Jeffrey T Cole

US Patent:

8065293, Nov 22, 2011

Filed:

Oct 24, 2007

Appl. No.:

11/923430

Inventors:

Kunal Mukerjee - Redmond WA, US
Jeffrey Cole - Redmond WA, US
Brendan Meeder - Redmond WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06F 17/30

US Classification:

707711, 707696, 707739, 707740, 707741, 707742, 707743, 707744, 707745, 707746, 707802

Abstract:

An indexing system uses a graph-like data structure that clusters features indexes together. The minimum atomic value in the data structure is represented as a leaf node which is either a single feature index or a sequence of two or more feature indexes when a minimum sequence length is imposed. Root nodes are formed as clustered collections of leaf nodes and/or other root nodes. Context nodes are formed from root nodes that are associated with content that is being indexed. Links between a root node and other nodes each include a sequence order value that is used to maintain the sequencing order for feature indexes relative to the root node. The collection of nodes forms a graph-like data structure, where each context node is indexed according to the sequenced pattern of feature indexes. Clusters can be split, merged, and promoted to increase the efficiency in searching the data structure.

US Patent:

20120316680, Dec 13, 2012

Filed:

Jun 13, 2011

Appl. No.:

13/158465

Inventors:

Jean Sebastien Fouillade - Redmond WA, US
Adrien Felon - Seattle WA, US
Jeffrey Cole - Seattle WA, US
Nathaniel T. Clinton - Sammamish WA, US
Russell Sanchez - Redmond WA, US
Francois Burianek - Kirkland WA, US
Malek M. Chalabi - Redmond WA, US
Harshavardhana Narayana Kikkeri - Bellevue WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

B25J 13/08

US Classification:

700258, 901 1, 901 46

Abstract:

A robot tracks objects using sensory data, and follows an object selected by a user. The object can be designated by a user from a set of objects recognized by the robot. The relative positions and orientations of the robot and object are determined. The position and orientation of the robot can be used so as to maintain a desired relationship between the object and the robot. Using the navigation system of the robot, during its movement, obstacles can be avoided. If the robot loses contact with the object being tracked, the robot can continue to navigate and search the environment until the object is reacquired.

US Patent:

20130342572, Dec 26, 2013

Filed:

Jun 26, 2012

Appl. No.:

13/533148

Inventors:

Adam G. Poulos - Redmond WA, US
Stephen G. Latta - Seattle WA, US
Daniel J. McCulloch - Kirkland WA, US
Jeffrey Cole - Seattle WA, US

International Classification:

G09G 5/00

US Classification:

345633

Abstract:

A system and method are disclosed for controlling content displayed to a user in a virtual environment. The virtual environment may include virtual controls with which a user may interact using predefined gestures. Interacting with a virtual control may adjust an aspect of the displayed content, including for example one or more of fast forwarding of the content, rewinding of the content, pausing of the content, stopping the content, changing a volume of content, recording the content, changing a brightness of the content, changing a contrast of the content and changing the content from a first still image to a second still image.

US Patent:

20130343600, Dec 26, 2013

Filed:

Jun 22, 2012

Appl. No.:

13/530925

Inventors:

Harshavardhana Narayana Kikkeri - Bellevue WA, US
Michael F. Koenig - Bellevue WA, US
Jeffrey Cole - Seattle WA, US

Assignee:

MICROSOFT CORPORATION - Redmond WA

International Classification:

G06K 9/62

US Classification:

382103

Abstract:

Face recognition training database generation technique embodiments are presented that generally involve collecting characterizations of a person's face that are captured over time and as the person moves through an environment, to create a training database of facial characterizations for that person. As the facial characterizations are captured over time, they are will represent the person's face as viewed from various angles and distances, different resolutions, and under different environmental conditions (e.g., lighting and haze conditions). Further, over a long period of time where facial characterizations of a person are collected periodically, these characterizations can represent an evolution in the appearance of the person. This produces a rich training resource for use in face recognition systems. In addition, since a person's face recognition training database can be established before it is needed by a face recognition system, once employed, the training will be quicker.

