Share via

Skeleton Tracking With Multiple Kinect Sensors

  • Article

Kinect for Windows 1.5, 1.6, 1.7, 1.8

Skeleton Tracking With Multiple Kinect Sensors

The Kinect for Windows SDK supports up to 4 simultaneous Kinect for Windows Sensors for skeleton tracking. This support is available through both the native and managed versions of the Skeleton Tracking API.

Practical Considerations for Skeletal Tracking using Multiple Sensors

The infrared emitter of a Kinect sensor projects a pattern of infrared light. This pattern of light is used to calculate the depth of the people in the field of view allowing the recognition of different people and different body parts. If you use more than one Kinect sensor to illuminate the target area, you may notice a reduction in the accuracy and precision of skeletal tracking due to interference between the infrared light sources. To reduce the possibility of interference, it is recommended that no more than one Kinect sensor (or infrared light source) points to a field of view where skeletal tracking is being done. Also recall that Skeleton Tracking works best when the tracked user is facing the sensor.

The Skeleton Tracking API does not synchronize skeleton IDs across multiple sensors. For example, Sensor 1 may assign skeleton tracking ID 1 to user A, and skeleton tracking ID 2 to user B. There is no guarantee that user A is also assigned skeleton tracking ID 1 by sensor B, or even that sensor B is tracking user A.