Kinect v2 skeleton datasets of simulated abnormal gaits
- Citation Author(s):
-
Kooksung Jun
(Gwangju Institute of Science and Technology)
Yongwoo Lee
(Gwangju Institute of Science and Technology)
Sanghyub Lee
(Gwangju Institute of Science and Technology)
Deok-Won Lee
(Gwangju Institute of Science and Technology)
Mun Sang Kim
(Gwangju Institute of Science and Technology)
- Submitted by:
- Kooksung Jun
- Last updated:
- DOI:
- 10.21227/21wx-kh75
- Data Format:
- Links:
1290 views
- Categories:
- Keywords:
Abstract
Skeleton datasets for Normal, Antalgic, Stiff legged, Lurching, Steppage, and Trendelenburg gaits.
Instructions:
Data Quantity
10 people x 6 gaits x 120 instances
Data Form
time, 0, joint0_x, joint0_y, joint0_z, 1, joint1_x, joint1_y, joint1_z, ... , joint24_x, joint24_y, joint24_z
The joint numbers can be found in Reference.
Data Collection
We collected datasets by using multiple Kinect system (6 Kinect v2). We calibrated the coordinate systems of all sensors by using ArUco markers. For more information, please refer to the below reference or contact me.
Reference
K. Jun, Y. Lee, S. Lee, D. Lee and M. S. Kim, "Pathological Gait Classification Using Kinect v2 and Gated Recurrent Neural Networks," in IEEE Access, vol. 8, pp. 139881-139891, 2020, doi: 10.1109/ACCESS.2020.3013029.
