John G Karvounis

US Patent:

20130332098, Dec 12, 2013

Filed:

Jun 12, 2013

Appl. No.:

13/915998

Inventors:

Dan Hakim - Silver Spring MD, US
John Karvounis - Bowie MD, US
Travis Young - Rockville MD, US
Carole Teolis - Bethesda MD, US

International Classification:

G01C 25/00

US Classification:

702 93, 702 92

Abstract:

Methods for calibrating a body-worn magnetic sensor by spinning the magnetic sensor 360 degrees to capture magnetic data; if the spin failed to produce a circle contained in an x-y plane fit a sphere to the captured data; determining offsets based on the center of the sphere; and removing the offsets that are in the z-direction. Computing a magnetic heading reliability of a magnetic sensor by determining an orientation of the sensor at one location; transforming the orientation between two reference frames; measuring a first vector associated with the magnetic field of Earth at the location; processing the first vector to generate a virtual vector when a second location is detected; measuring a second vector associated with the magnetic field of Earth at the second location; and calculating the magnetic heading reliability at the second location based on a comparison of the virtual vector and the second vector.

US Patent:

20130332065, Dec 12, 2013

Filed:

Jun 12, 2013

Appl. No.:

13/916479

Inventors:

Christopher Giles - Prince Frederick MD, US
John Karvounis - Bowie MD, US
Benjamin Funk - Hanover MD, US
Jared Napora - Severn MD, US
Carole Teolis - Glenn Dale MD, US

International Classification:

G01C 21/12

US Classification:

701411, 701505, 701501, 701472, 701445

Abstract:

Disclosed herein are methods and systems for fusion of sensor and map data using constraint based optimization. In an embodiment, a computer-implemented method may include obtaining tracking data for a tracked subject, the tracking data including data from a dead reckoning sensor; obtaining constraint data for the tracked subject; and using a convex optimization method based on the tracking data and the constraint data to obtain a navigation solution. The navigation solution may be a path and the method may further include propagating the constraint data by a motion model to produce error bounds that continue to constrain the path over time. The propagation of the constraint data may be limited by other sensor data and/or map structural data.

US Patent:

20230065658, Mar 2, 2023

Filed:

Aug 24, 2022

Appl. No.:

17/894660

Inventors:

- Greenbelt MD, US
John Karvounis - Bowie MD, US
Carole Teolis - Glendale MD, US

International Classification:

G01S 19/21
G01S 19/08
G01S 19/37

Abstract:

System, computer program products, and methods for detecting and compensating for sensor interference. Sensor interference may result from environmental interference or from electronic signal interference. Sensor location input may be adapted or rejected when interference is detected. The system can monitor the accuracy, as well as the integrity, of all navigation sensors. The system can also automatically eliminate the faulty or compromised data from a final navigation solution.

US Patent:

20200404245, Dec 24, 2020

Filed:

Sep 2, 2020

Appl. No.:

17/010727

Inventors:

- Greenbelt MD, US
John George Karvounis - Bowie MD, US

International Classification:

H04N 13/239
G06K 9/00
G06K 9/62
H04N 5/222
G06T 7/80
G06T 7/246
G06T 7/277

Abstract:

LK-SURF, Robust Kalman Filter, HAR-SLAM, and Landmark Promotion SLAM methods are disclosed. LK-SURF is an image processing technique that combines Lucas-Kanade feature tracking with Speeded-Up Robust Features to perform spatial and temporal tracking using stereo images to produce 3D features can be tracked and identified. The Robust Kalman Filter is an extension of the Kalman Filter algorithm that improves the ability to remove erroneous observations using Principal Component Analysis and the X84 outlier rejection rule. Hierarchical Active Ripple SLAM is a new SLAM architecture that breaks the traditional state space of SLAM into a chain of smaller state spaces, allowing multiple tracked objects, multiple sensors, and multiple updates to occur in linear time with linear storage with respect to the number of tracked objects, landmarks, and estimated object locations. In Landmark Promotion SLAM, only reliable mapped landmarks are promoted through various layers of SLAM to generate larger maps.

