Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Hyperspectral remote sensing image anomaly detection method based on low-rank joint collaborative representation

A hyperspectral remote sensing and collaborative representation technology, which is applied in the field of hyperspectral remote sensing image anomaly detection with low-rank joint collaborative representation, can solve the problem of abnormal pixel pollution of hyperspectral remote sensing images, etc., to overcome abnormal pixel pollution, good effect, The effect of reducing running time

Active Publication Date: 2019-12-27
HOHAI UNIV
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Purpose of the invention: In order to overcome the deficiencies of the prior art, the present invention provides a hyperspectral remote sensing image anomaly detection method that can effectively solve the problem of hyperspectral remote sensing image anomaly detection dictionary construction and abnormal pixel pollution under the representation model, which is a low-rank joint cooperative representation

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 remote sensing image anomaly detection method based on low-rank joint collaborative representation
  • Hyperspectral remote sensing image anomaly detection method based on low-rank joint collaborative representation
  • Hyperspectral remote sensing image anomaly detection method based on low-rank joint collaborative representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0052] Example: The experimental data is a hyperspectral remote sensing image acquired by a Nuance CRi hyperspectral sensor, including 400×400 pixels, 46 bands, a spectral resolution of 10nm, and a spectral range of 650-1100nm. As shown in Figure 2(a) and (b), only two types of ground objects are included in the figure; grass and 10 stones, and 10 stones covering 2261 pixels are considered as abnormal objects. In the experiment, the parameter a is set to 3000, and the parameter b is set to 3.

[0053] Such as figure 1 As shown, the specific implementation steps are:

[0054] (1) Perform data preprocessing on the original hyperspectral remote sensing image data, and convert it into a two-dimensional matrix X of m×n size, where m is 46 and n is 160,000;

[0055] (2) Use the mean shift clustering algorithm to cluster the two-dimensional matrix X, and obtain C clusters and cluster centers c i ;

[0056] (3) Count the number of pixels in each cluster, if it is greater than 3000...

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 remote sensing image anomaly detection method based on low-rank joint collaborative representation. A hyperspectral remote sensing image is divided into a background part and an abnormal target part. The background part is linearly represented by a dictionary, dictionary atoms are effectively selected by setting two threshold parameters, and a coefficient matrix is constrained by adopting a low rank and an l2 norm. Abnormal target uses sparse constraints. According to the method, the problem of abnormal pixel pollution based on a representation method can be solved, and the precision of hyperspectral anomaly detection is effectively improved by utilizing the synergistic effect among dictionary atoms.

Description

technical field [0001] The invention belongs to the technical field of hyperspectral remote sensing image processing, and in particular relates to a hyperspectral remote sensing image anomaly detection method with low-rank joint cooperative representation. Background technique [0002] Hyperspectral remote sensing is a multi-dimensional information acquisition technology that combines imaging technology with spectral technology. It can detect two-dimensional geometric space information and one-dimensional spectral information of targets at the same time, and obtain hundreds of continuous and narrow-band image data with high spectral resolution. , with a spectral resolution of 10 -2 ~10 -1 lambda. Different from traditional multispectral remote sensing, the main features of hyperspectral remote sensing are: high spectral resolution, multiple and continuous bands, large amount of data, and integration of maps. The band range of hyperspectral remote sensing is generally less...

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/194G06V20/13G06V2201/07G06F18/23Y02A40/10
Inventor 苏红军吴曌月
Owner HOHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com