# US 2019/0065696 A1 · System, Apparatus and Method for Hierarchical Identification, Multi-Tier Target Library Processing, and Two-Stage Identification

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

- Number: US 2019/0065696 A1
- Document ID: US20190065696A1
- Status: Published application
- Kind: A1
- Application number: 16/108,737
- Filed: 2018-08-22
- Published: 2019-02-28
- Earliest claimed: 2017-08-22
- Assignees: Geospatial Technology Associates LLC
- Applicants: Geospatial Technology Associates LLC
- Inventors: William F. Basener
- Web page: https://patentgrep.com/patent/US20190065696A1

## CPC

- G16C 20/20: Identification of molecular entities, parts thereof or of chemical compositions
- G01J 3/2823: {Imaging spectrometer}
- G01N 21/31: Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry {(G01N21/72 takes precedence)}
- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06F 18/24323: {Tree-organised classifiers}
- G06V 10/764: using classification, e.g. of video objects
- G16B 35/00: ICT specially adapted for in silico combinatorial libraries of nucleic acids, proteins or peptides
- G16C 20/60: In silico combinatorial chemistry
- G01N 2021/1793: {Remote sensing}
- G06V 10/58: relating to hyperspectral data
- G06V 20/194: {using hyperspectral data, i.e. more or other wavelengths than RGB}
- G06V 2201/07: Target detection
- G16C 20/70: Machine learning, data mining or chemometrics
- G16C 20/90: Programming languages; Computing architectures; Database systems; Data warehousing
- G16C: COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- 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)
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY

## Abstract

Embodiments of a system, method and apparatus incorporate two-stage identification of targets in hyperspectral image analysis. In various embodiments, unmixing is employed that integrates F-test and model averaging approaches. Further, a multi-tier target library process provides an improvement in the spectra that can be used to detect target materials and spectra that can be used for unmixing in identification. Additionally, the hierarchical identification of the present disclosure combines probabilities from model averaging to generate target identifications simultaneously at multiple levels of specificity.

## Claims

### Claim 1

A method for detection and identification of target material in spectral imagery, comprising:
storing a first set of spectra for a plurality of target materials in a target detection library;
determining, by an apparatus using the target detection library, a target detection score representing the likelihood of presence of at least one of the plurality of target materials in each of a plurality of pixels in a spectral image;
storing a second set of spectra for a plurality of target materials in a target identification library; and
determining, by the apparatus using the target identification library, a material identification score representing a likely identification of one or more of the plurality of target materials for each of the plurality of pixels.

### Claim 2 (depends on 1)

The method of claim 1, wherein the first set of spectra stored in the target detection library is different from the second set of spectra stored in the target identification library.

### Claim 3 (depends on 1)

The method of claim 1, wherein a subset of the first set of spectra stored in the target detection library is the same as a subset of the second set of spectra stored in the target identification library.

### Claim 4 (depends on 1)

The method of claim 1, wherein the target detection score for each of the plurality of pixels is determined simultaneously, and wherein the material identification score for each of the plurality of pixels is determined simultaneously.

### Claim 5 (depends on 1)

The method of claim 1, wherein the plurality of target materials comprises a plurality of multi-level hierarchical target material class designations, and wherein the material identification score is determined simultaneously for each of the plurality of multi-level hierarchical target material class designations.

### Claim 6 (depends on 1)

The method of claim 1, further comprising determining the first set of spectra and the second set of spectra.

### Claim 7 (depends on 2)

The method of claim 2, wherein the first set of spectra comprises at least one mixture of one or more of the target materials with at least one additional non-target material.

### Claim 8 (depends on 2)

The method of claim 2, wherein the second set of spectra comprises at least one low abundance target material.

### Claim 9 (depends on 1)

The method of claim 1, wherein determining a material identification score comprises determining a model selection metric for each of a plurality of linear mixture models and applying model averaging on the plurality of linear mixture models.

### Claim 10 (depends on 9)

The method of claim 9, wherein determining a material identification score further comprises, after determining the model selection metrics for each of the plurality of linear mixture models, rejecting one or more of the plurality of linear mixture models.

### Claim 11

An apparatus for detecting and identifying target material in spectral imagery, comprising:
at least one processor;
at least one memory device storing a plurality of instructions which, when executed by the at least one processor, cause the at least one processor to:
determine, using a target detection library, a target detection score representing the likelihood of presence of at least one of a plurality of target materials in each of a plurality of pixels in a spectral image;
determine, using a target identification library, a material identification score representing a likely identification of one or more of the plurality of target materials for each of the plurality of pixels.

### Claim 12 (depends on 11)

The apparatus of claim 11, wherein the target detection library comprises a first set of spectra, the target identification library comprises a second set of spectra, and the first set of spectra is different from the second set of spectra.

### Claim 13 (depends on 11)

The apparatus of claim 11, wherein the plurality of target materials comprises a plurality of multi-level hierarchical target material class designations, and wherein the material identification score is determined simultaneously for each of the plurality of multi-level hierarchical target material class designations.

### Claim 14 (depends on 12)

The apparatus of claim 12, wherein the first set of spectra comprises at least one mixture of one or more of the plurality of target materials with at least one additional non-target material.

### Claim 15 (depends on 12)

The apparatus of claim 12, wherein the second set of spectra comprises at least one low abundance target material.

### Claim 16 (depends on 11)

The apparatus of claim 11, wherein the plurality of instructions further cause the at least one processor to determine a model selection metric for each of a plurality of linear mixture models and apply model averaging on the plurality of linear mixture models.

### Claim 17

A system, comprising:
an apparatus comprising at least one processor and at least one memory device storing a plurality of instructions which, when executed by the at least one processor, cause the at least one processor to:
receive at least one spectral image comprising a plurality of pixels;
determine, using a target detection library, a target detection score representing the likelihood of presence of at least one of a plurality of target materials in at least one pixel of the at least one spectral image; and
determine, using a target identification library, a material identification score representing a likely identification of one or more of the plurality of target materials for the at least one pixel; and
an interface in communication with the at least one processor representing the material identification score for the one or more of the plurality of target materials for the at least one pixel.

### Claim 18 (depends on 17)

The system of claim 17, wherein the plurality of target materials comprises a plurality of multi-level hierarchical target material class designations, and wherein the plurality of instructions cause the at least one processor to simultaneously determine the material identification score for each of the plurality of multi-level hierarchical target material class designations.

### Claim 19 (depends on 17)

The system of claim 17, wherein the plurality of instructions further cause the at least one processor to determine a model selection metric for each of a plurality of linear mixture models and apply model averaging on the plurality of linear mixture models.

### Claim 20 (depends on 17)

The system of claim 17, wherein a first set of spectra for a plurality of target materials is stored in the target detection library, a second set of spectra for a plurality of target materials is stored in the target identification library, and the first set of spectra is different from the second set of spectra.