US Patent:

20200372706, Nov 26, 2020

Filed:

Aug 10, 2020

Appl. No.:

16/989212

Inventors:

- Greenbelt MD, US
Daniel Hakim - Silver Spring MD, US
Daniel Franchy - Catonsville MD, US
Jared Napora - Severn MD, US
John Karvounis - Bowie MD, US
Jonathan Fetter Degges - Washington DC, US
Tim Wang - Germantown MD, US
Benjamin Funk - Hanover MD, US
Carole Teolis - Glendale MD, US
Carol Politi - Bethesda MD, US
Stuart Woodbury - Ellicott City MD, US

International Classification:

G06T 17/05
G06F 30/13

Abstract:

Systems, methods and instructions for creating building models of physical structures is disclosed. The building model may be a collection of floors defined by outlines containing regions that may be offset relative to a main region, and a collection of connectors. Connectors may have connection points for tracking, routing and sizing. Connectors may indicate elevation changes through georeferenced structural features. Signal elements may also be features that provide corrections when tracking. Feature descriptors are data that describes the structural configuration and signal elements enabling them to be matched to previously collected data in a database. User interface elements assist a user of a tracking device in collecting floor information, structural features and signal features and validating certain collected information based on previously known information. The height of floors may also be inferred based on sensor data from the tracking device.

US Patent:

20200372707, Nov 26, 2020

Filed:

Aug 10, 2020

Appl. No.:

16/989287

Inventors:

- Greenbelt MD, US
Daniel Hakim - Silver Spring MD, US
Daniel Franchy - Catonsville MD, US
Jared Napora - Severn MD, US
John Karvounis - Bowie MD, US
Jonathan Fetter Degges - Washington DC, US
Tim Wang - Germantown MD, US
Benjamin Funk - Hanover MD, US
Carole Teolis - Glendale MD, US
Carol Politi - Bethesda MD, US
Stuart Woodbury - Ellicott City MD, US

International Classification:

G06T 17/05
G06F 30/13

Abstract:

Systems, methods and instructions for creating building models of physical structures is disclosed. The building model may be a collection of floors defined by outlines containing regions that may be offset relative to a main region, and a collection of connectors. Connectors may have connection points for tracking, routing and sizing. Connectors may indicate elevation changes through georeferenced structural features. Signal elements may also be features that provide corrections when tracking. Feature descriptors are data that describes the structural configuration and signal elements enabling them to be matched to previously collected data in a database. User interface elements assist a user of a tracking device in collecting floor information, structural features and signal features and validating certain collected information based on previously known information. The height of floors may also be inferred based on sensor data from the tracking device.

US Patent:

20190371054, Dec 5, 2019

Filed:

May 31, 2019

Appl. No.:

16/428519

Inventors:

- Greenbelt MD, US
Daniel Hakim - Silver Spring MD, US
Daniel Franchy - Catonsville MD, US
Jared Napora - Severn MD, US
John Karvounis - Bowie MD, US
Jon Fetter Degges - Washington DC, US
Tim Wang - Germantown MD, US
Benjamin Funk - Hanover MD, US
Carole Teolis - Glendale MD, US
Carol Politi - Bethesda MD, US
Stuart Woodbury - Ellicott City MD, US

International Classification:

G06T 17/05
G06F 17/50

Abstract:

Systems, methods and instructions for creating building models of physical structures is disclosed. The building model may be a collection of floors defined by outlines containing regions that may be offset relative to a main region, and a collection of connectors. Connectors may have connection points for tracking, routing and sizing. Connectors may indicate elevation changes through georeferenced structural features. Signal elements may also be features that provide corrections when tracking. Feature descriptors are data that describes the structural configuration and signal elements enabling them to be matched to previously collected data in a database. User interface elements assist a user of a tracking device in collecting floor information, structural features and signal features and validating certain collected information based on previously known information. The height of floors may also be inferred based on sensor data from the tracking device.

US Patent:

20190007673, Jan 3, 2019

Filed:

Jun 14, 2018

Appl. No.:

16/009115

Inventors:

- Greenbelt MD, US
John George Karvounis - Bowie MD, US

International Classification:

H04N 13/239
H04N 5/222
G06T 7/246
G06T 7/277
G06K 9/00
G06K 9/62
G06T 7/80
H04N 13/122
G06K 9/46
H04N 13/246
H04N 13/00
H04N 13/282

Abstract:

LK-SURF, Robust Kalman Filter, HAR-SLAM, and Landmark Promotion SLAM methods are disclosed. LK-SURF is an image processing technique that combines Lucas-Kanade feature tracking with Speeded-Up Robust Features to perform spatial and temporal tracking using stereo images to produce 3D features can be tracked and identified. The Robust Kalman Filter is an extension of the Kalman Filter algorithm that improves the ability to remove erroneous observations using Principal Component Analysis and the X84 outlier rejection rule. Hierarchical Active Ripple SLAM is a new SLAM architecture that breaks the traditional state space of SLAM into a chain of smaller state spaces, allowing multiple tracked objects, multiple sensors, and multiple updates to occur in linear time with linear storage with respect to the number of tracked objects, landmarks, and estimated object locations. In Landmark Promotion SLAM, only reliable mapped landmarks are promoted through various layers of SLAM to generate larger maps.