Camera System for Efficient non-contact Measurement in Distance Medicine

The posture of body segments can be negatively influenced by many diseases of the nervous, visual and musculoskeletal systems. This article outlines a newly designed system and related procedures to record and evaluate anatomical body angles. The system is equipped with two mutually calibrated cameras allowing the evaluation of body movement in two anatomical planes. The hardware part of the camera system and calibration method was designed for practical use in clinical practice. Moreover, the proposed camera system allows for the recording and evaluation of motion data in a home environment or at a safe distance. It enables non-invasive and non-contact measuring of body segments and, therefore, can be used in distance rehabilitation and distance diagnosing. The study also demonstrates the hardware’s performance accelerator based on a human body tracking algorithm. The device utilizes the third party algorithms, such as OpenPose, for the extraction of major body points from selected video frames. Any missing data points are then interpolated through the proposed tracking algorithm. This procedure results in an acceleration of the overall hardware performance.

[1]  Danna Zhou,et al.  d. , 1934, Microbial pathogenesis.

[2]  Jian Li,et al.  Real-time human gesture grading based on OpenPose , 2017, 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).

[3]  C. Castejón,et al.  Analysis and Comparison of Motion Capture Systems for Human Walking , 2016, Experimental Techniques.

[4]  Patrik Kutilek,et al.  Comparison of Methods of Measurement of Head Position in Neurological Practice , 2010 .

[5]  Francesco Amenta,et al.  Telerehabilitation: Review of the State-of-the-Art and Areas of Application , 2017, JMIR rehabilitation and assistive technologies.

[6]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Yaser Sheikh,et al.  OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  J. Hozman,et al.  Determining the Position of Head and Shoulders in Neurological Practice with the use of Cameras , 2011 .

[9]  J. Hozman,et al.  Identification of the Position of Head and Shoulders in Neurological Practice with the Use of Two Cameras , 2011 .

[10]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[11]  J. L. Roux.  An Introduction to the Kalman Filter , 2003 .

[12]  K. Moran,et al.  Clinical and biomechanical outcomes of rehabilitation targeting intersegmental control in athletic groin pain: prospective cohort of 205 patients , 2018, British Journal of Sports Medicine.

[13]  Tathagata Ray,et al.  Human Gait Analysis Using OpenPose , 2019, 2019 Fifth International Conference on Image Information Processing (ICIIP).

[14]  Azra Fetic,et al.  The procedure of a camera calibration using Camera Calibration Toolbox for MATLAB , 2012, 2012 Proceedings of the 35th International Convention MIPRO.

[15]  Takashi Sato,et al.  Interpolation-Based Object Detection Using Motion Vectors for Embedded Real-time Tracking Systems , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).