Skip to content
Free public beta until December 4, 2026: every course is open, no card needed. After that, the first chapter of each course stays free and full access is a one-time $39 ($19 for up to 100 founding members chosen for helpful feedback). Your progress is kept. How the beta works

multi-object tracking (MOT)

Maintaining a consistent identity for each of several tracked objects across a video, including through brief occlusion.

Multi-object tracking (MOT) maintains a consistent identity for each of several simultaneously tracked objects across a video sequence, solving a frame-to-frame assignment problem between new detections and existing tracks (often combined with per-track Kalman filtering) and reasoning about what to do with a track that briefly disappears behind an occlusion before it reappears.

Examples

  • MOT keeps the same identity on a pedestrian who walks briefly behind a parked van and reappears a few frames later, rather than assigning them a brand-new ID.

Read the full section →
Graph settings

Calculator