KickTrimmer Lab · Ball-Speed Video Twin

This Space acts as a desktop twin of the KickTrimmer mobile app: load a football clip, detect the kick, and estimate the ball speed frame-by-frame. It previews future ball rings color-coded by hypothetical impact velocity as the ball travels toward the goal, letting you experiment with FX settings before shipping them to the phone build.

⚠️ Work in progress: we are still closing the gap with the mobile feature set (automatic horizon & goal finding, diagonal speed correction, etc.), so the numbers you see here are prototypes—not final certified speeds.

SAM2 API

Programmatic KickTrimmer Pipeline

Submitting a video here runs the same automated workflow as the Interactive UI:

1. Upload the raw MP4.
2. YOLO13 detects and tracks the ball to get the first kick estimate.
3. SAM2 tracks the ball around that kick window. If SAM2's kick disagrees with YOLO's, it automatically re-tracks the entire clip for better accuracy.
4. YOLO13 detects the player on the SAM2 kick frame, then SAM2 propagates the player masks around that window.
5. The Space renders a default cutout video and returns it together with the processing log below.

Optional annotations

You can still send helper points via JSON:

{
    "annotations": [
        {"object_id": 1, "frame": 0, "x": 363, "y": 631, "label": "positive"},
        {"object_id": 1, "frame": 187, "x": 296, "y": 485, "label": "positive"},
        {"object_id": 2, "frame": 187, "x": 296, "y": 412, "label": "positive"}
    ]
}

• Object 1 = ball, Object 2 = player. Use timestamps when possible; the API will reconcile timestamps and frame indices for you.