Tracking people through KinectV2
The people tracking task is made thanks to both KinectV2 skeleton extraction and pedestrian detection through laser information (not yet implemented).
We use the KinectV2 to take advantage of its API by getting information like general human position and orientation. Moreover extracting the general skeleton gives us information about arm position, head orientation that can be exploited form security purpose and deeper Human Robot Interaction.
We intend to fusethe skeleton general position information with pedestrian detection through laser. Such combined information ensure more reactive robot behavior in case of partial loose of squeleton information.
Moreorver, the Kinectv2 offers HD camera that is used for Human recognition and identification