion capture systems used in these studies have involved a large number of cameras because such systems use small-sized ball markers; hence the position accuracy of the markers and the system calibration are very significant. However, since the human walking gait is a simple periodic motion rather than a complex motion, we have developed a specialized motion capture system for this study using dual video cameras and large band-type markers without high-level system calibration in order to capture the human walking gait. In addition to its lower complexity, the proposed capture method requires only a low-cost system and has high space efficiency. An image processing algorithm is also proposed for deriving the human gait data. Finally, we verify the reliability and accuracy of our system by comparing a zero moment point (ZMP) trajectory calculated by the motion captured data with a ZMP trajectory measured by foot force sensors.

scholarly journals Concurrent assessment of gait kinematics using marker-based and markerless motion capture

2020 ◽  
Author(s):  
Robert Kanko ◽  
Elise Laende ◽  
Elysia Davis ◽  
W. Scott Selbie ◽  
Kevin J. Deluzio
Keyword(s):  
Motion Capture ◽  
Lower Limb ◽  
Video Data ◽  
Motion Capture System ◽  
Kinematic Data ◽  
Markerless Motion Capture ◽  
Common Marker ◽  
Optical Motion ◽  
Optical Motion Capture ◽  
Motion Capture Systems

AbstractKinematic analysis is a useful and widespread tool used in research and clinical biomechanics for the estimation of human pose and the quantification of human movement. Common marker-based optical motion capture systems are expensive, time intensive, and require highly trained operators to obtain kinematic data. Markerless motion capture systems offer an alternative method for the measurement of kinematic data with several practical benefits. This work compared the kinematics of human gait measured using a deep learning algorithm-based markerless motion capture system to those of a common marker-based motion capture system. Thirty healthy adult participants walked on a treadmill while data were simultaneously recorded using eight video cameras (markerless) and seven infrared optical motion capture cameras (marker-based). Video data were processed using markerless motion capture software, marker-based data were processed using marker-based capture software, and both sets of data were compared. The average root mean square distance (RMSD) between corresponding joints was less than 3 cm for all joints except the hip, which was 4.1 cm. Lower limb segment angles indicated pose estimates from both systems were very similar, with RMSD of less than 6° for all segment angles except those that represent rotations about the long axis of the segment. Lower limb joint angles captured similar patterns for flexion/extension at all joints, ab/adduction at the knee and hip, and toe-in/toe-out at the ankle. These findings demonstrate markerless motion capture can measure similar 3D kinematics to those from marker-based systems.

Tracking of Markers for 2D and 3D Gait Analysis Using Home Video Cameras

2013 ◽  
Vol 4 (3) ◽  
pp. 36-52 ◽  
Author(s):  
Sandro Mihradi ◽  
Ferryanto ◽  
Tatacipta Dirgantara ◽  
Andi I. Mahyuddin
Keyword(s):  
Gait Analysis ◽  
Motion Capture ◽  
Motion Capture System ◽  
Distance Method ◽  
Home Video ◽  
Video Cameras ◽  
Optical Motion ◽  
Spatio Temporal ◽  
Optical Motion Capture ◽  
2D And 3D

This work presents the development of an affordable optical motion-capture system which uses home video cameras for 2D and 3D gait analysis. The 2D gait analyzer system consists of one camcorder and one PC while the 3D gait analyzer system uses two camcorders, a flash and two PCs. Both systems make use of 25 fps camcorder, LED markers and technical computing software to track motions of markers attached to human body during walking. In the experiment for 3D gait analyzer system, the two cameras are synchronized by using flash. The recorded videos for both systems are extracted into frames and then converted into binary images, and bridge morphological operation is applied for unconnected pixel to facilitate marker detection process. Least distance method is then employed to track the markers motions, and 3D Direct Linear Transformation is used to reconstruct 3D markers positions. The correlation between length in pixel and in the real world resulted from calibration process is used to reconstruct 2D markers positions. To evaluate the reliability of the 2D and 3D optical motion-capture system developed in the present work, spatio-temporal and kinematics parameters calculated from the obtained markers positions are qualitatively compared with the ones from literature, and the results show good compatibility.

Measuring human movement for biomechanical applications using markerless motion capture

2006 ◽  
Author(s):  
Lars Mündermann ◽  
Stefano Corazza ◽  
Ajit M. Chaudhari ◽  
Thomas P. Andriacchi ◽  
Aravind Sundaresan ◽  
...  
Keyword(s):  
Motion Capture ◽  
Human Movement ◽  
Markerless Motion Capture

scholarly journals Gap Reconstruction in Optical Motion Capture Sequences Using Neural Networks

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6115
Author(s):  
Przemysław Skurowski ◽  
Magdalena Pawlyta
Keyword(s):  
Neural Networks ◽  
Motion Capture ◽  
Matrix Completion ◽  
Input Sequence ◽  
Feedforward Neural Networks ◽  
Network Architectures ◽  
Motion Data ◽  
Optical Motion ◽  
Body Kinematic ◽  
Optical Motion Capture

Optical motion capture is a mature contemporary technique for the acquisition of motion data; alas, it is non-error-free. Due to technical limitations and occlusions of markers, gaps might occur in such recordings. The article reviews various neural network architectures applied to the gap-filling problem in motion capture sequences within the FBM framework providing a representation of body kinematic structure. The results are compared with interpolation and matrix completion methods. We found out that, for longer sequences, simple linear feedforward neural networks can outperform the other, sophisticated architectures, but these outcomes might be affected by the small amount of data availabe for training. We were also able to identify that the acceleration and monotonicity of input sequence are the parameters that have a notable impact on the obtained results.

Sign in / Sign up

Export Citation Format

Share Document