Hyperspectral band selection method based on multi-data-set collaborative analysis, and storage medium

A band selection and hyperspectral technology, applied in the field of image processing, can solve problems such as inability to guide band selection, and achieve the effect of promoting knowledge sharing, promoting the search process, and improving the performance of band selection

Pending Publication Date: 2022-01-28
NORTHWESTERN POLYTECHNICAL UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The traditional band selection algorithm only analyzes one data set at a time, searches the band subset from knowledge zero, and cannot effectively mine spectral information from high-dimensional hyperspectral images to guide band selection

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 based on multi-data-set collaborative analysis, and storage medium
  • Hyperspectral band selection method based on multi-data-set collaborative analysis, and storage medium
  • Hyperspectral band selection method based on multi-data-set collaborative analysis, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] See figure 1 and figure 2 , figure 1 is a schematic flowchart of a hyperspectral band selection method based on collaborative analysis of multiple data sets provided by an embodiment of the present invention, figure 2 is a process schematic diagram of a hyperspectral band selection method based on collaborative analysis of multiple data sets provided by an embodiment of the present invention. This embodiment provides a hyperspectral band selection method based on collaborative analysis of multiple data sets, the hyperspectral band selection method includes steps S1 to S6, wherein:

[0062] S1. Acquire K hyperspectral data sets, where each hyperspectral data set corresponds to a band selection task, and an initial population including POP individuals is generated based on each band selection task.

[0063] Specifically, given multiple hyperspectral datasets {D 1 ,D 2 ,...,D K}, each hyperspectral data set is a hyperspectral image, and K band selection tasks are e...

Embodiment 2

[0131] Yet another embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0132] S1. Acquire K hyperspectral data sets, wherein each hyperspectral data set corresponds to a band selection task, and an initial population including POP individuals is generated based on each band selection task;

[0133] S2. Let the number of initialization iterations g=1, and calculate the fitness value of each individual in each of the initial populations based on the objective function;

[0134] S3. Based on the relationship between the random number and the crossover probability, perform crossover or mutation operations on the parent individuals in the current population to obtain the first offspring individuals;

[0135] S4. Based on the cross-dataset migration probability, perform a crossover operation on the parent individuals betw...

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 discloses a hyperspectral band selection method based on multi-data-set collaborative analysis, and a storage medium. The method comprises the following steps: acquiring K hyperspectral data sets; calculating fitness values of individuals in each initial population; performing crossover or mutation operation on parent individuals in a current population to obtain first offspring individuals; performing crossover operation on parent individuals among the current population according to a cross-data migration probability to obtain second filial generation individuals; updating the current population according to the fitness values and updating the cross-dataset migration probability according to a migration probability function; selecting individuals with a highest fitness value as an optimal wave band of the current population and outputting the optimal wave band. According to the invention, a hyperspectral multi-data-set waveband selection collaborative analysis framework is constructed, and the waveband selection performance of each data set is improved by using a same spectral range and similar spectrum-space structures of the data sets.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a hyperspectral band selection method based on collaborative analysis of multiple data sets and a storage medium. Background technique [0002] Hyperspectral images are widely used in farmland detection, urban planning, atmospheric science, and military reconnaissance. Compared with other remote sensing images, hyperspectral can realize the simultaneous acquisition of ground object spatial information, radiation information and spectral information, so it has been widely studied. However, the high-dimensional data of hyperspectral images also brings challenges while providing rich spectral information. First, there is a correlation between adjacent spectral bands in hyperspectral images, and the information redundancy increases. Second, the detailing of spectral information leads to the "Hughes phenomenon" in classification. Finally, high-dimensional data h...

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): G06K9/00G06K9/62
CPCG06F2218/12G06F18/24
Inventor 侍佼张曦周德云雷雨李枭扬谭春晖吴天成
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap