A Survey on 3D object Detection.

less than 1 minute read


  • gray scale matching:

    the pixel distance must be computed as a function of both pixel position and pixel intensity.

  • gradient matching:

    Another way to be robust to illumination changes. The alternative is to use correlation.

  • Large modelbase

  • Feature based model.

    match between object feature and image features.

  • Interpretation Trees.

    The search is through a tree. Each node in the tree represents a set of matches. Root node represents empty set. Each other node is the union of the matches in the parent node and one additional match.

  • Hypothesized and Test

    This is used for generating a hypothesis about the projection from the object coordinate frame to the image frame.

    The hypothesis can b obtained by pose consistency, pose clustering, or by using invariants.