Tracker

Tracking is a technique that involves analyzing the motion of an image over time. Silhouette provides multiple options for tracking: Point, Planar, Mocha, Flow, Object and Syntheyes (via the 3D Scene node).

• Point: Track one, two or four track points.

• Planar: Tracks several points (corners, edges and ridges) to define a plane.

• Mocha: Provides 2D transformation data by tracking planes rather than points.

• Flow: Uses optical flow to track a shape’s points.

• Object: Detects and tracks faces or license plates.

• Syntheyes: 3D tracking with SynthEyes.

• Head Track ML: Create and track 3D head meshes.

Mocha Tracker

Mocha tracking technology provides 2D transformation data by tracking planes rather than points.

Planar Tracker

Silhouette’s Planar Tracker tracks several points (corners, edges and ridges) on the image while automatically handling partial occlusions of the tracked object, producing excellent results even with textureless objects.

Flow Tracker

The Flow tracker uses optical flow to track a shape’s points.

Point Tracker

The Point tracker uses trackers which are placed on distinguishable image features. It offers two modes: Point Track ML and Classic. Point Track ML leverages machine learning to maintain tracking even through occlusion or when the object moves off-screen, while Classic mode gives you complete manual control.

SynthEyes Tracker

The 3D Scene node provides an environment where you can 3D track with SynthEyes. Select tracked 3D points, solve them into a plane, and place cards in 3D space.

Head Track ML

Automatically creates a 3D head mesh and tracks facial shape, pose, and expressions over time. When used with the Unwrap and Rewrap nodes, it enables stable, face-aware beauty effects.

Tracker Features

• Planar tracking using either Mocha or Silhouette’s Planar tracker

• Planar trackers provide automatic, markerless motion analysis and tracking

• Planar tracker tracks corners, edges or ridges

• Track multiple planes simultaneously

• Machine learning point tracker maintains tracking even through occlusion or when the object moves off-screen

• Flow tracker uses optical flow to track a shape’s points

• Object tracker detects and tracks faces or license plates

• Unlimited Point trackers for manual precision

• Match Moving or Stabilization

• Pre-processing filters for problematic shots include: Blur, Sharpen, Contrast, Gamma, De-Noise and Remove Flicker will increase tracker accuracy for problematic images

• Post-processing of point tracking data to include: Average, Smooth and Merge

• Tracker export to popular formats

SynthEyes Tracker

• Use cards to Insert, Match Move and Stabilize in the Transform node

• Stabilize and Unproject directly in the Viewer using cards

• Convert 3D trackers into 2D point trackers

Head Track ML

• Creates and tracks 3D head meshes

• Place anchor points in areas that require manual positioning or more precise stabilization.