Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Hyperspectral abnormal object detection method based on structure sparse representation and internal cluster filtering

A sparse representation, abnormal target technology, applied in the field of hyperspectral abnormal target detection, can solve the problem of low target detection efficiency, and achieve the effect of improving the detection rate

Inactive Publication Date: 2017-07-04
NORTHWESTERN POLYTECHNICAL UNIV
View PDF3 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of low target detection efficiency of the existing hyperspectral anomaly target detection methods, the present invention provides a hyperspectral anomaly target detection method based on structural sparse representation and internal clustering filtering

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 abnormal object detection method based on structure sparse representation and internal cluster filtering
  • Hyperspectral abnormal object detection method based on structure sparse representation and internal cluster filtering
  • Hyperspectral abnormal object detection method based on structure sparse representation and internal cluster filtering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The specific steps of the hyperspectral anomaly target detection method based on structural sparse representation and internal clustering filtering in the present invention are as follows:

[0033] Suppose the input hyperspectral image is a 3D data cube containing n b bands, each band is a picture of nrow row and n col The column size of the image. For the convenience of calculation, each band is stretched into a row vector, and all row vectors form a two-dimensional matrix X, Among them, each column of X represents the spectrum corresponding to each pixel, and this direction is the spectral dimension; each row of X corresponds to all pixel values ​​of a band (ie n p =n row ×n col ), the direction is the spatial dimension. details as follows:

[0034] 1. Robust background dictionary learning based on principal component analysis.

[0035] (1) Use the double-window local RX algorithm to obtain the background pixel set.

[0036] According to the resolution of the...

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 abnormal object detection method based on structure sparse representation and internal cluster filtering, aiming at addressing the technical problem of low object detection effciency of current hyperspectral abnormal object detection methods. The technical solution involves: after selecting an initial background pixel, using the dictionary learning method which is based on principal component analysis to study a background dictionary which obtains rebustness, in the course of sparse vector resolution and image reconstruction, introducing re-weighted laplacian prior to increase the solution precision of sparse vector, computing the errors betwen an original image and a reconstructed image to obtain a sparse representation error, using the internal cluster filtering to represent space spectrum characteristics of hyperspectral data, obtaining the internal cluster error by computing the error between a to-be-tested pixel and other pixel linear representation result, and finally combining the sparse representation error and the linear weighting of the internal cluster error and implementing precise extraction of an abnormal object. According to the invention, the method increases 10-15% of detection rate with the proviso of a constant false alarm rate compared with prior art.

Description

technical field [0001] The invention relates to a hyperspectral abnormal target detection method, in particular to a hyperspectral abnormal target detection method based on structural sparse representation and internal clustering filtering. Background technique [0002] Hyperspectral anomaly target detection technology is a hyperspectral target detection technology that only uses the spectral difference between image pixels to detect targets without providing prior spectral information of the target to be measured. Strong practicality. [0003] Compared with the entire hyperspectral image, the abnormal target not only has a lower probability of occurrence, but also accounts for a small proportion. Traditional abnormal target detection algorithms generally assume that the image background obeys a Gaussian distribution. Under this assumption, global or local statistical properties can be used to detect abnormal targets. However, in practical applications, due to the limitati...

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): G06K9/62
CPCG06F18/23213
Inventor 张艳宁李飞张秀伟陈妍佳张磊魏巍蒋冬梅
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
Eureka Blog
Learn More
PatSnap group products