# US 12,602,758 B1 · Building leakage detector using reference-free background oriented schlieren photography

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

- Number: US 12,602,758 B1
- Document ID: US12602758B1
- Status: Granted
- Kind: B1
- Application number: 18/377,580
- Filed: 2023-10-06
- Granted: 2026-04-14
- Earliest claimed: 2023-03-17
- Assignees: UT-Battelle, LLC
- Applicants: UT-Battelle, LLC
- Inventors: Philip R. Boudreaux; Singanallur Vaidyanathan Venkatakrishnan; Emishaw D. Iffa; Diana E. Hun; William Powell Partridge, Jr.; Gurneesh Singh Jatana; Rui Zhang
- Web page: https://patentgrep.com/patent/US12602758B1

## CPC

- G01M 3/38: by using light (G01M3/02 takes precedence)
- G06T 7/0002: {Inspection of images, e.g. flaw detection}
- G06T 7/001: {using an image reference approach}
- G06T 7/11: Region-based segmentation
- G06T 7/215: Motion-based segmentation
- G06T 7/248: {involving reference images or patches}
- G06T 7/269: using gradient-based methods
- G06T 7/40: Analysis of texture (depth or shape recovery from texture G06T7/529)
- G01M 3/04: by detecting the presence of fluid at the leakage point
- G06T 2207/10016: Video; Image sequence
- G06T 2207/10048: Infrared image
- G06T 2207/30132: Masonry; Concrete
- G06T 2207/30184: Infrastructure
- G01M: TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A non-invasive technique to measure exfiltration and infiltration (leakage) in buildings including a system and method employing RFN-BOS photography. Leakage through a building envelope can be visualized using RFN-BOS photography when the background has sufficient texture and the temperature difference between the leakage and ambient air is sufficient. Leakage can be detected when there is a temperature difference of as low as 12° C.-15° C. through CMU and brick claddings. A minimum ΔT detection limit can be reduced to 5° C. so that the RFN-BOS technique can be used through all climate zones, and use of a sufficiently textured cladding in which the contrast textural feature is at 1,650 or greater. If the cladding has insufficient texture, the system uses a projection system to first project a high contrasting image pattern on the cladding surface. Prioritized sealing of leaks is provided based on an order of their corresponding leak-ranking parameters.

## Claims

### Claim 1

A system for detecting leaks at a surface of a building structure, the system comprising:
a video camera disposed at a predetermined distance from a surface of the building structure, the video camera capturing images of a surface of the building structure; and
a hardware processor associated with a memory storing program instructions in a computer system, the hardware processor running the program instructions configuring the processor to:
detect, from said received image information, differences in light intensity at corresponding pixel locations in successive image frames;
provide a visualization of an air flow movement based on detected differences in light intensities at the corresponding pixel locations in successive images;
identify and isolate one or more regions of interest within said air flow visualization, a region of interest (ROI) corresponding to a location indicating a potential leak at the surface of the structure;
obtain one or more flow parameters characterizing the air flow movement within said ROI; and
identify, based on said obtained one or more flow parameters, a location and magnitude of said potential leak at the surface of the building structure.

### Claim 2 (depends on 1)

The system as claimed in claim 1, wherein said one or more flow parameters comprises:
a pixel-shift parameter representing a refractive-feature displacement obtained based on a cross correlation computation of the air flow movement in sequential difference images of said captured images.

### Claim 3 (depends on 2)

The system as claimed in claim 2, wherein said air flow movement is an air turbulence, said hardware processor is further configured to:
identify a plume region corresponding to said air turbulence, said plume region corresponding to a diameter of the leak; and
estimate a cross-sectional area bound of the plume region.

### Claim 4 (depends on 3)

The system as claimed in claim 3, wherein said hardware processor is further configured to compute an air flow velocity based on said obtained refractive-feature displacement, said one or more flow parameters comprise:
a volumetric flow rate parameter (Q) obtained based on a multiplication of the obtained computed air flow velocity with the estimated cross-sectional area bound of the plume region.

### Claim 5 (depends on 2)

The system as claimed in claim 2, wherein said air flow movement is an air fluctuation, said hardware processor is further configured to:
identify a plume region corresponding to said air fluctuation, said plume region corresponding to a diameter of the potential leak; and
estimate a cross-sectional area bound of the plume region.

### Claim 6 (depends on 1)

The system as claimed in claim 1, wherein said visualization of the air flow movement is based on applying a background oriented Schlieren photographic technique.

### Claim 7 (depends on 1)

The system as claimed in claim 1, further comprising:
an image projection sub-system for projecting a high contrast image upon the building surface prior to the video camera capturing images of the surface, said projected image pattern increasing the apparent texture of the surface.

