IP Library Granted Patent US 12,656,857
Granted Patent B2
US 12,656,857 · App. 17/962,194 · Granted Jun 16, 2026

Systems and methods for augmented reality- assisted home inspection

Inventors: Brian M. Fields (Phoenix, AZ); Nathan L. Tofte (Downs, IL); Aaron C. Williams (Bloomington, IL); Joseph P. Harr (Bloomington, IL); Vicki King (Bloomington, IL)
Assignee: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY
G06F3/011G06N20/00G06Q50/163G06T7/0004G06T15/205G06T19/006G06T2207/20081
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,656,857
App. No.
17/962,194
Filed
Oct 7, 2022
Granted
Jun 16, 2026
Kind
B2
Art Unit
2663
USPC
382/141
Abstract

The following relates generally to using augmented reality (AR) for inspection of a property. In some examples, underlay layer data may be received (e.g., from a camera of an AR viewer device); and overlay layer data may be received (e.g., from a different camera or other overlay layer device). An AR display may be created by correlating the underlay layer data with the overlay layer data. A property inspection indicia may be identified based upon the correlated overlay layer data.

Claims (86)

1 . A computer-implemented method of using Augmented Reality (AR) for inspection of a property, the method comprising:

generating, in real time, overlay layer data by snaking a camera behind a wall;

receiving, with one or more processors, underlay layer data indicative of a field of view associated with an AR viewer device;

receiving, with the one or more processors, the overlay layer data;

correlating, with the one or more processors, the overlay layer data with the underlay layer data;

identifying, with the one or more processors, a property inspection indicia based upon the correlated overlay layer data generated by snaking the camera behind the wall;

creating, with the one or more processors, an AR display based upon the correlation, the AR display including (i) an indication of the property inspection indicia, and (ii) the camera snaking behind the wall; and

displaying, with the one or more processors, the AR display to a user via the AR viewer device.

2 . The computer-implemented method of claim 1 , wherein the property inspection indicia comprises:

a water leakage;

a water damage;

an insulation deficiency;

a fire hazard;

a structural deficiency; and/or

building code compliance information.

3 . The computer-implemented method of claim 1 , wherein the overlay layer data further comprises data generated from:

a thermal imaging camera;

a stud finder device;

an ultrasound (US) imager; and/or

an analysis of a blueprint of a building on the property.

4 . The computer-implemented method of claim 1 , wherein:

the underlay layer data is generated by an underlay layer camera coupled to the AR viewer device.

5 . The computer-implemented method of claim 1 , further comprising:

in response to identifying the property inspection indicia, with the one or more processors, storing an image of the AR display; and

generating, with the one or more processors, a report that correlates: (i) the stored image, and (ii) a description of the property inspection indicia.

6 . The computer-implemented method of claim 5 , wherein generating the report further comprises:

correlating, with the one or more processors, the stored image to a location on the property; and

including, with the one or more processors, the correlated location in the report.

7 . The computer-implemented method of claim 1 , wherein the property inspection indicia is generated in response to a user input.

8 . The computer-implemented method of claim 1 , wherein identifying the property inspection indicia comprises:

routing, with the one or more processors, the underlay layer data and/or the overlay layer data to a machine learning algorithm.

9 . The computer-implemented method of claim 8 , further comprising:

detecting, with the one or more processors, a user input indicating whether an output of the machine learning algorithm is correct; and

training the machine learning algorithm by routing, via the one or more processors, an indication of the user input to the machine learning algorithm, wherein the user input and the output of the machine learning algorithm are used as inputs for positive or negative reinforcement training of the machine learning algorithm.

10 . The computer-implemented method of claim 9 , wherein routing the indication of the user input to the machine learning algorithm further comprises:

routing, via the one or more processors, to the machine learning algorithm, overlay layer data corresponding the user input, wherein the overlay layer data corresponding the user input includes: (i) image data of home inspection indicia, (ii) thermal image data of home inspection indicia, and/or (iii) stud finder data of home inspection indicia.

11 . The computer-implemented method of claim 9 , wherein the machine learning algorithm is further configured to produce an estimate of an age the property inspection indicia.

12 . The computer-implemented method of claim 1 , wherein:

receiving the underlay layer data comprises receiving, with the one or more processors, the underlay layer data from a first camera with a field of view including a front side of the wall.

