# US 2010/0076920 A1 · Data Fusion Framework for Wide-Area Assessment of Buried Unexploded Ordnance

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

- Number: US 2010/0076920 A1
- Document ID: US20100076920A1
- Status: Published application
- Kind: A1
- Application number: 12/490,107
- Filed: 2009-06-23
- Published: 2010-03-25
- Earliest claimed: 2008-06-24
- Assignees: The United States of America as represented by the Secretary of the Navy
- Inventors: Kevin J. Johnson; Christian P. Minor
- Web page: https://patentgrep.com/patent/US20100076920A1

## CPC

- G01V 11/00: Prospecting or detecting by methods combining techniques covered by two or more of main groups G01V1/00 - G01V9/00
- G01V 2210/665: using geostatistical modeling
- G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02)

## Abstract

A data fusion framework is provided for wide-area assessments of unexploded ordnance. One or more wide-area survey data sources representing assessments of geographic sites that may contain unexploded ordnance (UXO) can be analyzed by a data source module as part of the data fusion framework. The data sources can include a geographic registration and a degree of belief and the data source module can register the data sources to a common map grid. A feature layer module can extract a plurality of feature layers from the wide-area survey data sources. A feature map module can generate a plurality of feature maps for each of the plurality of feature layers based on the degree of belief. Finally, a data fusion module can combine the plurality of feature maps and generate a plurality of output maps. This output maps can then be used by UXO site managers to support decisions regarding remediation efforts.

## Claims

### Claim 1

A method for assessing a wide area of geographic sites for sensing and surveillance tasks, comprising the steps of:
analyzing one or more wide-area survey data sources;
extracting a plurality of feature layers from the wide-area survey data sources;
generating a plurality of feature maps for each of the plurality of feature layers;
combining the plurality of feature maps in a data fusion module; and
generating a plurality of output maps produced by the data fusion module.

### Claim 2 (depends on 1)

The method of claim 1, wherein the wide-area survey data sources comprise a geographic registration and a degree of belief.

### Claim 3 (depends on 1)

The method of claim 1, wherein the step of analyzing the one or more wide-area survey data sources comprises registering the wide-area survey data sources to a common map grid based on a geographic registration.

### Claim 4 (depends on 1)

The method of claim 1, wherein the step of analyzing the one or more wide-area survey data sources is performed by a data source module, wherein the data source module is implemented in a computer system that comprises instructions stored in a machine-readable medium and a processor that executes the instructions.

### Claim 5 (depends on 1)

The method of claim 1, wherein the step of extracting a plurality of feature layers from the wide-area survey data sources is performed by a feature layer module, wherein the feature layer module is implemented in a computer system that comprises instructions stored in a machine-readable medium and a processor that executes the instructions.

### Claim 6 (depends on 1)

The method of claim 1, further comprising the step of registering the plurality of feature layers to a common map grid based on a geographic registration.

### Claim 7 (depends on 1)

The method of claim 1, wherein the step of generating the plurality of feature maps for each of the plurality of feature layers is based on a degree of belief.

### Claim 8 (depends on 1)

The method of claim 1, wherein the step of generating the plurality of feature maps for each of the plurality of feature layers is performed by a feature map module, wherein the feature map module is implemented in a computer system that comprises instructions stored in a machine-readable medium and a processor that executes the instructions.

### Claim 9 (depends on 1)

The method of claim 1, wherein the step of generating the plurality of feature maps for each of the plurality of feature layers further comprises apportioning a unit probability mass across one or more frame of discernment elements for each possible value of feature map intensity.

### Claim 10 (depends on 1)

The method of claim 1, wherein the data fusion module is implemented in a computer system that comprises instructions stored in a machine-readable medium and a processor that executes the instructions.

### Claim 11 (depends on 1)

The method of claim 1, wherein the step of combining the plurality of feature maps in a data fusion module utilizes a Dempster-Shafer theory for probabilistic combination.

### Claim 12 (depends on 1)

The method of claim 1, wherein the step of combining the plurality of feature maps in a data fusion module further comprises the step of incorporating heuristic rules into the data fusion module to quantify known interdependencies between feature layers.

### Claim 13

A method for assessing a wide-area of geographic sites for unexploded ordnance, comprising the steps of:
analyzing one or more wide-area survey data sources in a data source module, wherein the wide-area survey data sources comprise a geographic registration and a degree of belief;
registering the wide-area survey data sources to a common map grid based on the geographic registration in the data source module;
extracting a plurality of feature layers from the wide-area survey data sources in a feature layer module;
generating a plurality of feature maps for each of the plurality of feature layers based on the degree of belief in a feature map module;
combining the plurality of feature maps in a data fusion module; and
generating a plurality of output maps produced by the data fusion module.

### Claim 14 (depends on 13)

The method of claim 13, wherein the step of combining the plurality of feature maps in the data fusion module further comprises the step of incorporating heuristic rules into the data fusion module to quantify known interdependencies between feature layers.

### Claim 15 (depends on 13)

The method of claim 13, wherein the data source module, feature layer module, feature map module, and data fusion module are implemented in a computer system that comprises instructions stored in a machine-readable medium and a processor that executes the instructions.

### Claim 16

A system for assessing a wide area of geographic sites for unexploded ordnance, comprising:
one or more wide-area survey data sources; and
a data fusion framework, comprising:
a data source module configured to analyze the one or more wide-area survey data sources and register the wide-area survey data sources to a common map grid;
a feature layer module configured to extract a plurality of feature layers from the wide-area survey data sources;
a feature map module configured to generate a plurality of feature maps for each of the plurality of feature layers based on a degree of belief; and
a data fusion module configured to combine the plurality of feature maps and generate a plurality of output maps.

### Claim 17 (depends on 16)

The system of claim 16, wherein the wide-area survey data sources comprise a geographic registration and a degree of belief.

### Claim 18 (depends on 17)

The system of claim 17, wherein the data source module is configured to register the wide-are survey data sources to the common grid based on the geographic registration.

### Claim 19 (depends on 16)

The system of claim 16, wherein the data fusion module is further configured to incorporate heuristic rules into the data fusion module to quantify known interdependencies between feature layers.

### Claim 20 (depends on 16)

The system of claim 16, wherein the data source module, feature layer module, feature map module, and data fusion module are implemented in a computer system that comprises instructions stored in a machine-readable medium and a processor that executes the instructions.
