Visual object recognition and tracking
AssigneeEnergid Technologies Corporation
InventorsChu-Yin Chang, James D. English, Neil M. Tardella
Life of this patent
Estimating the term…
Abstract
This invention describes a method for identifying and tracking an object from two-dimensional data pictorially representing said object by an object-tracking system through processing said two-dimensional data using at least one tracker-identifier belonging to the object-tracking system for providing an output signal containing: a) a type of the object, and/or b) a position or an orientation of the object in three-dimensions, and/or c) an articulation or a shape change of said object in said three dimensions.
Claims30
A method for identifying and tracking an object from two-dimensional data pictorially representing said object, comprising:
- receiving, from a sensor, at least one set of said two-dimensional data pictorially representing said object, wherein said at least one set corresponds to one temporal instance and said two-dimensional data is generated by the sensor;
- processing, via a computing device, said at least one set of said two-dimensional data using at least one tracker-identifier for providing an output signal including a type of said object, at least one of a position and an orientation of said object in three-dimensions, and an articulation change and a shape change of said object in said three dimensions, wherein said type of the object is determined using a spatial model description of said object;
- and
- generating synthetic object images, via said processing, by selecting points on a surface of a four-dimensional quaternion hyperhemisphere using a predetermined method.
An object-tracking system for identifying and tracking an object from two-dimensional data pictorially representing said object, comprising:
- a sensor configured to receive at least one set of said two-dimensional data pictorially representing said object, wherein said at least one set corresponds to one temporal instance;
- a computing device including at least one tracker-identifier configured to process said at least one set of said two-dimensional data, and further configured to provide an output signal including a type of the object, at least one of a position and an orientation of the object in three-dimensions, and an articulation change and a shape change of said object in said three dimensions, wherein said type of the object is determined using a spatial model description of said object;
- and
- an object-model database in communication with said at least one tracker-identifier for providing points on a surface of a four-dimensional quaternion hyperhemisphere for generating synthetic object images using a predetermined method.
A method comprising:
- receiving, from a sensor, representing an object, wherein said data corresponds to one temporal instance and is generated by the sensor;
- and
- processing, via a computing device, said data using at least one tracker-identifier for providing an output signal including at least one of a type of the object a position, and an orientation of the object;
- generating synthetic object images, via said processing, by selecting points on a surface of a four-dimensional quaternion hyperhemisphere using a predetermined method;
- and
- wherein said processing comprises generating harmonic images out of said synthetic object images, wherein at least one of said synthetic object images contains said object, by summing said synthetic object images using hyperspherical harmonic weights.
A system comprising:
- a sensor configured to receive data representing an object, wherein said data corresponds to one temporal instance of the object;
- a computing device including at least one tracker-identifier configured to process said data and further configured to provide an output signal including at least one of a type of the object, a position, and an orientation of the object;
- an object-model database in communication with said at least one tracker-identifier for providing points on a surface of a four-dimensional quaternion hyperhemisphere for generating synthetic object images using a predetermined method;
- and
- wherein said processing comprises generating harmonic images out of said synthetic object images, wherein at least one of said synthetic object images contains said object, by summing said synthetic object images using hyperspherical harmonic weights.
Dependencies are inferred from the claim text.