Estimating pose in 3d space
AssigneeMagic Leap, Inc.
InventorsAdrian Kaehler, Gary Bradski
Life of this patent
Estimating the term…
Abstract
Methods and devices for estimating position of a device within a 3D environment are described. Embodiments of the methods include sequentially receiving multiple image segments forming an image representing a field of view (FOV) comprising a portion of the environment. The image includes multiple sparse points that are identifiable based in part on a corresponding subset of image segments of the multiple image segments. The method also includes sequentially identifying one or more sparse points of the multiple sparse points when each subset of image segments corresponding to the one or more sparse points is received and estimating a position of the device in the environment based on the identified the one or more sparse points.
Claims20
A computer-implemented method for estimating a pose of an image capture device, the method comprising:
- sequentially capturing, by an image capture device, a plurality of image segments of an image, the image representing at least a portion of an environment around the image capture device and including a plurality of sparse points;
- sequentially identifying sparse points of the plurality of sparse points in response to receiving the image segments corresponding to the sparse points;
- and
- periodically estimating at least one of a position or orientation of the image capture device within the environment based on a rolling set of sparse points comprising a predetermined number of most recently identified sparse points selected from the identified sparse points, and excluding sparse points that are not within the predetermined number of most recently identified sparse points,
- wherein each individual periodic estimation is based on a different set of sparse points relative to a set of sparse points used for a preceding estimation.
A computer-implemented method for estimating a pose of an image capture device, the method comprising:
- sequentially capturing, by an image capture device, a first plurality of image segments of an image that represents a field of view (FOV) of the image capture device, the first plurality of image segments forming less than an entirety of the image, the FOV comprising a plurality of sparse points;
- sequentially capturing a second plurality of image segments, the second plurality of image segments captured at least partially after the first plurality of image segments and forming at least another portion of the image;
- identifying a first group of sparse points based in part on the first plurality of image segments,
- determining at least one of a position or orientation of the image capture device within an environment of the imaging system based on the first group of sparse points,
- identifying a second group of sparse points based in part on the second plurality of image segments,
- updating the at least one of the position or orientation of the image capture device within the environment based at least in part on a rolling set of sparse points comprising a predetermined number of most recently identified sparse points selected first from the second group of sparse points and then from the first group of sparse points,
- identifying a third group of sparse points based in part on a third plurality of image segments, and
- updating the at least one of the position or orientation of the image capture device within the environment based at least in part on an updated rolling set of sparse points comprising the predetermined number of most recently identified sparse points selected first from the third group, then from the second group, and then from the first group of sparse points.
Dependencies are inferred from the claim text.