search

zc-alexfan / arctic

[CVPR 2023] Official repository for downloading, processing, visualizing, and training models on the ARCTIC dataset.
https://arctic.is.tue.mpg.de
Other
301 stars 18 forks source link

Possible inconsistency in the MoCap labels? #38

Closed heydarshahi closed 7 months ago

heydarshahi commented 7 months ago

Working on the MoCap data, I noticed some labels are not the same for different subjects. An example of this is: The markers on the base of the table correspond to [M_1, M_2, M_5, M_6] for subjects s01 through s04 and [M_5, M_6, M_7, M_8]for subjects s05 and s06.

Is there a part of the data that specifies which labels correspond to which markers? Of course, this might be a problem with my visualization, in which case I'd appreciate it if you could confirm that the labels correspond to the same markers across the subjects.

Thanks! Amin

zc-alexfan commented 7 months ago

Hi @heydarshahi, I don't remember the precise details because the data was captured 2 years ago. But it is possible that it is inconsistent because there are several markersets for the table and during the capture we might have used different names.

I would suggest to check the names of the table markers to see. You can see the names with Mokka by openning the c3d files. See details in doc.

I don't think the relative distances between the table markers will change in the capture because they were glued on the table (at least the ones that are at the top of the table). To verify the markers relative locations are unchanged, you can compute pair-wise distance between markers in different captures and see if the pair-wise distances are the same in all captures.

Hope it helps.