×

Method and apparatus for three-dimensional, textured models from plural video images

  • US 5,511,153 A
  • Filed: 01/18/1994
  • Issued: 04/23/1996
  • Est. Priority Date: 01/18/1994
  • Status: Expired due to Term
First Claim
Patent Images

1. A method of generating, from a multiple-frame video recording of an object, geometrically specified digital pixelmaps that collectively represent a three-dimensional model of the object, the method comprising the steps of:

  • a. digitizing each frame of the video recording into a pixelmap;

    b. selecting at least seven object features from a first digitized video frame;

    c. tracking the features among a plurality of digitized video frames to determine changes in the relative distances therebetween;

    d. based on changes in the relative distances, recursively estimating a plurality of unknown parameters including camera focal length, camera translation, camera rotation, and spatial locations of the tracked features;

    e. based on the estimated parameters, defining spatial vectors that specify the spatial locations of object details depicted by each pixel of a plurality of digitized video frames; and

    f. based on the spatial vectors, mapping each pixel from the plurality of digitized video frames to pixel locations within a plurality of final pixelmaps that collectively define a digital representation of the object.

View all claims
  • 4 Assignments
Timeline View
Assignment View
    ×
    ×