METHOD FOR THE AUTOMATED IDENTIFICATION OF REAL WORLD OBJECTS

• US 20140300597A1
• Filed: 04/08/2013
• Published: 10/09/2014
• Est. Priority Date: 04/08/2013
• Status: Active Grant

• Current Assignee: Jeffrey W. Holcomb
• Original Assignee: Jeffrey W. Holcomb
• Inventors: Holcomb, Jeffrey W.
• Granted Patent: US 10,776,978 B2
• Time in Patent Office: Days
• US Class Current: 345/420
• CPC Class Codes: G06T 13/40 of characters, e.g. humans, animals or virtual beings
• CPC Class Codes: G06V 10/422 for representing the structure of the pattern or shape of an object therefor
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition

Abstract

A method is provided for the automated identification of real world objects. The invention, implementable via various means such as a processing system, method, or data structure in a recording medium such as memory or as a self-contained electronic circuit, has wide ranging applicability to numerous fields such as in a user interface for gaming systems, like Kinect, or immersive environments such as remote surgical operations, and other medical diagnostic applications. Similarly, our method can be utilized in artificial intelligence application for automated robotic identification of targets, such as drone assisted search and rescue missions, and the enablement of patent protection against unlawful replication on 3D printers. The method of the invention includes the steps of creating a 3D representation for the real world object to be identified, segmenting the newly created 3D representation according to potential identities, alignment of minimal, unique representations for said potential identities to the corresponding segments of the newly created 3D representation, and then the analysis of said alignments to determine which potential identity correctly identifies the real world object to be identified.

Claims

1. The development of a generalized mathematical method for representing objects using a minimal amount of information, and scale restrictions that allow for the acquisition of varying degrees of information for object representation;

where said representation can be implemented on any computational device.

2. A method for constructing the minimal representations from claim 1 via the reduction of a traditional skeletal representation for an object;

where said construction can be performed on any computational device.

4. A method for verifying the accuracy of the minimal representations computed in claim 3 by comparing them with the minimal representations constructed in claim 2;

where said verification process can be performed on any computational device.

3. A method for computing a minimal representation for an object based on object information and previously known minimal representations taken from an object library;

where said computation can be executed on any computational device.

5. A generalized method for automatic object identification;

where said method can be implemented on any computational device.

6. An automatic rigging methodology that allows a library of skeletons to be automatically rigged to a library of input meshes