Tracking three-dimensional geometric shapes
AssigneeMicrosoft Technology Licensing, LLC
InventorsLingzhi L. Allen, Wolfgang M. Pauli
Life of this patent
Estimating the term…
Abstract
A set of geometric shapes to be applied by a machine learning model to objects identified in image data is defined. A learning rate of the machine learning model is updated in response to external events. The machine learning model is used to estimate spatial parameters for each of the objects identified in the image data. The spatial parameters are estimated by fitting the objects to the set of geometric shapes. Updates to the spatial parameters are temporally integrated. A spatial estimate of the objects identified in the image data is generated.
Claims20
A method of analyzing image data to estimate spatial parameters of objects represented in the image data, the method comprising:
- receiving a selection of geometric shapes to be applied by a machine learning model to the objects represented in the image data;
- in response to detection of an external event, updating a learning rate of the selection of geometric shapes by the machine learning model;
- using the machine learning model to estimate spatial parameters for each of the objects, wherein the spatial parameters are estimated by fitting the geometric shapes to the objects;
- generating integrated spatial parameters by temporally integrating successive updates to the spatial parameters;
- and
- generating a spatial estimate of the objects based on the integrated spatial parameters.
A computing system comprising:
- a processing system comprising a processor;
- and
- computer-readable media having thereon computer-executable instructions that are structured such that, when executed by the processing system, cause the computing system to perform operations comprising:
- accessing a set of geometric shapes to be applied by a machine learning model to objects identified in image data;
- updating a learning rate of the machine learning model in response to an external event;
- estimating spatial parameters for each of the objects using the machine learning model, wherein the spatial parameters are estimated by fitting the set of geometric shapes to the objects;
- temporally integrating successive updates to the spatial parameters;
- and
- generating a spatial estimate of the objects identified in the image data.
A computer-readable storage medium having thereon computer-executable instructions that are structured such that, when executed by a processing system of a computing system, cause the computing system to perform operations comprising:
- defining a set of geometric shapes to be applied by a machine learning model to objects identified in image data;
- updating a learning rate of the machine learning model in response to an external event;
- estimating spatial parameters for each of the objects using the machine learning model, wherein the spatial parameters are estimated by fitting the set of geometric shapes to the objects;
- temporally integrating successive updates to the spatial parameters;
- and
- generating a spatial estimate of the objects identified in the image data.
Dependencies are inferred from the claim text.