Supercharge Your Innovation With Domain-Expert AI Agents!

A hyperspectral open set domain adaptation method based on multi-classifier domain adversarial network

A technology of multiple classifiers and classifiers, which is applied in the field of hyperspectral image open set classification, can solve problems such as low classification accuracy, long time consumption, and high cost of data labeling, and achieve low complexity, simple implementation, good classification performance and real-time effect

Active Publication Date: 2022-07-19
NAT UNIV OF DEFENSE TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide a hyperspectral open set field based on a multi-classifier domain confrontation network for the problems of high data labeling cost, time-consuming, and low classification accuracy in the hyperspectral image classification task in the open set scene. adaptive method

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
  • A hyperspectral open set domain adaptation method based on multi-classifier domain adversarial network
  • A hyperspectral open set domain adaptation method based on multi-classifier domain adversarial network
  • A hyperspectral open set domain adaptation method based on multi-classifier domain adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] An embodiment of the present invention provides a hyperspectral open set domain adaptation method based on a multi-classifier domain adversarial network, including:

[0038] S1: Acquire hyperspectral images;

[0039] In this embodiment, the method for acquiring a hyperspectral image includes: providing an original hyperspectral image; and performing bilateral filtering preprocessing on the original hyperspectral image to form a hyperspectral image.

[0040] The original hyperspectral image is denoted as P ∈ H A×B×C , A is the height of the data cube in the original hyperspectral image, B is the width of the data cube in the original hyperspectral image, and C is the number of spectral channels of the data cube in the original hyperspectral image. Hyperspectral images are represented as The spatial dimension of the data cube in the hyperspectral image is the same as the spatial dimension of the data cube in the original hyperspectral image, and the number of spectral ...

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

A hyperspectral open-set domain adaptation method based on multi-classifier domain adversarial network, a dynamic adaptive thresholding scheme based on multi-classifier structure to evaluate the domain-level identifiable feature information of each sample in the target domain, thereby enhancing the adversarial training process The robustness of the target domain is finally achieved to accurately classify the common categories in the target domain and the source domain while rejecting the unknown category target as the "unknown" class. The invention has a clear structure and is easy to implement, can significantly improve the classification effect of hyperspectral images in an open set scene, and has profound theoretical basis and practical significance.

Description

technical field [0001] The invention relates to the technical field of hyperspectral image open set classification, in particular to a hyperspectral open set domain self-adaptation method based on a multi-classifier domain confrontation network. Background technique [0002] Hyperspectral images are widely used to solve many problems in the field of remote sensing due to their rich spatial and spectral information, such as object classification, object segmentation and so on. Among them, the object classification is the process of automatically assigning the pixel data in the hyperspectral image to the correct object category label. The early ground object classification research was realized based on the manual annotation features, that is, the effective features of the hyperspectral image data were first extracted. , and then use a classifier to classify the features to the correct labels. As deep learning technology has been proven to have strong advantages in data deep ...

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 Patents(China)
IPC IPC(8): G06V20/10G06V10/764G06V10/774G06V10/74G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06N3/084G06V20/194G06V20/13G06F18/22G06F18/214G06F18/24
Inventor 彭元喜唐学斌杨文婧徐炜遐周侗李春潮涂文轩
Owner NAT UNIV OF DEFENSE TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com