13 . The computer-implemented method of claim 1 , wherein correlating the overlay layer data with the underlay layer data comprises:

identifying a location of a property based upon the field of view associated with the AR viewer device;

identifying overlay layer data associated with an object located at the identified location of the property; and

analyzing the underlay layer data to detect a presence of the object.

14 . The computer-implemented method of claim 13 , wherein creating the AR display further comprises including a text box with text describing the object.

15 . The computer-implemented method of claim 13 , wherein creating the AR display further comprises including a warning that the object is associated with a building code violation.

16 . The computer-implemented method of claim 13 , wherein identifying the location of the property viewable via the AR viewer device further comprises:

generating, with the one or more processors, location data of the AR viewer device based upon information received from a Wi-Fi router and/or a beacon device;

receiving, with the one or more processors, orientation data of the AR viewer device from an orientation sensor of the AR viewer device; and

comparing the location data and the orientation data to a layout of the property.

17 . The computer-implemented method of claim 1 , wherein correlating the overlay layer data with the underlay layer data comprises:

based upon the underlay data, identifying an object located within the field of view associated with the AR viewer device; and

obtaining overlay layer data corresponding to the identified object.

18 . The computer-implemented method of claim 17 , wherein creating the AR display further comprises including a text box with text describing the identified object.

19 . The computer-implemented method of claim 17 , wherein creating the AR display further comprises including a warning that the identified object is associated with a building code violation.

20 . A computer system configured to use Augmented Reality (AR) for inspection of a property, the computer system comprising one or more processors configured to:

receive underlay layer data indicative of a field of view associated with an AR viewer device;

receive overlay layer data generated by a camera snaking behind a wall;

correlate the overlay layer data with the underlay layer data;

identify a property inspection indicia based upon the correlated overlay layer data generated by snaking the camera behind the wall;

create an AR display based upon the correlation, the AR display including (i) an indication of the property inspection indicia, and (ii) the camera snaking behind the wall; and

display the AR display to a user via the AR viewer device.

21 . The computer system of claim 20 , wherein the property inspection indicia comprises:

a water leakage;

a water damage;

an insulation deficiency;

a fire hazard;

a structural deficiency; and/or

building code compliance information.

22 . The computer system of claim 20 , wherein the overlay layer data further comprises data generated from:

a thermal imaging camera;

a stud finder device;

an ultrasound (US) imager; and/or

an analysis of a blueprint of a building on the property.

23 . The computer system of claim 20 , further comprising: (i) the AR viewer device, and (ii) an underlay layer camera, wherein the underlay layer data comprises data generated by the underlay layer camera.

24 . The computer system of claim 20 , wherein the one or more processors are configured to generate the property inspection indicia by routing the underlay layer data and/or the overlay layer data into a machine learning algorithm.

25 . A computer device for using Augmented Reality (AR) for inspection of a property, the computer device comprising:

one or more processors; and

one or more memories coupled to the one or more processors;

the one or more memories including computer-executable instructions stored therein that, when executed by the one or more processors, cause the one or more processors to:

receive underlay layer data indicative of a field of view associated with an AR viewer device;

receive overlay layer data generated by a camera snaking behind a wall;

correlate the overlay layer data with the underlay layer data;

identify a property inspection indicia based upon the correlated overlay layer data generated by snaking the camera behind the wall;

create an AR display based upon the correlation, the AR display including (i) an indication of the property inspection indicia, and (ii) the camera snaking behind the wall; and

display the AR display to a user via the AR viewer device.