US Patent:

20170206668, Jul 20, 2017

Filed:

Mar 30, 2017

Appl. No.:

15/474687

Inventors:

- Redmond WA, US
Arthur Tomlin - Kirkland WA, US
Tony Ambrus - Seattle WA, US
Jeffrey Cole - Seattle WA, US
Ian Douglas McIntyre - Redmond WA, US
Drew Steedly - Redmond WA, US
Frederik Schaffalitzky - Bellevue WA, US
Georg Klein - Seattle WA, US
Kathleen P. Mulcahy - Seattle WA, US

Assignee:

Microsoft Technology Licensing, LLC - Redmond WA

International Classification:

G06T 7/246
G06T 19/00
G02B 27/01
G06T 7/60

Abstract:

Embodiments are disclosed for methods and systems of distinguishing movements of features in a physical environment. For example, on a head-mounted display device, one embodiment of a method includes obtaining a representation of real-world features in two or more coordinate frames and obtaining motion data from one or more sensors external to the head-mounted display device. The method further includes distinguishing features in one coordinate frame from features in another coordinate frame based upon the motion data.

US Patent:

20150317834, Nov 5, 2015

Filed:

May 1, 2014

Appl. No.:

14/267755

Inventors:

Adam G. Poulos - Sammamish WA, US
Arthur Tomlin - Kirkland WA, US
Tony Ambrus - Seattle WA, US
Jeffrey Cole - Seattle WA, US
Ian Douglas McIntyre - Redmond WA, US
Drew Steedly - Redmond WA, US
Frederik Schaffalitzky - Bellevue WA, US
Georg Klein - Seattle WA, US
Kathleen P. Mulcahy - Seattle WA, US

International Classification:

G06T 19/00
G06K 9/46
G06K 9/00
G06K 9/62
G02B 27/01
G06T 7/20

Abstract:

Embodiments are disclosed for methods and systems of distinguishing movements of features in a physical environment. For example, on a head-mounted display device, one embodiment of a method includes obtaining a representation of real-world features in two or more coordinate frames and obtaining motion data from one or more sensors external to the head-mounted display device. The method further includes distinguishing features in one coordinate frame from features in another coordinate frame based upon the motion data.

US Patent:

20150092986, Apr 2, 2015

Filed:

Oct 7, 2014

Appl. No.:

14/507956

Inventors:

Harshavardhana Narayana Kikkeri - Bellevue WA, US
Michael F. Koenig - Bellevue WA, US
Jeffrey Cole - Seattle WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06K 9/00

US Classification:

382103

Abstract:

Face recognition training database generation technique embodiments are presented that generally involve collecting characterizations of a person's face that are captured over time and as the person moves through an environment, to create a training database of facial characterizations for that person. As the facial characterizations are captured over time, they are will represent the person's face as viewed from various angles and distances, different resolutions, and under different environmental conditions (e.g., lighting and haze conditions). Further, over a long period of time where facial characterizations of a person are collected periodically, these characterizations can represent an evolution in the appearance of the person. This produces a rich training resource for use in face recognition systems. In addition, since a person's face recognition training database can be established before it is needed by a face recognition system, once employed, the training will be quicker.

US Patent:

20140347390, Nov 27, 2014

Filed:

May 22, 2013

Appl. No.:

13/900416

Inventors:

Adam G. Poulos - Sammamish WA, US
Tony Ambrus - Seattle WA, US
Jeffrey Cole - Seattle WA, US
Ian Douglas McIntyre - Redmond WA, US
Stephen Latta - Seattle WA, US
Peter Tobias Kinnebrew - Seattle WA, US
Nicholas Kamuda - Seattle WA, US
Robert Pengelly - Seattle WA, US
Jeffrey C. Fong - Seattle WA, US
Aaron Woo - Bellevue WA, US
Udiyan I. Padmanahan - Bellevue WA, US
Andrew Wyman MacDonald - Seattle WA, US
Olivia M. Janik - Seattle WA, US

International Classification:

G06T 19/00

US Classification:

345633

Abstract:

Embodiments are disclosed that relate to placing virtual objects in an augmented reality environment. For example, one disclosed embodiment provides a method comprising receiving sensor data comprising one or more of motion data, location data, and orientation data from one or more sensors located on a head-mounted display device, and based upon the motion data, determining a body-locking direction vector that is based upon an estimated direction in which a body of a user is facing. The method further comprises positioning a displayed virtual object based on the body-locking direction vector.