AR-enabled labeling using aligned CAD models
AssigneePalo Alto Research Center Incorporated
InventorsMatthew A. Shreve, Robert R. Price
Life of this patent
Estimating the term…
Abstract
One embodiment provides a system that facilitates efficient collection of training data for training an image-detection artificial intelligence (AI) engine. During operation, the system obtains a three-dimensional (3D) model of a physical object placed in a scene, generates a virtual object corresponding to the physical object based on the 3D model, and substantially superimposes, in a view of an augmented reality (AR) camera, the virtual object over the physical object. The system can further configure the AR camera to capture a physical image comprising the physical object in the scene and a corresponding AR image comprising the virtual object superimposed over the physical object, and create an annotation for the physical image based on the AR image.
Claims20
A computer-implemented method for facilitating efficient collection of training data for training an image-detection artificial intelligence (AI) engine, the method comprising:
- obtaining a three-dimensional (3D) model of a physical object placed in a scene;
- generating a virtual object corresponding to the physical object based on the 3D model;
- and
- configuring an augmented reality (AR) camera to:
- automatically superimpose the virtual object over the physical object in a view of the AR camera;
- capture a physical image comprising the physical object in the scene and a corresponding AR image comprising the virtual object superimposed over the physical object;
- and
- automatically create an annotation for the physical image based on the AR image.
A computer system for facilitating efficient collection of training data for training an image-detection artificial intelligence (AI) engine, the system comprising:
- a processor;
- and
- a storage device storing instructions that when executed by the processor cause the processor to perform a method, the method comprising:
- obtaining a three-dimensional (3D) model of a physical object placed in a scene;
- generating a virtual object corresponding to the physical object based on the 3D model;
- configuring an augmented reality (AR) camera;
- to:
- automatically superimpose the virtual object over the physical object in a view of the AR camera;
- capture a physical image comprising the physical object in the scene and a corresponding AR image comprising the virtual object superimposed over the physical object;
- and
- automatically create an annotation for the physical image based on the AR image.
Dependencies are inferred from the claim text.