### Claim 8 (depends on 7)

The system as claimed in claim 7, wherein said image projection sub-system for projecting said high contrast image comprises a high resolution projector, said projected high contrast image comprising one of: a random dot pattern or linear pattern upon the low contrast material surface.

### Claim 9 (depends on 7)

The system as claimed in claim 7, wherein said image projection sub-system for projecting said high contrast image comprises a coherent laser light source with diffracting optics or pattern-generating optics or reticles, wherein coherent laser light is diffused to provide one or more of: a speckle pattern, a dot pattern or a shaped pattern upon the low contrast material surface.

### Claim 10 (depends on 7)

The system as claimed in claim 7, wherein said image projection sub-system for projecting said high contrast image comprises a high powered light source with pattern-generating optics for producing one or more of: a random dot pattern, a dot pattern, a linear pattern or a shaped pattern upon the low contrast material surface.

### Claim 11 (depends on 1)

The system as claimed in claim 1, wherein to isolate one or more regions of interest within said air flow visualization, the hardware processor is further configured to:
perform an image segmentation technique from said received image information.

### Claim 12

A computer program product for detecting leaks at a surface of a building structure, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor device to cause the device to:
receive image information from a sequence of images, said sequence of images being captured from a video camera disposed at a predetermined distance from a surface of the building structure;
detect, from said received image information, differences in light intensity at corresponding pixel locations in successive image frames;
provide a visualization of an air flow movement based on detected differences in light intensities at the corresponding pixel locations in successive images;
identify and isolate one or more regions of interest within said air flow visualization, a region of interest (ROI) corresponding to a location indicating a potential leak at the surface of the structure;
obtain one or more flow parameters characterizing the air flow movement within said ROL and
identify, based on said obtained one or more flow parameters, a location and magnitude of said potential leak at the surface of the building structure.

### Claim 13 (depends on 12)

The computer program product as claimed in claim 12, wherein said one or more flow parameters comprises:
a pixel-shift parameter representing a refractive-feature displacement obtained based on a cross correlation computation of the air flow movement in sequential difference images of said captured images.

### Claim 14 (depends on 13)

The computer program product as claimed in claim 13, wherein said air flow movement is an air turbulence, said program instructions further configuring the processor device to:
identify a plume region corresponding to said air turbulence, said plume region corresponding to a diameter of the leak.

### Claim 15 (depends on 13)

The computer program product as claimed in claim 13, wherein said air flow movement is an air fluctuation, said program instructions further configure the processor device to:
identify a plume region corresponding to said air fluctuation, said plume region corresponding to a diameter of the leak; and
estimate a cross-sectional area bound of the plume region.

### Claim 16 (depends on 13)

The computer program product as claimed in claim 13, wherein said program instructions further configure the processor device to compute an air flow velocity based on said obtained refractive-feature displacement, said one or more flow parameters comprise:
a volumetric flow rate parameter (Q) obtained based on a multiplication of the computed air flow velocity with the estimated cross-sectional area bound of the plume region.

### Claim 17 (depends on 12)

The computer program product as claimed in claim 12, wherein to isolate one or more regions of interest within said air flow visualization, said program instructions further configure the processor device to:
perform an image segmentation technique from said received image information.

### Claim 18

A method of detecting leaks at a surface of a building structure, the method comprising:
capturing, from a video camera device, a sequence of images, said video camera device disposed at a predetermined distance from a surface of the building structure;
detecting, from said received image information, using a hardware processor, differences in light intensity at corresponding pixel locations in successive image frames;
providing, using the hardware processor, a visualization of an air flow movement based on detected differences in light intensities at the corresponding pixel locations in successive images;
identifying and isolating, using the hardware processor, one or more regions of interest within said air flow visualization, a region of interest (ROI) corresponding to a location indicating a potential leak at the surface of the structure;
obtaining, using the hardware processor, one or more flow parameters characterizing the air flow movement within said ROI; and
identifying, based on said obtained one or more flow parameters, a location and magnitude of said potential leak at the surface of the building structure.

### Claim 19 (depends on 18)

The method as claimed in claim 18, wherein said one or more flow parameters comprises:
a pixel-shift parameter representing a refractive-feature displacement obtained based on a cross correlation computation of the air flow movement in sequential difference images of said captured images.

### Claim 20 (depends on 19)

The method as claimed in claim 19, wherein said air flow movement is an air turbulence, said method further comprising:
identifying, using the hardware processor, a plume region corresponding to said air turbulence, said plume region corresponding to a diameter of the leak.

