US 11,113,819 B2 · Graphical fiducial marker identification suitable for augmented reality, virtual reality, and robotics

Abstract

In various examples, image data may be received that represents an image. Corner detection may be used to identify pixels that may be candidate corner points. The image data may be converted from a higher dimensional color space to a converted image in a lower dimensional color space, and boundaries may be identified within the converted image. A set of the candidate corner points may be determined that are within a threshold distance to one of the boundaries, and the set of the candidate corner points may be analyzed to determine a subset of the candidate corner points representative of corners of polygons. Using the subset of the candidate corner points, one or more polygons may be identified, and a filter may be applied to the polygons to identify a polygon as corresponding to a fiducial marker boundary of a fiducial marker.

Claims20

Dependent claims

A method comprising:

receiving image data representative of an image;
converting the image data from a higher dimensional color space to a converted image in a lower dimensional color space;
identifying first pixels corresponding to boundaries in the converted image;
detecting second pixels that represent candidate corner points;
determining a set of the candidate corner points that are within a threshold pixel distance to at least one of the boundaries based at least in part on comparing the first pixels to the second pixels;
analyzing the set of the candidate corner points to determine a subset of the candidate corner points representative of corners of at least one polygon;
and
applying at least one filter to the at least one polygon to identify a polygon of the at least one polygon as corresponding to a fiducial marker boundary of a fiducial marker.

5 more elements

A method comprising:

receiving data representative of boundaries in a first image and associated boundary identifiers (IDs) for the boundaries;
determining pixels in at least one of the first image or a second image that represent candidate corner points within a threshold pixel distance to at least one of the boundaries;
for each boundary of the boundaries:
determining, based at least in part on the boundary IDs, a set of the candidate corner points that are associated with a same boundary ID;
generating edges extending between members of the set of the candidate corner points;
computing angles formed by adjacent edges of the edges;
and
identifying a subset of the set of the candidate corner points associated with a set of the angles of least magnitude as corners of a quadrilateral;
and
applying at least one filter to the quadrilateral to determine whether the quadrilateral corresponds to a fiducial marker boundary of a fiducial marker.

7 more elements

A method comprising:

determining, by one or more graphics processing units (GPUs), first pixels in an image that represent candidate corner points;
determining, by the one or more GPUs, second pixels in the image that represent boundaries in the image;
determining, by the one or more GPUs, a set of the candidate corner points corresponding to the first pixels that are within a threshold pixel distance from one or more of the second pixels corresponding to the boundaries;
copying, by the one or more GPUs, the set of the candidate corner points from GPU memory to central processing unit (CPU) memory, the CPU memory associated with one or more CPUs;
for each boundary of the boundaries:
determining, by the one or more CPUs, a subset of the set of the candidate corner points that are associated with a same boundary of the at least one boundary;
generating, by the one or more CPUs, edges extending between members of the subset of the set of the candidate corner points;
computing, by the one or more CPUs, angles formed by adjacent edges of the edges;
and
identifying, by the one or more CPUs, the candidate corner points from the subset of the set of the candidate corner points associated with a set of the angles of least magnitude as corners of a quadrilateral;
and
determining, by the one or more CPUs, whether the quadrilateral corresponds to a fiducial marker boundary of a fiducial marker.

9 more elements

Dependencies are inferred from the claim text.

Graphical fiducial marker identification suitable for augmented reality, virtual reality, and robotics

Life of this patent

Graphical fiducial marker identification suitable for augmented reality, virtual reality, and robotics

Life of this patent

Abstract

Claims20