3D object recognition
AssigneeApple Inc.
InventorsJan Solem, Fredrik Kahl
Life of this patent
Estimating the term…
Abstract
A method, device, system, and computer program for object recognition of a 3D object of a certain object class using a statistical shape model for recovering 3D shapes from a 2D representation of the 3D object and comparing the recovered 3D shape with known 3D to 2D representations of at least one object of the object class.
Claims25
A method for object recognition of a three dimensional (3D) object, comprising the steps of:
- obtaining at least one two dimensional (2D) representation of said object;
- detecting image features in said obtained 2D representation;
- recovering a highly probable 3D shape of said object of a certain object class consistent with 2D images of said object using at least one obtained image where 2D features are detected and using a learned statistical multi-view shape model of the shape variation;
- and
- comparing said recovered 3D shape with a reference representation of at least one object of said object class.
A device for object recognition of a three dimensional (3D) object, comprising:
- means for obtaining at least one two dimensional (2D) representation of said object;
- means for detecting image features in said obtained 2D representation;
- means for recovering a highly probable 3D shape of said object of a certain object class consistent with 2D images of said object using one or more images where 2D features are detected and using a learned statistical multi-view shape model of the shape variation;
- and
- means for comparing said recovered 3D shape with a reference representation of at least one object of said object class.
A computer program stored in a computer readable storage medium and executed in a computational unit for object recognition of a three dimensional (3D) object, comprising:
- an instruction set for obtaining at least one externally acquired two dimensional (2D) representation of said 3D object;
- an instruction set for detecting image features in said obtained 2D representation;
- an instruction set for recovering a highly probable 3D shape of said 3D object of a certain object class consistent with 2D images of said 3D object using one or more images where 2D features are detected and using a learned statistical multi-view shape model of the shape variation;
- and
- an instruction set for comparing said recovered 3D shape with a reference representation of at least one object of said object class;
A system for object recognition of a three dimensional (3D) object, comprising:
- means for obtaining at least one two dimensional (2D) representation of said 3D object;
- means for detecting image features in said obtained 2D representation;
- means for recovering a highly probable 3D shape of said 3D object of a certain object class consistent with 2D images of said 3D object using one or more images where 2D features are detected and using a learned statistical multi-view shape model of the shape variation;
- means for comparing said recovered 3D shape with a reference representation of at least one object of said object class;
- and
- means for responding to a result from said means for comparison.
Dependencies are inferred from the claim text.