Difference between revisions of "Calibration Definition AI"
From iPi Docs
(Created page with "Calibration is a process of computing accurate camera positions and orientations from a video. This step is essential and required for multi-camera system setup. Calibration...") |
|||
| Line 2: | Line 2: | ||
Calibration can be done by user waving a small glowing object called ''marker'' (for color/color+depth cameras). Novel AI-based pose estimation algorithms allow to use AI-detected joint positions instead of glowing object (flashlight), that makes the process simpler. | Calibration can be done by user waving a small glowing object called ''marker'' (for color/color+depth cameras). Novel AI-based pose estimation algorithms allow to use AI-detected joint positions instead of glowing object (flashlight), that makes the process simpler. | ||
| + | {{Note|This feature requires Nvidia RTX video card. Please refer to detailed [[AI-based_Tracking#Introduction|System Requirements]]}} | ||
{{Important|Once you calibrated the camera system, you should not move your cameras for subsequent video shoots. If you move at least one camera, you need to perform calibration again.}} | {{Important|Once you calibrated the camera system, you should not move your cameras for subsequent video shoots. If you move at least one camera, you need to perform calibration again.}} | ||
{{Tip|We recommend to run calibration twice - before and after capture session. If any camera was moved during capture session, calibration made after the session can give you correct camera positions.}} | {{Tip|We recommend to run calibration twice - before and after capture session. If any camera was moved during capture session, calibration made after the session can give you correct camera positions.}} | ||
Revision as of 13:04, 31 October 2024
Calibration is a process of computing accurate camera positions and orientations from a video. This step is essential and required for multi-camera system setup.
Calibration can be done by user waving a small glowing object called marker (for color/color+depth cameras). Novel AI-based pose estimation algorithms allow to use AI-detected joint positions instead of glowing object (flashlight), that makes the process simpler.
