Bounding Boxes (2D & 3D)

Bounding box annotation is one of the most common techniques in computer vision, used to draw rectangular boxes around objects of interest in an image or video.


🔹 Key Features:

  • Defined by two points: top-left and bottom-right corners.
  • Represents the location and size of an object.
  • Simple and efficient, but less precise for irregular shapes.

🔹 Use Cases:

Object detection (vehicles, pedestrians, animals)
Face detection in security or social apps
Retail: Product localization on shelves
Medical AI: Identifying regions of interest in scans