Method and apparatus for three-dimensional, textured models from plural video images
First Claim
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.
4 Assignments
0 Petitions
Accused Products
Abstract
A method and apparatus for generating three-dimensional, textured computer models from a series of video images of an object is disclosed. The invention operates by tracking a selected group of object features through a series of image frames and, based on changes in their relative positions, estimates parameters specifying camera focal length, translation and rotation, and the positions of the tracked features in the camera reference frame. After segmentation of the images into two-dimensional bounded regions that each correspond to a discrete surface component of the actual object, the texture contained in the various video frames is applied to these regions to produce a final three-dimensional model that is both geometrically and photometrically specified.
167 Citations
26 Claims
-
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 Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. 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. tracking a plurality of features among a plurality of digitized video frames to determine changes in the relative distances therebetween; c. based on changes in the relative distances, estimating a plurality of unknown parameters including camera translation, camera rotation, and spatial locations of the tracked features; d. segmenting the object into bounded, two-dimensional object regions having contours; e. defining final pixelmaps whose contours match those of the object regions; f. based on the estimated parameters, defining the spatial location and orientation of the object regions; and g. based on the estimated parameters and the spatial location and orientation of the object regions, defining vectors that map object details specified by each pixel of a plurality of digitized video frames to pixel locations within the final pixelmaps.
-
-
15. Apparatus for generating, from digital pixelmaps representative of a multiple-frame video recording of an object, geometrically specified, textured pixelmaps that collectively represent a three-dimensional model of the object, the apparatus comprising:
-
a. electronic storage means; b. means for partitioning the storage means into memory partitions for electronically storing each video-frame pixelmap and a plurality of final pixelmaps; b. means for selecting and electronically identifying at least seven object features from a first digitized video frame; c. means for tracking the features among a plurality of digitized video frames to determine changes in the relative distances therebetween; d. means for recursively estimating, based on changes in the relative distances, a plurality of unknown parameters including camera focal length, camera translation, camera rotation, and spatial locations of the tracked features; e. means for defining, based on the estimated parameters, vectors that specify spatial locations of object details specified by each pixel in a plurality of digitized video frames; and f. means for mapping, based on the spatial vectors, pixels from the digitized video frames that correspond to a single planar object surface to locations within the final pixelmaps, each final pixelmap being representative of a single object surface. - View Dependent Claims (16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26)
-
Specification