Spectral image classification of rooftop condition for use in property insurance

• US 8,775,219 B2
• Filed: 07/13/2012
• Issued: 07/08/2014
• Est. Priority Date: 07/13/2012
• Status: Active Grant

• Current Assignee: Northrop Grumman Systems Corporation (Northrop Grumman Corporation)
• Original Assignee: Northrop Grumman Systems Corporation (Northrop Grumman Corporation)
• Inventors: Swanson, Aaron L., Helmlinger, Mark C.
• Primary Examiner(s): Norman, Samica L
• Application Number:
  US13/548,878
• Publication Number:
  US 20140019166A1
• Time in Patent Office: 725 Days
• Field of Search: 705/4, 702/156
• US Class Current: 705/4
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G06Q 50/16 Real estate

Abstract

A method and apparatus is disclosed for applying high resolution spectral imaging (hyperspectral or multispectral) to property characterization, specifically rooftop classification of type and condition using reference data for insurance applications. The system can also be used to classify the condition of vegetation and property hazards. Classifying rooftop type and condition using remote spectral imaging greatly improves quantitative accuracy of roof inspections and decreases the cost of inspection across large geographic domains. By comparing the spatially subset spectral reflection of rooftops to a reference spectra, the rooftop type and condition can be accurately assessed. The aerial inspection produces uniform and consistent data can be ingested into property insurance evaluations for many different uses. The cost of residential property inspections and re-inspections performed via manual visual inspection is reduced and a geospatial database for the targeted residential and commercial property region that can be used for sustained property assessment is created.

Claims

1. A method for aerially assessing roof type and conditions in a geographic area to determine property liability, comprising the steps of:

creating a database, coupled to a computer processor, of spectral information for roof materials found in the geographic area;

building, by said computer processor, a model of the geographic area to identify roof objects using aerial photos;

mapping the geographic area using an airborne hyperspectral or multi-spectral imager to collect high resolution aerial spectral images;

measuring, by said computer processor, requisite geopositional data to accurately locate aerial imagery to geographic area of interest;

analyzing, by said computer processor, the high resolution aerial spectral images to characterize the condition of roof objects according to the geographic property model by comparing the images with the reference spectral information from the database;

associating, by said computer processor, the roof objects with geographic identifications of specific properties; and

developing property liability assessments for the specific properties based on the comparisons.

2. The method of claim 1 wherein the spectral information comprises hyperspectral image (HSI) or multispectral (MSI) data.

3. The method of claim 1 wherein the database of spectral information further comprises data associating high resolution aerial spectral images with roof material from specific manufacturers.

4. The method of claim 1, wherein the mapping step is performed by a space borne spectral imager that uses PAN sharpening or other high geospatial resolution to obtain spectral imagery at sub-meter to meter resolution for geographic area of interest.

5. The method of claim 1 wherein the database of spectral information further comprises data associating high resolution aerial spectral images with spectral response curves indicating aging impacts on roof material.

6. The method of claim 5 wherein the database further comprises spectral response curves indicating weathering impacts, vegetation impacts, storm impacts and solar radiation impacts on roof material.

7. A system for assessing roof conditions to determine property liability comprising:

one or more databases for storing spectral information for roof materials, said spectral information including at least one of aging impacts on roof material, weathering impacts on roof material, vegetation impacts on roof material, storm impacts on roof material, or solar radiation impacts on roof material;

an airborne spectral imager for collecting spectral images of a geographic area;

a processor for building a geospatial model of the geographic area to identify roof objects, for analyzing the spectral images to characterize the condition of roof objects identified by the model by comparing the roof objects with reference spectral information stored in the database, associating the roof objects with geographic identifications of specific properties and for developing property liability assessments based on the comparisons.

8. The system of claim 7, wherein the airborne spectral imager is a spaceborne spectral imager that uses PAN sharpening or other high geospatial resolution to obtain spectral imagery at sub-meter to meter resolution for geographic area.

9. The system of claim 7 further comprising:

a display, coupled to the processor, for presenting the property liability assessments to a user of the system.

10. The system of claim 9 wherein the property liability assessments further comprise one or more of reports, maps and data tables.

11. The system of claim 7 wherein the spectral images comprises hyperspectral image (HSI) or multispectral image (MSI) data.

12. A property insurance liability assessment business method comprising the steps of:

creating a database, coupled to a computer processor, of spectral information for roof materials found in the geographic area;

building, by said computer processor, a model of the geographic area to identify roof objects using digital aerial photography;

mapping the geographic area using an airborne spectral imager to collect hyperspectral images;

analyzing, by said computer processor, spectral images to characterize the condition of roof objects according to the model by comparing the spectral images with the reference spectral information from the database;

associating, by said computer processor, the roof objects with geographic identifications of specific properties; and

developing property liability assessments for the specific properties based on the comparisons.

13. The method of claim 12 wherein the spectral images comprise hyperspectral image (HSI) or multispectral (MSI) data.

14. The method of claim 12 wherein the database of spectral information further comprises data associating high resolution aerial spectral images with roof material from specific manufacturers.

15. The method of claim 12, wherein the mapping step is performed by a space borne spectral imager that uses PAN sharpening or other high geospatial resolution to obtain spectral imagery at sub-meter to meter resolution for geographic area of interest.

16. The method of claim 12 wherein the database of spectral information further comprises data associating high resolution aerial spectral images with spectral response curves indicating aging impacts on roof material.

17. The method of claim 16 wherein the database further comprises spectral response curves indicating weathering impacts, vegetation impacts, storm impacts and solar radiation impacts on roof material.

18. A computer program product comprising a non-transitory computer readable storage medium having computer program logic recorded thereon for enabling a processor to analyze hyperspectral images to determine roof condition to determine property liability, said computer program logic comprising:

a receiving procedure for receiving spectral images and aerial photography of a geographic area;

a modeling procedure for building a model of the geographic area and identifying roof objects from the aerial photography;

an analyzing procedure for comparing spectral images of an identified roof object with spectral information stored in a database;

an associating procedure for associating roof objects with geographic identifications of specific properties; and

a reporting procedure for developing property liability assessments for the specific properties based on the comparisons.

19. The computer program product of claim 18 wherein the spectral images comprise hyperspectral image (HSI) or multispectral image (MSI) data.

20. The computer program product of claim 18 wherein the reporting procedure further comprises procedures for generating reports in the form of maps or data tables.