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

Low-rank sparse decomposition hyperspectral anomaly detection method based on local features

A local feature, sparse decomposition technology, applied in measurement devices, analysis materials, image analysis and other directions, can solve problems such as affecting the detection accuracy of abnormal targets, insufficient low-rank sparse matrix decomposition accuracy, etc., to improve interpretability, easy to implement, The effect of fewer parameters

Active Publication Date: 2020-08-25
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional methods based on low-rank sparse matrix factorization often focus on matrix factorization, ignoring the internal relationship based on local features, resulting in insufficient precision of low-rank sparse matrix factorization, which affects the detection accuracy of abnormal targets.

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
  • Low-rank sparse decomposition hyperspectral anomaly detection method based on local features
  • Low-rank sparse decomposition hyperspectral anomaly detection method based on local features
  • Low-rank sparse decomposition hyperspectral anomaly detection method based on local features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The key invention of the present invention is a low-rank sparse matrix decomposition hyperspectral abnormal target detection method based on local features, which solves the problem of lack of image-based local feature information in traditional methods. Combine below figure 1 , the specific embodiment of the present invention will be described in further detail.

[0048] Based on the image matrix X, abnormal target detection is performed on hyperspectral remote sensing images. The specific implementation process is as follows:

[0049] Read the original 3D hyperspectral image into a matrix X={x 1 ,...,x t ,...,x i}, i is the number of image bands, and j is the number of image pixels. Each column of vector x in matrix X j =(x1j ,...,x tj ,...,x ij ) T is the spectral radiance value of the pixel. Perform the following operations on the hyperspectral remote sensing image matrix X:

[0050] (1) Construct a hyperspectral image description model based on local feat...

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

In order to improve the precision of hyperspectral target detection, the invention provides a low-rank sparse matrix decomposition hyperspectral abnormal target detection method based on local features in allusion to the lack of low-rank information based on the local features in hyperspectral abnormal target detection. According to the method, on the basis of a traditional low-rank sparse matrixdecomposition method, the background part of a hyperspectral image is further refined to represent the product of a basis matrix B and a coefficient matrix C according to the low-rank property of thebackground of the hyperspectral image and the sparsity of an abnormal target, and a hyperspectral image description model based on local features is constructed; secondly, iterative updating rules ofthe new basis matrix B, the coefficient matrix C and the sparse part S are constructed; and finally, abnormal target detection is performed according to a solving result. Experiments prove that the method can improve the hyperspectral abnormal target detection precision.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a low-rank sparse decomposition hyperspectral anomaly detection method based on local features. Background technique [0002] Hyperspectral images have high spectral resolution and contain rich and detailed spectral information of ground objects, which greatly improves the ability to distinguish ground objects. In the field of target detection, hyperspectral images can use the unique spectral curve characteristics of various ground objects to identify many similar ground objects that cannot be identified by multispectral images. The research on hyperspectral target detection algorithm has always occupied an important position in the field of hyperspectral remote sensing data analysis and processing. [0003] When the target spectral information is difficult to obtain, abnormal target detection methods are often used to detect abnormal targets....

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): G06T7/00G01N21/17
CPCG06T7/0002G01N21/17G01N2021/1793G06T2207/10036G06T2207/30181
Inventor 许明明张燕刘善伟
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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