# US 10,872,404 B1 · Method for detecting anomalies on or in the surface of a structure

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

- Number: US 10,872,404 B1
- Document ID: US10872404B1
- Status: Granted
- Kind: B1
- Application number: 16/761,671
- Filed: 2019-10-22
- Published: 2020-12-10
- Granted: 2020-12-22
- Earliest claimed: 2018-10-26
- Assignees: Roof Asset Management USA, Ltd.
- Applicants: Roof Asset Management USA, Ltd.
- Inventors: Joseph C. Cobb
- Web page: https://patentgrep.com/patent/US10872404B1

## CPC

- G06T 7/0004: {Industrial image inspection}
- G01J 5/02: Constructional details
- G01M 5/0091: {by using electromagnetic excitation or detection}
- G01J 2005/0077: {Imaging}
- G06T 2207/10024: Color image
- G06T 2207/10032: Satellite or aerial image; Remote sensing
- G06T 2207/10048: Infrared image
- G06T 2207/30184: Infrastructure
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G01J: MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY (light sources F21, H01J, H01K, H05B; investigating properties of materials by optical means G01N)
- G01M: TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR

## Abstract

Described herein is a method of detecting anomalies on a surface of a structure. The method may comprise taking a thermal image of the surface of the structure. The method may further comprise taking a visual image of the surface of the structure. The method may then comprise conducting a thermal image numerical analysis on the thermal image. The thermal image numerical analysis may comprise obtaining a thermal image numerical value table. The thermal image numerical analysis may then comprise obtaining a surface nominal thermal value of the surface material. The thermal image numerical analysis may then comprise eliminating a first subset of pixels having a thermal value within a nominal thermal variation from the plurality of pixels. The thermal image numerical analysis may then comprise comparing the thermal value of each pixel of the plurality of pixels not in the first subset of pixels to the surface nominal thermal value to identify at least one anomaly. The thermal image numerical analysis method may then comprise removing a first number (n1) of first anomalies from the thermal image numerical analysis. Finally, the method may comprise comparing the first anomalies from the thermal image numerical analysis to the visual image.

## Claims

### Claim 1

A method of detecting anomalies on a surface of a structure comprising: taking a thermal image of the surface of the structure,
conducting a thermal image numerical analysis on the thermal image wherein the thermal image numerical analysis comprises the steps of:
i. obtaining a thermal image numerical value table comprising a plurality of pixels with each pixel having an X coordinate, a Y coordinate, and a Z coordinate with the X coordinate and the Y coordinate corresponding to a specific spatial location of the pixel on the surface of the structure, and the Z coordinate corresponding to a thermal value of said pixel which is a real number greater than or equal to 0;
ii. obtaining a surface nominal thermal value;
iii eliminating a first subset of pixels from the plurality of pixels wherein each of the first subset of pixels has a thermal value which is within a nominal thermal variation of a surface material of the surface to the surface nominal thermal value;
iv. comparing a thermal value of each pixel of the plurality of pixels not in the first subset of pixels to the surface nominal thermal value to identify at least one anomaly;
v. comparing the thermal value of a second number (n2) of a second anomalies from the thermal image numerical value table wherein n2 is an integer greater than or equal to 0 to the surface nominal thermal value in order to identify a type of anomaly selected from a group consisting of an energy loss anomaly, and a live load anomaly, and
vi. removing a first number (ni) of first anomalies from the thermal image numerical value table wherein ni is an integer greater than or equal to 0, and the first anomalies are selected from the group consisting of at least one non-delta anomaly, at least one non-signature anomaly, at least one non-pattern anomaly, at least one non-visual anomaly, and at least one non-cavity anomaly.

### Claim 2 (depends on 1)

The method of claim 1, wherein the thermal image is taken at least 60 minutes after sunset on a sunny day.

### Claim 3 (depends on 2)

The method of claim 2, wherein the thermal image is taken at a time selected from the group consisting of no more than about 6 hours after sunset, no more than about 5 hours after sunset, no more than about 4 hours sunset, no more than about 3 hours after sunset, and no more than about 2 hours after sunset.

