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

Fast algorithm for determination of contaminated area in Bohai Bay based on remote sensing images

A technology of polluted areas and fast algorithms, applied in the field of data analysis technology and signal processing, to achieve good convergence, good recovery effect, and low computational complexity

Inactive Publication Date: 2019-01-25
TIANJIN UNIV
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is in order to overcome the deficiencies in the prior art, and provides a kind of fast algorithm based on the judgment of Bohai Bay pollution area of ​​remote sensing image, the present invention is aimed at the judgment problem of Bohai Bay pollution area of ​​remote sensing image, to the form of matrix decomposition The purpose of simultaneously estimating the background low-rank matrix and the foreground support matrix is ​​achieved by adding low-rank conditional constraints and introducing continuous priors as sparse conditional constraints.

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
  • Fast algorithm for determination of contaminated area in Bohai Bay based on remote sensing images
  • Fast algorithm for determination of contaminated area in Bohai Bay based on remote sensing images
  • Fast algorithm for determination of contaminated area in Bohai Bay based on remote sensing images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The present invention will be further described below in conjunction with the accompanying drawings.

[0055] Based on the current robust principal component analysis algorithm, such as low-rank matrix analysis method and Bayesian method, the present invention proposes a novel Bayesian-Ising- Signal (BIS) mixture model. At the same time, it is theoretically proved that the model is equivalent to the robust principal component analysis model. The algorithm has a remarkable effect on the recovery of low-rank matrix and the detection of singular value matrix. It not only improves the accuracy and speed, but also can effectively process more complex information, and has better robustness.

[0056] The present invention's fast algorithm based on the Bohai Bay polluted area judgment of remote sensing image comprises the following steps:

[0057] Step 1. Based on the expressions of the Bayesian model, the Ising model and the signal model, a Bayesian-Ising-signal (BIS) hybrid...

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 fast algorithm for judging the contaminated area of Bohai Bay based on remote sensing images: based on a Bayesian model, an Ising model and a signal model, the Bayesian-Isin-Signal (BIS) hybrid model is constructed; the variational Bayesian method is used to estimate the background low rank matrix L: to estimate U and V, to estimate the super parameter alpha, and to estimate the noise precision beta, and estimate foreground support matrix S. The invention aims at the judgment problem of Bohai Bay contaminated area of remote sensing image, restricts the form of matrixdecomposition by low rank condition and introduces continuous prior as sparse condition constraint to achieve the purpose of simultaneously estimating low rank matrix of background and foreground support matrix. In order to guarantee the existence of low rank solutions in the low rank decomposition process, an independent prior distribution with the same sparse profile is introduced for variablesand parameters, and a posteriori inference is made by using variational Bayesian method. In addition, considering the spatial distribution characteristics of singular value space, Markov random fieldsare introduced to estimate the foreground support matrix.

Description

technical field [0001] The invention relates to data analysis technology and signal processing technology, more specifically, to a fast algorithm for judging Bohai Bay polluted areas based on remote sensing images. Background technique [0002] Principal Component Analysis (PCA), as a classic data analysis method, is widely used in science and engineering fields. In recent years, combined with the rise of low-rank matrix analysis, a new technology in the field of signal processing, the robust principal component analysis (RPCA) problem has been raised to a new level. It mainly solves the problem of decomposing the observation matrix into a low-rank matrix and a sparse matrix, which is expressed in mathematical form as a convex optimization problem. [0003] The RPCA problem has been a long-standing research hotspot in the field of computer vision, and many efficient algorithms and corresponding software have been successfully applied to practice. However, with the developm...

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): G06K9/62
CPCG06F18/29
Inventor 潘静宋占杰李硕宦国强杨富圣
Owner TIANJIN 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