Alignment of images of a three-dimensional object

• US 10,447,999 B2
• Filed: 10/20/2015
• Issued: 10/15/2019
• Est. Priority Date: 10/20/2015
• Status: Expired due to Fees

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: de Lima, Diogo S., Sharma, Divya, Dibenedetto, Dante, Gerasimets, Ilya, Saranin, Arsenii
• Primary Examiner(s): Kholdebarin, Iman K
• Application Number:
  US14/918,213
• Publication Number:
  US 20170109888A1
• Time in Patent Office: 1,456 Days
• Field of Search: None
• CPC Class Codes: G01S 17/00 Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
• CPC Class Codes: G01S 17/89 for mapping or imaging
• CPC Class Codes: G01S 7/4808 Evaluating distance, position or velocity data
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06T 2200/08 involving all processing steps from image acquisition to 3D model generation
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 3/147 using affine transformations
• CPC Class Codes: G06T 7/30 Determination of transform parameters for the alignment of images, i.e. image registration
• CPC Class Codes: H04N 13/257 Colour aspects

Abstract

In one example implementation, a system for aligning of images of a three-dimensional (3D) object includes a select engine to select a first image and a second image from a sequence of images of a 3D object taken at different object orientations from a capture cycle of a scanner, a combine engine to combine first metadata from the first image and second metadata from the second image to form combined metadata, an orientation engine to select a third image from the sequence of images, where the third image is from an opposite object orientation relative to a first object orientation of the first image or a second object orientation of the second image, and an align engine to align the sequence of images based on the combined metadata and third metadata from the third image.

Claims

1. A system, comprising:

a select engine to select a first image and a second image from a sequence of images of a three-dimensional (3D) object taken at different object orientations from a same capture cycle of a scanner, wherein selecting the first image and the second image from the sequence of images is based on an alignment of a point cloud of the first image with an alignment of a point cloud with the second image;

a combine engine to combine first metadata from the first image and second metadata from the second image to form combined metadata;

an orientation engine to select a third image from the sequence of images, wherein the third image is from an opposite object orientation relative to a first object orientation of the first image or a second object orientation of the second image; and

an align engine to align the sequence of images based on the combined metadata and third metadata from the third image without metadata from other images included in the sequence of images from the same capture cycle.

2. The system of claim 1, wherein the first image and the second image are from adjacent object orientations.

3. The system of claim 1, comprising a model engine to generate a 3D model of the 3D object using the aligned sequence of images.

4. The system of claim 1, wherein the combined metadata includes metadata representative of respective geometries of the 3D object as viewed from the first object orientation and the second object orientation.

5. The system of claim 1, wherein the same capture cycle comprises a sequence of at least six different object orientations.

6. The system of claim 1, wherein a total number of object orientations included in the same capture cycle is an even number.

7. The system of claim 6, wherein the opposite object orientation is about 180 degrees of rotation along the same capture cycle from the first object orientation or the second object orientation.

8. The system of claim 1, wherein the scanner includes:

a depth-sensor camera; and

a red, green, and blue (RGB) camera.

15. The system of claim 1, wherein selecting the first image and the second image further comprises selecting two images from the same capture cycle that use the least amount of rotation of the point clouds of the two images to align the two images.

9. A non-transitory computer readable medium storing instructions executable by a processing resource to cause a computing device to:

receive a sequence of images of a three-dimensional (3D) object taken at different object orientations from a same capture cycle of a scanner;

select a first image and a second image from the sequence of images, wherein selecting the first image and the second image from the sequence of images is based on an alignment of a point cloud of the first image with an alignment of a point cloud with the second image;

combine metadata of the first image with metadata of the second image to form combined metadata;

select a third image from the sequence of images from an opposite object orientation relative to a first object orientation of the first image or a second object orientation of the second image;

align an image of the sequence of images based on the combined metadata and metadata of the third image without metadata from other images included in the sequence of images from the same capture cycle; and

generate at least a portion of a 3D model of the 3D object using the aligned sequence of images.

10. The medium of claim 9, wherein the instructions to align include instructions to rotate and translate a point cloud of an image of the sequence of images by a rotation angle matrix determined based on the combined metadata and the metadata of the third image.

11. The medium of claim 9, wherein the instructions to select the first image and the second image include instructions to select two images from the sequence of images having a desired alignment.

12. A method, comprising:

selecting a first image and a second image from a sequence of images of a three-dimensional (3D) object taken at different object orientations from a same capture cycle of a scanner, wherein selecting the first image and the second image from the sequence of images is based on an alignment of a point cloud of the first image with an alignment of a point cloud with the second image;

receiving first metadata of the first image of the 3D object at a first object orientation and second metadata of the second image of the 3D object at a second object orientation adjacent to the first object orientation along a sequence of object orientations corresponding to the sequence of images from the same capture cycle of the scanner;

combining the first metadata and the second metadata to form a combined metadata;

receiving third metadata from a third image of the 3D object at a third object orientation opposite from the first object orientation or the second object orientation; and

aligning the sequence of images to generate at least a portion of a 3D model of the 3D object based on the combined metadata and the third metadata without metadata of other images included in the sequence of images from the same capture cycle.

13. The method of claim 12, comprising selecting the third image from the sequence of images from the same capture cycle of the scanner.

14. The method of claim 12, comprising rotating the 3D object within a single plane at a fixed angle relative the scanner during the same capture cycle.