The face tracking model uses the projected linear 3D model for a video camera input. It does the following:
Tracks visual features from the previous frame to the current frames
Aligns a 2D shape to track features
Computes a 3D point cloud data from depth measurement
Minimizes the loss function
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month, and much more.