# US 12,217,503 B2 · Tidal flat extraction method based on hyperspectral data

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

- Number: US 12,217,503 B2
- Document ID: US12217503B2
- Status: Granted
- Kind: B2
- Application number: 18/808,129
- Filed: 2024-08-19
- Published: 2025-01-09
- Granted: 2025-02-04
- Earliest claimed: 2023-07-04
- Assignees: Ningbo University
- Applicants: Ningbo University
- Inventors: Gang Yang; Weiwei Sun; Chunchen Shao; Xiangchao Meng; Tian Feng
- Web page: https://patentgrep.com/patent/US12217503B2

## CPC

- G06V 20/194: {using hyperspectral data, i.e. more or other wavelengths than RGB}
- G06F 18/00: Pattern recognition
- G06V 10/22: by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V 10/32: Normalisation of the pattern dimensions
- G06V 10/58: relating to hyperspectral data
- G06V 20/13: Satellite images
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

The provided is a tidal flat extraction method based on hyperspectral data. The method includes: acquiring and preprocessing hyperspectral data; calculating a constraint condition; calculating, according to the constraint condition, a normalized difference tidal flat index (NDTFI), generating a sample index statistical box chart, and determining a tidal flat extraction threshold according to the sample index statistical box chart; and removing a misclassified pixel based on a coastal buffer zone and a high spatial resolution image, thereby achieving final extraction of a tidal flat. The method has the following beneficial effects. The method is an effective supplement to the existing tidal flat extraction methods. The method adopts an easily realized process, improves the accuracy of tidal flat extraction, reflects the real spatial distribution of the tidal flat, and provides a scientific basis for tidal flat management and protection.

## Claims

### Claim 1

A tidal flat extraction method based on hyperspectral data, comprising:
S1, acquiring and preprocessing hyperspectral data, wherein the preprocessing comprises radiometric calibration, atmospheric correction, and orthorectification;
S2, calculating a constraint condition, comprising a first constraint condition w, a second constraint condition v, and a third constraint condition s;
S3, calculating, according to values of the first constraint condition w, the second constraint condition v, and the third constraint condition s, a normalized difference tidal flat index (NDTFI); generating a sample index statistical box chart; and determining a tidal flat extraction threshold according to the sample index statistical box chart; and
S4, removing a misclassified pixel based on a coastal buffer zone and a high spatial resolution image, thereby achieving final extraction of a tidal flat,
wherein in the step S2, the first constraint condition w is calculated as follows:
w=ρ1274+ρ1660−ρ1980+α1
wherein ρ1274 denotes a band value with a center wavelength of 1,274 nm, ρ1660 denotes a band value with a center wavelength of 1.660 nm, and ρ1980 denotes a band value with a center wavelength of 1,980 nm; and α1 denotes an offset coefficient of the first constraint condition w.

### Claim 2 (depends on 1)

The tidal flat extraction method based on the hyperspectral data according to claim 1, wherein in the step S2, the second constraint condition v is calculated as follows:
v=(ρ670−ρ979)+(ρ670−ρ1156)+α2
wherein ρ670 denotes a band value with a center wavelength of 670 nm, ρ979 denotes a band value with a center wavelength of 979 nm, and ρ1156 denotes a band value with a center wavelength of 1,156 nm; and α2 denotes an offset coefficient of the second constraint condition v.

### Claim 3 (depends on 2)

The tidal flat extraction method based on the hyperspectral data according to claim 2, wherein in the step S2, the third constraint condition s is calculated as follows:
s=ρ1105−ρ1031+α3
wherein ρ1031 denotes a band value with a center wavelength of 1,031 nm, and ρ1105 denotes a band value with a center wavelength of 1,105 nm; and α3 denotes an offset coefficient of the third constraint condition s.

### Claim 4 (depends on 3)

The tidal flat extraction method based on the hyperspectral data according to claim 3, wherein in the step S3, the NDTFI is calculated as follows:
NDTFI
=
{
ρ
⁢
816
-
ρ1980
ρ
⁢
816
+
ρ1980
⁢
w
>
0
,
v
>
0
,
s
>
0
-
❘
"\[LeftBracketingBar]"
ρ
⁢
816
-
ρ1980
ρ
⁢
816
+
ρ
⁢
1980
❘
"\[RightBracketingBar]"
⁢
w
<
0
⁢
or
⁢
v
<
0
⁢
or
⁢
s
<
0
wherein ρ816 denotes a band value with a center wavelength of 816 nm, and ρ1980 denotes a band value with a center wavelength of 1,980 nm.

### Claim 5 (depends on 4)

The tidal flat extraction method based on the hyperspectral data according to claim 4, wherein the step S3 comprises: distinguishing the tidal flat from a non-tidal-flat surface feature according to the tidal flat extraction threshold, wherein the tidal flat is expressed as follows:
NDTFI(m,n)≥mintf
wherein NDTFI(m,n) denotes the value of NDTFI at a location (m,n), and mint denotes a lower limit of the tidal flat extraction threshold.

### Claim 6 (depends on 5)

The tidal flat extraction method based on the hyperspectral data according to claim 5, wherein in the step S4, the high spatial resolution image is a sub-meter high spatial resolution image provided for visual comparison.

