Calibration: 5 second rule
We recommend you start each recording session with the actor striking a “T pose” within the first five seconds of your video.
That’s because, for best results, our AI will attempt to detect the entirety of the actor’s body in clear view of a full frame within the first five seconds of your video. It does so to establish a clear and confident baseline signal from which it can better interpret the motion that follows.
In the absence of a clear baseline signal within the first five seconds of your video, your results may suffer significantly. However, because you may also get results that are perfectly fine, we will still process your video. To be sure you understand the risk, in those cases, we will display a warning that ouir results come with a “bad calibration.”
Should the actor be wearing specific clothing?
No specific clothing is required.
As a general rule, when your recorded content features low contrast or low lighting, we recommend more fitted, high contrast clothing, for better results.
Does the actor’s entire body have to be visible?
Avoid having any part of the body outside the frame of the video – especially joints, including hands and feet, and the head. If that happens, our AI will adjust its output to ‘force’ the body back into the frame. As a consequence, in your results, you will likely see violent snaps and non-sensical movement of those limbs or other body parts that are outside the frame.
Simply put, the more we see in the video, the more accurate we get. So you want to maximize the visibility of the actor’s body in the video, especially with respect to the specific joints and limbs that represent the motion you want to capture. Always choose your angle with that in mind. Here are some situations to consider:
- Body obscured by body rotation: Our AI reconstructs the position of joints and entire limbs that are obscured by the actor’s own body. If you are not happy with your results, adjust your camera angle to test a different body rotation relative to the camera. Always try to maximize the visibility of body parts that engage in the most ‘unexpected’ (statistically implausible) pose or motion.
- Body obscured by other objects: Avoid having any part of the body obscured by other objects. Our AI reconstructs the position of joints and entire limbs that are obscured that way, but the longer that state persists, and the more of the body is affected, the more likely it becomes that the AI will produce results that are statistically plausible within the context of the actor’s movements, rather than loyal to what the actor actually does.
How many people can I record in the same video?
At this time, we track motion for one individual at a time. This means that you should avoid having more than one person in the frame at any point, even for a short time or inadvertently. If you do, our AI may significantly alter its results to reconcile conflicting data. As a consequence, in your results, you will likely see violent snaps and non-sensical movement.
In the future, we will be adding the ability to separately capture and track motion of multiple actors simultaneously.
Can I record content indoors and outdoors?
Yes absolutely. You can shoot videos in any environment, and that includes indoors and outdoors — at home, in a studio, in the streets or in the wild.
Are there any restrictions around the distance between the actor and the camera?
There are no specific physical distance (or proximity) requirements. As a general rule, you should aim to fill out as much of the frame as possible.
If you are recording from a larger distance, we recommend, that the actor takes up no less than 35% of the height of the frame.
The greater the distance from the actor (ie the smaller the actor is in the frame), the more you should insist on good visibility, lighting and contrast.
What happens if I have multiple people in the frame? Can I choose which person we track?
We recommend you don’t use footage that involves multiple people in the frame, because you can’t at this time choose the person you track.
However, you may choose to use footage where additional people appear solely before you start the T Pose calibration. However, you should note that the risk of detection failure is generally increased, so we recommend that you avoid those situations.