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

A Nonlinear Abundance Estimation Method for Hyperspectral Images Based on Constrained Least Squares

A hyperspectral image and least squares technology, applied in the field of remote sensing image processing, can solve problems such as inaccurate results, and achieve the effects of good adaptability, good unmixing accuracy, anti-noise performance, and low computational complexity

Inactive Publication Date: 2016-03-09
FUDAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for some hyperspectral images containing sand, minerals, vegetation, and waters, due to the existence of nonlinear mixing phenomena, LMM will get inaccurate results.

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 Nonlinear Abundance Estimation Method for Hyperspectral Images Based on Constrained Least Squares
  • A Nonlinear Abundance Estimation Method for Hyperspectral Images Based on Constrained Least Squares
  • A Nonlinear Abundance Estimation Method for Hyperspectral Images Based on Constrained Least Squares

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0089] Below, the specific embodiment of the present invention is illustrated with simulation data and actual remote sensing image data respectively:

[0090] The nonlinear abundance estimation method (algorithm) based on constrained least squares adopted in the present invention is represented by CNLS-AE.

[0091] 1. Simulation data experiment

[0092] In this section, we test the performance of the proposed algorithm on artificially generated simulation data. We compare the algorithm proposed in this paper with two gradient methods based on GBM and PPNMM, namely GBM-GDA and PPNMM-GDA algorithms mentioned in [7] and [8], respectively. In addition, we also compare with the better performance of the LMM-based FCLS algorithm [10].

[0093] We use root mean square error (RootMeanSquareError, RMSE) and reconstruction error (ReconstructionError, RE) to measure the pros and cons of abundance estimation algorithms. RMSE is used to measure how close the estimated result of the abun...

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 belongs to the technical field of remote sensing image processing and particularly relates to a hyperspectral image nonlinear abundance estimation method based on constrained least squares. According to the method, through introducing abundance nonnegative constraint, abundance sum-to-one constrain and the bounded constraint of a nonlinear parameter, a hyperspectral image nonlinear unmixing problem is transformed into a problem of solving the constraint nonlinear least squares of an abundance vector and the nonlinear parameter. Furthermore, an alternating iteration optimization algorithm is employed to solve the problem. According to the method, starting from a mixed model of a hyperspectral observation pixel, combined with abundance and nonlinear physics significances in the model, the shortcomings of linear unmixing are effectively overcome, and the method also has good anti noise performance and can be used as an effective solution of the hyperspectral remote sensing image nonlinear unmixing. The method has an important application value at the aspect of high precision unmixing based on a hyperspectral remote sensing image and the detection and identification of a ground target.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a nonlinear abundance estimation method for hyperspectral remote sensing images. Background technique [0002] Remote sensing technology is a new comprehensive technology developed in the 1960s. It is closely related to science and technology such as space, electron optics, computer, and geography. It is one of the most powerful technical means for studying the earth's resources and environment. Hyperspectral remote sensing is a multi-dimensional information acquisition technology that combines imaging technology with spectral technology. The hyperspectral imager simultaneously detects the two-dimensional geometric space and one-dimensional spectral information of the target on dozens to hundreds of very narrow and continuous spectral segments of the electromagnetic spectrum. In the hyperspectral image, each observation pixel can extract a com...

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): G06T7/00
Inventor 普晗晔王斌
Owner FUDAN 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