Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


main.pdf (1.04 MB)

ETD Abstract Container

Abstract Header

Fusing Joint Information from Multiple Kinect Sensors to Detect Errors in Exercises

VANKAMAMIDI, SRIHARSHA
http://orcid.org/0000-0002-3043-5916
http://rave.ohiolink.edu/etdc/view?acc_num=akron1477921964956213

Abstract Details

2016, Master of Science in Engineering, University of Akron, Electrical Engineering.
The Kinect camera is a versatile tool that can be effectively used to recognize and correct errors in exercise performance using the 3D joint location data. In several exercises that involve complex sequences of motion, a single camera cannot track all the joint locations because of occlusions. A natural solution is to utilize multiple cameras. However, two challenges must be addressed before multiple cameras can be utilized. First, the joint data from each camera uses the location of the camera as the reference. Second, although the Kinect cameras are supposed to collect data at 30 fps, there is variability in the period of each camera. We propose a solution to address these challenges. We utilize Singular Value Decomposition to rotate and translate the joint data to a single reference point. We interpolate the data from multiple cameras to a common time base. The results demonstrate the effectiveness of the approach.
SHIVAKUMAR SHASTRY (Advisor)
8 p.
Computer Engineering

Recommended Citations

Citations

  • VANKAMAMIDI, S. (2016). Fusing Joint Information from Multiple Kinect Sensors to Detect Errors in Exercises [Master's thesis, University of Akron]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=akron1477921964956213

    APA Style (7th edition)

  • VANKAMAMIDI, SRIHARSHA. Fusing Joint Information from Multiple Kinect Sensors to Detect Errors in Exercises . 2016. University of Akron, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=akron1477921964956213.

    MLA Style (8th edition)

  • VANKAMAMIDI, SRIHARSHA. "Fusing Joint Information from Multiple Kinect Sensors to Detect Errors in Exercises ." Master's thesis, University of Akron, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=akron1477921964956213

    Chicago Manual of Style (17th edition)

akron1477921964956213
348
© 2016, some rights reserved.Creative Commons License Fusing Joint Information from Multiple Kinect Sensors to Detect Errors in Exercises by SRIHARSHA VANKAMAMIDI is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License. Based on a work at etd.ohiolink.edu.
This open access ETD is published by University of Akron and OhioLINK.