### Claim 7 (depends on 6)

The tidal flat extraction method based on the hyperspectral data according to claim 6, wherein in the step S2, final values of α1, α2, and α3 are determined through sensitivity analysis.

### Claim 8 (depends on 1)

A tidal flat extraction system based on hyperspectral data, configured to implement the tidal flat extraction method based on the hyperspectral data according to claim 1, and comprising:
a preprocessing module, configured to acquire and preprocess the hyperspectral data, wherein the preprocessing comprises the radiometric calibration, the atmospheric correction, and the orthorectification;
a first calculation module, configured to calculate the constraint condition, comprising the first constraint condition w, the second constraint condition v, and the third constraint condition s;
a second calculation module, configured to calculate, according to the values of the first constraint condition w, the second constraint condition v, and the third constraint condition s, the NDTFI; generate the sample index statistical box chart; and determine the tidal flat extraction threshold according to the sample index statistical box chart; and
an extraction module, configured to remove the misclassified pixel based on the coastal buffer zone and the high spatial resolution image, thereby achieving the final extraction of the tidal flat.

### Claim 9 (depends on 1)

A non-transitory computer storage medium, configured to store a computer program, wherein when the computer program runs on a computer, the computer performs the tidal flat extraction method based on the hyperspectral data according to claim 1.

### Claim 10 (depends on 8)

The tidal flat extraction system according to claim 8, wherein in the step S2 of the tidal flat extraction method, the second constraint condition v is calculated as follows:
v=(ρ670−ρ979)+(ρ670−ρ1156)+α2
wherein ρ670 denotes a band value with a center wavelength of 670 nm, ρ979 denotes a band value with a center wavelength of 979 nm, and ρ1156 denotes a band value with a center wavelength of 1,156 nm; and α2 denotes an offset coefficient of the second constraint condition v.

### Claim 11 (depends on 10)

The tidal flat extraction system according to claim 10, wherein in the step S2 of the tidal flat extraction method, the third constraint condition s is calculated as follows:
s=ρ1105−ρ1031+α3
wherein ρ1031 denotes a band value with a center wavelength of 1,031 nm, and ρ1105 denotes a band value with a center wavelength of 1,105 nm; and α3 denotes an offset coefficient of the third constraint condition s.

### Claim 12 (depends on 11)

The tidal flat extraction system according to claim 11, wherein in the step S3 of the tidal flat extraction method, the NDTFI is calculated as follows:
NDTFI
=
{
ρ
⁢
816
-
ρ1980
ρ
⁢
816
+
ρ1980
⁢
w
>
0
,
v
>
0
,
s
>
0
-
❘
"\[LeftBracketingBar]"
ρ
⁢
816
-
ρ1980
ρ
⁢
816
+
ρ
⁢
1980
❘
"\[RightBracketingBar]"
⁢
w
<
0
⁢
or
⁢
v
<
0
⁢
or
⁢
s
<
0
wherein ρ816 denotes a band value with a center wavelength of 816 nm, and ρ1980 denotes a band value with a center wavelength of 1,980 nm.

### Claim 13 (depends on 12)

The tidal flat extraction system according to claim 12, wherein the step S3 of the tidal flat extraction method comprises: distinguishing the tidal flat from a non-tidal-flat surface feature according to the tidal flat extraction threshold, wherein the tidal flat is expressed as follows:
NDTFI(m,n)≥mintf
wherein NDTFI(m,n) denotes the value of NDTFI at a location (m,n), and mint denotes a lower limit of the tidal flat extraction threshold.

### Claim 14 (depends on 13)

The tidal flat extraction system according to claim 13, wherein in the step S4 of the tidal flat extraction method, the high spatial resolution image is a sub-meter high spatial resolution image provided for visual comparison.

### Claim 15 (depends on 14)

The tidal flat extraction system according to claim 14, wherein in the step S2 of the tidal flat extraction method, final values of α1, α2, and α3 are determined through sensitivity analysis.

### Claim 16 (depends on 9)

The non-transitory computer storage medium according to claim 9, wherein in the step S2 of the tidal flat extraction method, the first constraint condition w is calculated as follows:
w=ρ1274+ρ1660−ρ1980+α1
wherein ρ1274 denotes a band value with a center wavelength of 1,274 nm, ρ1660 denotes a band value with a center wavelength of 1,660 nm, and ρ1980 denotes a band value with a center wavelength of 1,980 nm; and α1 denotes an offset coefficient of the first constraint condition w.

### Claim 17 (depends on 16)

The non-transitory computer storage medium according to claim 16, wherein in the step S2 of the tidal flat extraction method, the second constraint condition v is calculated as follows:
v=(ρ670−ρ979)+(ρ670−ρ1156)+α2
wherein ρ670 denotes a band value with a center wavelength of 670 nm, ρ979 denotes a band value with a center wavelength of 979 nm, and ρ1156 denotes a band value with a center wavelength of 1,156 nm; and α2 denotes an offset coefficient of the second constraint condition v.

### Claim 18 (depends on 17)

The non-transitory computer storage medium according to claim 17, wherein in the step S2 of the tidal flat extraction method, the third constraint condition s is calculated as follows:
s=ρ1105−ρ1031+α3
wherein ρ1031 denotes a band value with a center wavelength of 1,031 nm, and ρ1105 denotes a band value with a center wavelength of 1,105 nm; and α3 denotes an offset coefficient of the third constraint condition s.
