# US 2024/0193859 A1 · Estimating dimensions of geo-referenced ground-level imagery using orthogonal imagery

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0193859 A1
- Document ID: US20240193859A1
- Status: Published application
- Kind: A1
- Application number: 18/415,250
- Filed: 2024-01-17
- Published: 2024-06-13
- Earliest claimed: 2013-10-25
- Assignees: Hover Inc.
- Applicants: Hover Inc.
- Inventors: Bo Hu; Sarthak Sahu
- Web page: https://patentgrep.com/patent/US20240193859A1

## CPC

- G06T 17/00: Three-dimensional [3D] modelling for computer graphics
- G06T 1/0007: {Image acquisition}
- G06T 7/75: {involving models}
- G06T 17/20: Finite element generation, e.g. wire-frame surface description, {tesselation}
- G06T 2207/10004: Still image; Photographic image
- G06T 2210/04: Architectural design, interior design
- G06T 2219/012: Dimensioning, tolerancing
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A system and method is provided for measurements of building façade elements by combining ground-level and orthogonal imagery. The measurements of the dimension of building façade elements are based on ground-level imagery that is scaled and geo-referenced using orthogonal imagery. The method continues by creating a tabular dataset of measurements for one or more architectural elements such as siding (e.g., aluminum, vinyl, wood, brick and/or paint), windows or doors. The tabular dataset can be part of an estimate report.

## Claims

### Claim at position 1

-20. (canceled)

### Claim 21

A method of generating measurements of a three-dimensional building model, comprising:
receiving a plurality of ground-level images capturing a building object;
determining a location associated with the plurality of ground-level images;
generating an unscaled three-dimensional building model from a set consisting of the plurality of ground-level images, wherein the unscaled three-dimensional building model represents the building object as a plurality of pixels in a three-dimensional space;
receiving a geo-referenced top-view orthogonal image of the building object based on the location associated with the plurality of ground-level images, wherein the geo-referenced top-view orthogonal image represents the building object as a plurality of pixels in a two-dimensional space;
matching a first three-dimensional pixel and a second three-dimensional pixel of the unscaled three-dimensional building model to corresponding two-dimensional pixels in the geo-referenced top-view orthogonal image;
deriving a geometric scale relative among all pixels of the three-dimensional building model based on the matching; and
generating a measurement between a third pixel and a fourth pixel of the three-dimensional building model based on the derived geometric scale.

### Claim 22 (depends on 21)

The method of claim 21, wherein the plurality of ground-level images are captured using a smartphone.

### Claim 23 (depends on 21)

The method of claim 21, wherein generating the unscaled three-dimensional building model comprises:
generating a three-dimensional point cloud of the building object from the set consisting of the plurality of ground-level images.

### Claim 24 (depends on 23)

The method of claim 23, wherein generating the unscaled three-dimensional building model further comprises:
identifying architectural features of the three-dimensional point cloud.

### Claim 25 (depends on 24)

The method of claim 24, further comprising:
generating measurements of the architectural features based on the derived geometric scale.

### Claim 26 (depends on 21)

The method of claim 21, wherein matching at least the first three-dimensional pixel and the second three-dimensional pixel of the unscaled three-dimensional building model to corresponding two-dimensional pixels in the geo-referenced top-view orthogonal image comprises:
matching at least two vertices of a planar surface of the unscaled three-dimensional building model to corresponding pixels in the geo-referenced top-view orthogonal image.

### Claim 27 (depends on 21)

The method of claim 21, wherein generating the measurement between the third pixel and the fourth pixel of the three-dimensional building model based on the derived geometric scale comprises:
receiving a selection of the third pixel;
receiving a selection of the fourth pixel;
determining, in three-dimensional space, a linear distance between the third pixel and the fourth pixel; and
converting the linear distance to a geometric distance based on the derived geometric scale, wherein generating the measurement is further based on the geometric distance.

### Claim 28

One or more non-transitory computer-readable media storing instructions that, when executed by a system comprising one or more processors, cause the one or more processors to perform operations comprising:
receiving a plurality of ground-level images capturing a building object; determining a location associated with the plurality of ground-level images;
generating an unscaled three-dimensional building model from a set consisting of the plurality of ground-level images, wherein the unscaled three-dimensional building model represents the building object as a plurality of pixels in a three-dimensional space;
receiving a geo-referenced top-view orthogonal image of the building object based on the location associated with the plurality of ground-level images, wherein the geo-referenced top-view orthogonal image represents the building object as a plurality of pixels in a two-dimensional space;
matching a first three-dimensional pixel and a second three-dimensional pixel of the unscaled three-dimensional building model to corresponding two-dimensional pixels in the geo-referenced top-view orthogonal image;
deriving a geometric scale relative among all pixels of the three-dimensional building model based on the matching; and
generating a measurement between a third pixel and a fourth pixel of the three-dimensional building model based on the derived geometric scale.

### Claim 29 (depends on 28)

The one or more non-transitory computer-readable media of claim 28, wherein the plurality of ground-level images are captured using a smartphone.

### Claim 30 (depends on 28)

The one or more non-transitory computer-readable media of claim 28, wherein generating the unscaled three-dimensional building model comprises:
generating a three-dimensional point cloud of the building object from the set consisting of the plurality of ground-level images.

### Claim 31 (depends on 30)

The one or more non-transitory computer-readable media of claim 30, wherein generating the unscaled three-dimensional building model further comprises:
identifying architectural features of the three-dimensional point cloud.

### Claim 32 (depends on 31)

The one or more non-transitory computer-readable media of claim 31, further comprising:
generating measurements of the architectural features based on the derived geometric scale.

### Claim 33 (depends on 28)

The one or more non-transitory computer-readable media of claim 28, wherein matching at least the first three-dimensional pixel and the second three-dimensional pixel of the unscaled three-dimensional building model to corresponding pixels in the geo-referenced top-view orthogonal image comprises:
matching at least two vertices of a planar surface of the unscaled three-dimensional building model to corresponding pixels in the geo-referenced top-view orthogonal image.

### Claim 34 (depends on 28)

The one or more non-transitory computer-readable media of claim 28, wherein generating the measurement between the third pixel and the fourth pixel of the three-dimensional building model based on the derived scale comprises:
receiving a selection of the third pixel;
receiving a selection of the fourth pixel;
determining, in three-dimensional space, a linear distance between the third pixel and the fourth pixel; and
converting the linear distance to a geometric distance based on the derived scale, wherein generating the measurement is further based on the geometric distance.
