Landmark Tracking
Also known as: keypoint tracking, joint tracking
Landmark tracking follows the position of each detected body keypoint across consecutive video frames. This creates a time-series trajectory for every joint that enables timing and velocity measurements.
Pose estimation finds where joints are in a single frame; landmark tracking connects those positions over time to produce trajectories. From trajectories you can derive velocities, accelerations, angles at specific moments (like impact), and sequencing relationships between body segments. Tracking errors — where a joint jumps between frames — are a known challenge and are handled by filtering algorithms. Any metric derived from a noisy trajectory is labeled with lower confidence or flagged as an estimate.
You don't need to analyze trajectories directly. Just check the final skeleton overlay for obvious drifting joints — the system automatically handles the trajectory math behind the scenes.
In Motion Lab's trajectory panel, look for joints that show two distinct position clusters across the swing. This bifurcation pattern often indicates a genuine position change (like early wrist extension) rather than a tracking error and is worth investigating further.
Example
Landmark tracking follows the lead wrist across 40 frames of a golf downswing, computing peak wrist speed and the exact frame where it reaches maximum extension.
How it shows up on video
Play the video with the skeleton overlay at reduced speed — landmark tracking is visible as the smooth (or not-so-smooth) path each joint follows across frames. Abrupt jumps indicate tracking errors that will corrupt derived metrics.
Common mistakes
- Assuming all joints track equally well. The wrist and elbow are significantly harder to track than the hip or shoulder due to their speed and size.
- Using a metric derived from a noisy trajectory without checking the trajectory plot first.
- Confusing a tracking jump with a real movement — if a landmark teleports 15 cm in one frame, it is almost certainly an error.
- Not understanding that velocity and timing metrics are more sensitive to tracking errors than position metrics. A small position error becomes a large velocity error when differentiated over time.
In SwingVantage Motion Lab
Motion Lab plots each landmark's trajectory as a curve in the timeline panel. You can select any joint to see its position over time, and the system highlights frames where tracking confidence dropped below threshold.
Related terms
- Pose EstimationPose estimation is the computer-vision process that detects the positions of major body joints (keypoints) in each video frame. This produces the skeleton that SwingVantage uses to measure angles and movement patterns.
- Skeleton OverlayA skeleton overlay draws your detected body joints, and the lines connecting them, over your video. It shows exactly what the system tracked.
- Kinematic ChainThe kinematic chain is the sequence of body segments, from ground to tip, that pass force and speed through a swing. Each segment's energy amplifies the next.
- Movement SequencingMovement sequencing is the timed order in which body segments accelerate and decelerate through a swing — correct sequencing multiplies speed; incorrect sequencing bleeds it.
Put this into your swing
SwingVantage can spot this in your own swing — free to start.