Unlock instant, AI-driven research and patent intelligence for your innovation.

Hyperspectral band selection method, device and apparatus and storage medium

A band selection and hyperspectral technology, which is applied in measuring devices, color/spectral characteristic measurement, material analysis through optical means, etc., can solve the problem of low data volume processing speed, low business degree, and hyperspectral data band selection rate Low and other problems, to achieve the effect of increasing the speed

Active Publication Date: 2021-08-20
中国自然资源航空物探遥感中心
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the embodiments of the present application is to provide a hyperspectral band selection method, device, device, and storage medium to solve the problem of low rate of hyperspectral data band selection by using data parallelism and task parallelism, and further solve the current problem based on big data. In the selection of lower hyperspectral bands, due to the large amount of data, the processing speed is low and the degree of business is not high. This is a technical problem

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Hyperspectral band selection method, device and apparatus and storage medium
  • Hyperspectral band selection method, device and apparatus and storage medium
  • Hyperspectral band selection method, device and apparatus and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] see figure 1 ,Such as figure 1 As shown, the embodiment of the present application discloses a schematic flowchart of a hyperspectral band selection method. Such as figure 1 As shown, the method of the embodiment of the present application includes:

[0052] 101. Read the band data and mineral composition data of the hyperspectral ground features;

[0053] 102. Determine whether the data volume of the band data and mineral component data measured by the hyperspectral ground features exceeds the memory of the host, and if it exceeds, the band data and mineral component data of the hyperspectral ground features are measured according to the preset threshold Perform data block;

[0054] 103. Construct a hyperspectral band selection model combining data parallelism and task parallelism according to the block data;

[0055] 104. According to the hyperspectral band selection model, the band data and mineral component data of the segmented hyperspectral ground features ar...

Embodiment 2

[0083] see image 3 , image 3 It is a schematic structural diagram of a hyperspectral band selection device disclosed in an embodiment of the present application. Such as image 3 As shown, the device of the embodiment of the present application includes:

[0084] The reading module 201 is used to read the band data and mineral composition data of the hyperspectral ground objects;

[0085] Judgment module 202, for judging whether the data volume of the band data and the mineral composition data of the hyperspectral surface object actually measured exceeds the memory of the host computer, if exceeding, then according to the preset threshold value, the band data and the mineral composition data of the hyperspectral surface object actually measured Mineral components for data block;

[0086] A construction module 203, configured to construct a hyperspectral band selection model combining data parallelism and task parallelism according to the block data;

[0087] The data pr...

Embodiment 4

[0098] The embodiment of the present application discloses a storage medium, the storage medium stores a computer program, and the computer program is executed by a processor to select the hyperspectral band selection method disclosed in the first embodiment of the present application.

[0099] The storage medium of the embodiment of the present application judges whether the data volume of the band data and the mineral composition data of the hyperspectral ground features actually measured exceed the memory of the host, and then can perform the measurement of the hyperspectral ground features measured band data and data according to the preset threshold. Mineral component data block According to the preset threshold, the data of the band data and mineral components measured by the hyperspectral ground features are divided into data blocks and read into the host in sequence, so that the hyperspectral band combined with data parallelism and task parallelism can be constructed Se...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a hyperspectral band selection method, device and apparatus and a storage medium. The method comprises the steps of: reading actually measured wave band data and mineral component data of a hyperspectral ground object; judging whether the data volume of the actually measured wave band data of a hyperspectral ground object and the data volume of mineral component data exceed the memory of a host or not, and under the condition that the data volume of the actually measured wave band data of the hyperspectral ground object and and the data volume of the mineral component data exceed the memory of the host, performing data partitioning on the actually measured wave band data of the hyperspectral ground object and the mineral component data according to a preset threshold value; constructing a data parallelism and task parallelism combined hyperspectral band selection model according to the partitioned data; processing the partitioned actually measured wave band data of the hyperspectral ground object and the mineral component data according to the hyperspectral band selection model; and outputting the maximum correlation coefficient of the actually measured wave band of the hyperspectral ground object and the mineral component data data and a wave band range corresponding to the maximum correlation coefficient. According to the method of the invention, the rate of the wave band selection stage of massive hyperspectral image data can be effectively improved.

Description

technical field [0001] The present application relates to the technical field of remote sensing data processing, in particular, to a hyperspectral band selection method, device, equipment and storage medium. Background technique [0002] Hyperspectral remote sensing data includes triple information of space, radiation and spectrum. The amount of data in industrial applications has reached TB level, which has reached the level of massive data. The massive nature of data severely restricts the expansion of applications and the improvement of the efficiency of practical engineering applications. In hyperspectral band selection, if the traditional serial method is used, the calculation amount will reach hundreds of millions of floating point multiplication and addition operations; the complexity of a large number of data operations and processing determines that hyperspectral remote sensing image data processing has a strong However, ordinary computers and expensive special har...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G01N21/25
CPCG01N21/25G01N2021/1793Y02A40/10
Inventor 王梦飞贾伟洁和书慧陈嘉威边宇李佳
Owner 中国自然资源航空物探遥感中心