Kinect for Windows v2 sensor offers improved skeletal tracking. The enhanced fidelity of the depth camera, combined with improvements in the software, have led to a number skeletal tracking developments. In addition to now tracking as many as six complete skeletons (compared to two with the original sensor), and tracking 25 joints per person (as compared to 20 with the original sensor), the tracked positions are more anatomically correct and stable—and the range of tracking is broader. This enables and simplifies many scenarios, including more stable avateering, more accurate body position evaluation, crisper interactions, and more bystander involvement in interactive scenarios.
In the above YouTube video posted by Microsoft MVP Josh Blake of InfoStrat, you can see the improvements in skeletal tracking provided by the v2 sensor and the preview SDK 2.0
When asked how the improved skeletal-tracking capabilities can be utilized, Blake responded, “It helps improve several different scenarios. The more accurate anatomical precision is particularly useful in health and rehabilitation apps, as well as for controlling virtual avatars more accurately.” He also finds great potential in the enhanced hand-tracking capabilities, noting that “recognizing the two-finger point pose in addition to the hand open and hand closed poses means we have more options for developing interesting deep interactions.”
Read more about it here.