### Claim 21 (depends on 20)

The method as claimed in claim 20, wherein said air flow movement is an air fluctuation, said method further comprising:
identifying, using the hardware processor, a plume region corresponding to said air fluctuation, said plume region corresponding to a diameter of the leak; and
estimating a cross-sectional area bound of the plume region.

### Claim 22 (depends on 19)

The method as claimed in claim 19, further comprising:
computing, using the hardware processor, an air flow velocity based on said obtained refractive-feature displacement, wherein said one or more flow parameters comprise:
a volumetric flow rate parameter (Q) obtained based on a multiplication of the computed air flow velocity with the estimated cross-sectional area bound of the plume region.

### Claim 23 (depends on 18)

The method as claimed in claim 18, further comprising:
detecting, using the hardware processor, a contrast level associated with a material surface of said building structure,
comparing said associated contrast level against a threshold contrast level, and responsive to detecting said associated contrast level below the threshold contrast level,
projecting, using an image projection sub-system, a high-contrasting image pattern upon the surface prior to the video camera capturing images of the surface.

### Claim 24 (depends on 23)

The method as claimed in claim 23, wherein said projected high-contrasting image pattern comprises one or more of: a speckle pattern, a random dot pattern, a dot pattern, a linear pattern, or a shaped pattern upon the low contrast material surface.

### Claim 25 (depends on 18)

The method as claimed in claim 18, wherein to isolate one or more regions of interest within said air flow visualization, said method further comprises:
performing, using the hardware processor, an image segmentation technique from said received image information.

### Claim 26

A method for prioritizing a sealing of leaks at a surface of a building structure, the method comprising:
capturing, from a video camera device, a sequence of images at a predetermined area of the surface of the building structure;
processing the captured sequence of images to detect an air flow movement indicating a leak at the predetermined area of the surface of the building structure;
for each detected air flow movement indicating a leak, determining a corresponding leak-ranking parameter of each air flow movement at the predetermined area;
repeating said projecting, capturing, air flow movement detection processing, and corresponding leak-ranking parameter determining for each detected air flow movement at each of a plurality of different predetermine areas of the surface;
determining, based on said leak-ranking parameters for all detected air flow movements at different predetermined areas, corresponding leaks having a largest corresponding leak-ranking parameter or volumetric flow rate and successively smaller leak-ranking parameters or volumetric flow rates; and
prioritizing actions to seal leaks at locations at the surface in an order corresponding to leaks having the largest corresponding leak-ranking parameter or volumetric flow rate and successively smaller leak-ranking parameters or volumetric flow rates.

### Claim 27 (depends on 26)

The method as claimed in claim 26, wherein the processing the captured sequence of images to detect an air flow movement indicating a leak at the predetermined area of the surface of the building structure comprises:
receiving, at a hardware processor, image information from said captured image sequence and processing the image information to:
detect from said received image information, differences in light intensity at corresponding pixel locations in successive image frames;
provide a visualization of the air flow movement based on detected differences in light intensities at the corresponding pixel locations in successive images;
identify and isolate one or more regions of interest within said air flow visualization, a region of interest (ROI) corresponding to a location indicating a potential leak at the surface of the structure;
obtain one or more flow parameters characterizing the air flow movement within said ROI; and
identify, based on said obtained one or more flow parameters, a location and magnitude of said potential leak at the surface of the building structure.

### Claim 28 (depends on 27)

The method as claimed in claim 27, wherein said one or more flow parameters comprises:
a pixel-shift parameter representing a refractive-feature displacement obtained based on a cross correlation computation of the air flow movement in sequential difference images of said captured images.

### Claim 29 (depends on 28)

The method as claimed in claim 28, wherein said air flow movement comprises an air turbulence, said method further comprising:
identifying, using the processor device, a plume region corresponding to said air turbulence, said plume region corresponding to a velocity of the leak.

### Claim 30 (depends on 18)

The method as claimed in claim 18, wherein said air flow movement comprises an air fluctuation, said method further comprising:
identifying, using the hardware processor, a plume region corresponding to said air fluctuation, said plume region corresponding to a diameter of the leak; and
estimating a cross-sectional area bound of the plume region.

### Claim 31 (depends on 30)

The method as claimed in claim 30, further comprising:
computing an air flow velocity based on said obtained refractive-feature displacement, wherein said one or more flow parameters comprise:
a volumetric flow rate parameter (Q) obtained based on a multiplication of the computed air flow velocity with the estimated cross-sectional area bound of the plume region.

### Claim 32 (depends on 26)

The method as claimed in claim 26, wherein said processing the captured sequence of images to detect the air flow movement indicating a leak at the predetermined area of the surface of the building structure comprises:
applying a Background Oriented Schlieren (BOS) photographic technique.