3D Reconstruction of gait cycles

Dataset (zip file 1.4 GB)

In the uploaded data set you will find 3D reconstructions of two gait cycles from two different test subjects. The associated anthropometric measurements (i.e. limb segment lengths) can be found in the excel file.

There exist 20 gait cycles recorded over two different days for each test subject and there are 16 subjects in total. However, due to the huge amount of data only a few samples has been uploaded. All the data would be available on request.

Joint angles and joint positions estimated using a marker based motion capture system can also be available by request.

For more information regarding the setup, please read one of the following journal articles:

  1. Sandau M, Applications of Markerless Motion Capture in Gait Recognition, Danish Medical Journal, Feb 2016
  2. Sandau M, Heimbürger R V, Jensen KE, Moeslund T B, Aanæs H, Alkjær T, Simonsen E B., Reliable gait recognition using 3D reconstructions and random forests -An anthropometric approach, Journal of Forensic Sciences, 2014, In press
  3. Sandau M, Koblauch H, Moeslund T B, Aanæs H, Alkjær T, Simonsen E B. 2014. Markerless motion capture can provide reliable 3D gait kinematics in the sagittal and frontal plane. Journal of Medical Engineering & Physics, 2014, 36(9): 1168-1175.

Please email Martin Sandau by msc.22@hotmail.com for further information and requests.

Best regards
Dr. Martin Sandau