Geek Answers Handbook

Is it possible to save the user's skeleton and face data for recognition purposes?

I would like to be able to track people who enter and leave the premises. Basically, when a user approaches Kinect, they will store their facial and skeletal data. After that, this data will be deleted. At the moment, I'm just wondering if this is possible or not with the Microsoft SDK. I have seen a Kinect video / demo that can track people, but my goal is to identify them uniquely . Any information would be greatly appreciated.

+4
source share
2 answers

Yes, you can save skeleton and face data ... but for what you are doing, it looks like you want to save this for the session only. Since as soon as they leave, the data will be deleted, you can use the skeleton tracking identifier ... or indexes

SkeletonFrame sf = e.SkeletonFrame; //check which skeletons in array are active and // use that array indexes for player index SkeletonData player1 = sf.Skeletons[playerIndex1]; SkeletonData player2 = sf.Skeletons[playerIndex2];

You can see my answer to Kinect User Discovery for more information.

+1
source

You may be able to store skeletal data, but as far as I know, Kinect does not have the permission necessary for face recognition (especially if you are going to sit in the corner of the room).

There are commercial 3D face recognition solutions - Cybula , but these solutions usually cost thousands.

I would not know how accurate skeletal data would be - if all your users are the same, then you may have several problems. You will need to develop measurement tolerance and make sure that none of your users are inside this (which, if it is for the general public, could be a problem).

+1
source

More articles:


All Articles