Glossary
Bounding box
Definition
A bounding box is the smallest axis-aligned rectangle that encloses a detected object, stored as pixel coordinates — most often (x, y, width, height) or two corners. In detection it is paired with a confidence score, and it is the region a downstream stage acts on: to blur a face, you blur the pixels inside its box.
01
Why it matters
The box is the interface between detection and redaction. Its coordinates tell the blurring stage exactly which pixels to cover, and a track id links the same box across video frames so coverage does not flicker as a subject moves.
02
How Firsthand handles it
Firsthand returns bounding boxes with confidence and track ids for every detected face, plate, and screen, and can deliver them as a per-frame sidecar alongside the anonymized footage.
Related terms