IP Library Granted Patent US 11,392,625
Granted Patent B2
US 11,392,625 · App. 15/634,879 · Granted Jul 19, 2022

Systems and methods for utilizing property features from images

Inventors: Shadrian Strong (Arlington, VA); Lars Dyrud (Bristow, VA); David Murr (Minneapolis, MN)
Assignee: OmniEarth, Inc.
G06F16/29G06F16/5838G06F16/5862G06N3/02G06N3/04G06Q50/16G06V20/176
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 11,392,625
App. No.
15/634,879
Granted
Jul 19, 2022
Kind
B2
Abstract

A process for locating real estate parcels for a user comprises accessing a library of parceled real estate image data to identify objects and features in a plurality of parcels identified by the user as having a feature of interest. A predictive model is constructed and applied to a geographic region selected by the user to generate a customized output of real estate parcels predicted to have the feature of interest.

Claims (29)

1. A process for locating parcels for a user, the process comprising the steps of:

receiving, from a user, a parcel selection of multiple real estate parcels identified by the user, the multiple real estate parcels including one or more features of interest to the user, wherein the one or more features of interest includes one or more user-desired characteristic associated with each real estate parcel, the one or more features of interest capable of being visually discernable through first imagery of the multiple real estate parcels;

accessing, with one or more computer processors, first real estate image data, including the first imagery having pixels and including supplemental data having property attributes, for the parcel selection received from the user, from a library of real estate image data, the library arranged on a parcel by parcel basis;

constructing, with the one or more computer processors, a customized predictive model by analyzing the first real estate image data, including at least the first imagery, corresponding to the parcel selection for the one or more features of interest to the user to determine commonalities of the multiple real estate parcels of the parcel selection, the customized predictive model comprising machine learning algorithms used in one or more neural networks that develop and store correlations for the first imagery based on one or more of: image spectral information, image texture information, image contextual details, and patterns in the first real estate image data;

receiving, from the user, a selection of a geographic area;

identifying one or more real estate parcels predicted by the customized predictive model to have the one or more features of interest of the parcel selection from the user by:

analyzing, with the one or more computer processors, second real estate image data, including second imagery and including supplemental data having property attributes, of additional real estate parcels within the geographic area from the library of real estate image data, with the customized predictive model comprising the machine learning algorithms used in the one or more neural networks; and

generating a customized output of the identified real estate parcels predicted to have the one or more features of interest.

2. The process of claim 1 , wherein the first real estate image data and the second real estate image data comprise at least one of aerial imagery and satellite imagery.

3. The process of claim 1 , wherein receiving from the user the parcel selection includes receiving physical addresses of the multiple real estate parcels from a computer.

4. The process of claim 1 , wherein receiving from the user the parcel selection includes receiving input by the user from a map.

5. The process of claim 1 , further comprising generating a second customized output of the identified real estate parcels predicted to not have the one or more features of interest.

6. The process of claim 1 , wherein the customized output of the identified real estate parcels is displayed as a map.

7. The process of claim 1 , wherein the customized output of the identified real estate parcels is displayed as a list of addresses.

8. A system, comprising:

a non-transitory computer-readable storage medium storing instructions that, when executed by one or more processors, cause the one or more processors to:

receive, from a user, a parcel selection of multiple real estate parcels identified by a user, the multiple real estate parcels including one or more features of interest to the user, wherein the one or more features of interest includes one or more user-desired characteristic associated with each real estate parcel, the one or more features of interest capable of being visually discernable through first imagery of the multiple real estate parcels;

access first real estate image data, including first imagery having pixels and including supplemental data having property attributes, for the received parcel selection of multiple real estate parcels having the one or more features of interest to the user, from a library of real estate image data, the library arranged on a parcel by parcel basis;

construct a customized predictive model by analyzing the first real estate image data including at least the first imagery, corresponding to the parcel selection for the one or more features of interest to the user to determine commonalities of the multiple real estate parcels of the parcel selection, the customized predictive model comprising machine learning algorithms used in one or more neural networks that develop and store correlations for the first imagery based on one or more of: image spectral information, image texture information, image contextual details, and patterns in the first real estate image data;

identify one or more real estate parcels predicted to have the one or more features of interest of the parcel selection from the user by:

analyzing second real estate image data, including second imagery and including supplemental data having property attributes, of additional real estate parcels within a geographic area from the library of real estate image data, with the customized predictive model comprising the machine learning algorithms used in the one or more neural networks; and

generate a customized output of the identified real estate parcels predicted to have the one or more features of interest.

9. The system of claim 8 , wherein the first real estate image data and the second real estate image data comprise at least one of aerial imagery and satellite imagery.

10. The system of claim 8 , wherein the received parcel selection includes physical addresses of the multiple real estate parcels from a computer.

11. The system of claim 8 , wherein the received parcel selection includes selections from a map.

12. The system of claim 8 , the non-transitory computer-readable storage medium storing instructions that, when executed by one or more processor, further cause the one or more processor to:

generate a second customized output of the identified real estate parcels predicted to not have the one or more features of interest.

13. The system of claim 8 , wherein the customized output of the identified real estate parcels is displayed as a map.

14. The system of claim 8 , wherein the customized output of the identified real estate parcels is displayed as a list of addresses.

Assignments (7)
RELEASE OF SECURITY INTEREST Recorded Apr 15, 2025
From: HPS INVESTMENT PARTNERS, LLC
To: OMNIEARTH, INC.
Reel/Frame 070845/0259 →
RELEASE OF FIRST LIEN SECURITY INTEREST IN PATENTS Recorded Apr 9, 2025
From: MORGAN STANLEY SENIOR FUNDING, INC.
To: PICTOMETRY INTERNATIONAL CORP.; EAGLE VIEW TECHNOLOGIES, INC.; OMNIEARTH, INC.
Reel/Frame 070786/0022 →
FIRST LIEN SECURITY AGREEMENT Recorded Mar 28, 2025
From: EAGLE VIEW TECHNOLOGIES, INC.; PICTOMETRY INTERNATIONAL CORP.
To: MORGAN STANLEY SENIOR FUNDING, INC.
Reel/Frame 070671/0078 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 12, 2024
From: OMNIEARTH, INC.
To: EAGLE VIEW TECHNOLOGIES, INC.
Reel/Frame 066115/0970 →
FIRST LIEN PATENT SECURITY AGREEMENT Recorded Aug 23, 2018
From: OMNIEARTH, INC.
To: MORGAN STANLEY SENIOR FUNDING, INC., AS COLLATERAL AGENT
Reel/Frame 046919/0038 →
SECOND LIEN PATENT SECURITY AGREEMENT Recorded Aug 14, 2018
From: OMNIEARTH, INC.
To: HPS INVESTMENT PARTNERS, LLC,
Reel/Frame 046823/0814 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 27, 2017
From: STRONG, SHADRIAN; DYRUD, LARS; MURR, DAVID
To: OMNIEARTH, INC.
Reel/Frame 042830/0827 →
Continuity (2)
Provisional Application 62354873 · Jun 27, 2016
Related Publication 20170371897A1 · Dec 28, 2017
Cited By (1)
US 12,284,570