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

perception pipeline

The five-stage spine -- image, preprocess, features, model, prediction -- that any vision system can be placed on.

The perception pipeline names the five stages a computer-vision system runs through in order: acquiring an image, preprocessing it, extracting features, running a model over those features, and producing a prediction. Any individual technique this course teaches -- a corner detector, a CNN, a tracker -- can be placed at the specific stage of this pipeline it belongs to.

Examples

  • A face-unlock system acquires a frame, preprocesses it, extracts facial features, runs a matching model, and outputs a match/no-match prediction -- all five perception-pipeline stages in order.

Read the full section →
Graph settings

Calculator