Camera System Requirements
Last updated
Was this helpful?
Theia Axiom - v2025
Last updated
Was this helpful?
This section describes the basic camera system requirements for recording data to be used with Theia3D. See for additional recommendations and principles to follow when recording video data for Theia3D.
Theia3D requires a minimum of six cameras for tracking; however, we recommend a minimum of eight cameras for most capture volumes. The number of cameras required will increase with movement complexity, capture volume size, capture volume complexity, and the number of people to be tracked. The field of view and joint visibility requirements outlined below are the best guides when determining the number of cameras required for a specific capture volume.
The cameras must capture synchronous videos with identical start times and durations to be used with Theia3D.
Person identification and tracking perform best when the people of interest are fully visible and cover a large percentage of the fields of view of the cameras. In most applications a height of 500 pixels is adequate - this requirement may increase based on camera setup, focus, and image quality. It is important that the people of interest are in focus and clearly visible.
Ideal tracking conditions are achieved when all joints are visible in all cameras; however, this is rarely attainable due to occlusions from other limbs, people, and the environment. At a minimum, each joint must be visible in at least three cameras. When setting up the cameras it is important to position and orient the cameras in a way that minimizes occlusions while simultaneously providing views of the subject(s) from varying angles to improve joint depth and position calculations. For example, a purely sagittal view results in several occlusions and poor tracking from that view but provides useful information for identify the depth of joints tracked in a more frontal view.
Theia3D does not require people to wear specific clothing to be tracked. However, loose or baggy clothing may result in lower quality tracking. As a general rule, if you can easily identify joints in the camera images, then Theia3D can infer the joint positions as well.