### Claim 4 (depends on 2)

The method of claim 2, wherein the thermal image is taken on a day in which a geographic location of the surface experiences no more than about 40% cloud cover during at least the 4 hour preceding sunset.

### Claim 5 (depends on 2)

The method of claim 2, wherein the thermal image is taken on a day in which a geographic location of the surface experiences no more than about 30% cloud cover during at least the 4 hour preceding sunset.

### Claim 6 (depends on 2)

The method of claim 2, wherein the thermal image is taken on a day in which a geographic location of the surface experiences no more than about 20% cloud cover during at least the 4 hour preceding sunset.

### Claim 7 (depends on 2)

The method of claim 2, wherein the thermal image is taken on a day in which a geographic location of the surface experiences no more than about 10% cloud cover during at least the 4 hour preceding sunset.

### Claim 8 (depends on 1)

The method of claim 1, further comprising the steps of:
C. taking a visual image of the surface of the structure; and
D. comparing the first anomalies from the thermal image numerical analysis to the visual image.

### Claim 9 (depends on 8)

The method of claim 8, wherein the visual image is taken at or around solar noon on the same day as the thermal image.

### Claim 10 (depends on 1)

The method of claim 1, wherein obtaining the surface nominal thermal value comprises calculating the most prevalent thermal value across a second subset of the pixels.

### Claim 11 (depends on 10)

The method of claim 10, wherein the second subset of the plurality of pixels comprises a percentage of total pixels of the thermal image selected from the group consisting of at least 20% of the total pixels, at least 35% of the total pixels, at least 50% of the total pixels, at least 65% of the total pixels, at least 90% of the total pixels, at least 99% of the total pixels, and 100% of the total pixels.

### Claim 12 (depends on 1)

The method of claim 1, wherein the step of comparing a thermal value of each pixel of the plurality of pixels to the surface nominal thermal value yields an intensity value for each thermal value corresponding to each individual pixel calculated according to a formula:
(MTV)−(NTV)=IV
where MTV is the thermal value of each pixel and NTV is the surface nominal thermal value.

### Claim 13 (depends on 12)

The method of claim 12, wherein the intensity value is calculated for each pixel of the plurality of pixels which make up the thermal image numerical value table.

### Claim 14 (depends on 12)

The method of claim 12, wherein the intensity value is calculated for a third subset of the plurality of pixels comprising a percentage of the total pixels of the thermal image selected from the group consisting of at least 20% of the total pixels, at least 35% of the total pixels, at least 50% of the total pixels, at least 65% of the total pixels, at least 90% of the total pixels, at least 99% of the total pixels, and 100% of the total pixels.

### Claim 15 (depends on 12)

The method of claim 12, wherein the intensity value of each pixel of the plurality of pixels is plotted on a three dimensional graph.

### Claim 16 (depends on 1)

The method of claim 1, wherein obtaining the surface nominal thermal value comprises calculating the most prevalent thermal value across a second sub-set of the pixels.

### Claim 17 (depends on 16)

The method of claim 16, wherein the second subset of the plurality of pixels comprises a percentage of total pixels of the thermal image selected from the group consisting of at least 20% of the total pixels, at least 35% of the total pixels, at least 50% of the total pixels, at least 65% of the total pixels, at least 90% of the total pixels, at least 99% of the total pixels, and 100% of the total pixels.

### Claim 18 (depends on 1)

The method of claim 1, wherein the step of comparing a thermal value of each pixel of the plurality of pixels to the surface nominal thermal value yields an intensity value for each thermal value corresponding to each individual pixel calculated according to a formula:
(MTV)−(NTV)=IV
where MTV is the thermal value of each pixel and NTV is the surface nominal thermal value.

### Claim 19 (depends on 18)

The method of claim 18, wherein the intensity value is calculated for each pixel of the plurality of pixels which make up the thermal image numerical value table.