26 . The computer device of claim 25 , wherein the one or more memories including computer-executable instructions stored therein that, when executed by the one or more processors, further cause the one or more processors to generate the property inspection indicia by routing the underlay layer data and/or the overlay layer data into a machine learning algorithm.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 13, 2022
From: FIELDS, BRIAN M.; TOFTE, NATHAN L.; WILLIAMS, AARON C.; HARR, JOSEPH P.; KING, VICKI
To: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY
Reel/Frame 061417/0742 →
Continuity (2)
Provisional Application 63397691 · Aug 12, 2022
Related Publication 20240053816A1 · Feb 15, 2024
References Cited (56)
US 9057746B1 · Houlette et al. · 2015 [cited by applicant]
US 9152737B1 · Micali et al. · 2015 [cited by applicant]
US 9443195B2 · Micali et al. · 2016 [cited by applicant]
US 9609003B1 · Chmielewski et al. · 2017 [cited by applicant]
US 9699529B1 · Petri et al. · 2017 [cited by applicant]
US 9739813B2 · Houlette et al. · 2017 [cited by applicant]
US 9798979B2 · Fadell et al. · 2017 [cited by applicant]
US 9800958B1 · Petri et al. · 2017 [cited by applicant]
US 9942630B1 · Petri et al. · 2018 [cited by applicant]
US 10102584B1 · Devereaux et al. · 2018 [cited by applicant]
US 10142394B2 · Chmielewski et al. · 2018 [cited by applicant]
US 10198771B1 · Madigan et al. · 2019 [cited by applicant]
US 10296978B1 · Corder et al. · 2019 [cited by applicant]
US 10332059B2 · Matsuoka et al. · 2019 [cited by applicant]
US 10469282B1 · Konrardy et al. · 2019 [cited by applicant]
US 10586177B1 · Choueiter et al. · 2020 [cited by applicant]
US 10664922B1 · Madigan et al. · 2020 [cited by applicant]
US 10699346B1 · Corder et al. · 2020 [cited by applicant]
US 10699348B1 · Devereaux et al. · 2020 [cited by applicant]
US 10735829B2 · Petri et al. · 2020 [cited by applicant]
US 10740691B2 · Choueiter et al. · 2020 [cited by applicant]
US 10750252B2 · Petri et al. · 2020 [cited by applicant]
US 10796557B2 · Sundermeyer et al. · 2020 [cited by applicant]
US 10802477B1 · Konrardy et al. · 2020 [cited by applicant]
US 10804700B2 · Cohen et al. · 2020 [cited by applicant]
US 10818105B1 · Konrardy et al. · 2020 [cited by applicant]
US 10824867B1 · Assam · 2020 [cited by examiner]
US 10907844B2 · Ribbich et al. · 2021 [cited by applicant]
US 11003334B1 · Conway et al. · 2021 [cited by applicant]
US 11100594B1 · West et al. · 2021 [cited by applicant]
US 11164257B1 · Devereaux et al. · 2021 [cited by applicant]
US 11188686B2 · Duff · 2021 [cited by examiner]
US 11232873B1 · Aspro et al. · 2022 [cited by applicant]
US 11277465B2 · Chmielewski et al. · 2022 [cited by applicant]
US 11348193B1 · Konrardy et al. · 2022 [cited by applicant]
US 11417212B1 · Farooqui et al. · 2022 [cited by applicant]
US 11610238B1 · Kwak · 2023 [cited by examiner]
US 20090265193A1 · Collins et al. · 2009 [cited by applicant]
US 20140266669A1 · Fadell et al. · 2014 [cited by applicant]
US 20150061859A1 · Matsuoka et al. · 2015 [cited by applicant]
US 20150347910A1 · Fadell et al. · 2015 [cited by applicant]
US 20170076408A1 · D'Souza · 2017 [cited by examiner]
US 20190236732A1 · Speasl · 2019 [cited by examiner]
US 20190251520A1 · Bentley, III et al. · 2019 [cited by applicant]
US 20200104522A1 · Collart · 2020 [cited by examiner]
US 20210279811A1 · Waltman et al. · 2021 [cited by applicant]
US 20210312789A1 · Linn · 2021 [cited by applicant]
US 20220101275A1 · Aspro et al. · 2022 [cited by applicant]
CN 111626536A · 2020 [cited by applicant]
CN 113138558A · 2021 [cited by applicant]
JP 2003157357A · 2003 [cited by applicant]
KR 20150129845A · 2015 [cited by applicant]
WO WO2014159131A2 · 2014 [cited by applicant]
WO WO2016081511A2 · 2016 [cited by applicant]
WO WO2021087185A1 · 2021 [cited by applicant]
Barnum, Peter, et al. “Dynamic seethroughs: Synthesizing hidden views of moving objects.” 2009 8th IEEE International Symposium on Mixed and Augmented Reality. IEEE, 2009. (Year: 2009). [cited by examiner]