⚡ Dedicated GPU processing pipeline

Upload video
for AI analysis

Turn perspective surveillance footage into calibrated 2D top-down trajectories, entry/exit volumes, and a natural-language scene query model.

Select footage

Drag and drop your camera recording, or browse your computer

Drag & drop your video file here Supports MP4, MKV, MOV, WebM (up to 24 hours / 10 GB)

🔒 High-precision GPU analysis. You'll confirm your processing slot before any charge.

Don't have footage handy?
Explore the live app with sample scenes instead.
Open Live App →

Expected video quality & specs

Follow these recommendations for up to 94% trajectory detection precision

Resolution & framerate 1080p / 15-60 fps

Optimal detection requires 1080p (1920×1080) or 4K at 15–60 FPS. Low-framerate timelapse degrades motion vectors.

Camera elevation & position Elevated & fixed

Mount the camera 3–15 meters above ground, 30°–60° inclination. The camera must remain stationary.

Lens & optical distortion Minimal fisheye

Standard surveillance lenses (2.8–8mm) work out of the box. Extreme fisheye needs optical unwarping.

Ground reference points Visible surface

Clear line of sight to sidewalks, roads, or plaza surfaces helps high-precision 2D calibration.

Clip duration & encoding Up to 24h

Single clips up to 24 hours. H.264 (AVC) or H.265 (HEVC) with constant framerate.