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

Mixed pixel decomposition method for remote sensing images

A hybrid pixel decomposition and remote sensing image technology, applied in the field of remote sensing image processing, can solve problems such as the inability to obtain an optimal solution, and achieve the effect of overcoming the tendency to fall into local minima and effectively mixing pixel decomposition.

Inactive Publication Date: 2013-08-21
FUDAN UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the objective function of NMF has obvious non-convexity, so there are a large number of local minima, so it is almost impossible to obtain the optimal solution.

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
  • Mixed pixel decomposition method for remote sensing images
  • Mixed pixel decomposition method for remote sensing images
  • Mixed pixel decomposition method for remote sensing images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0158] 1. Simulation data

[0159] Artificially generated simulation data are used to test the performance of the algorithm. The ASSNMF proposed by the present invention is compared with the following unmixing algorithms for hyperspectral images: VCA [9], PSNMFSC [10] with spectrum and abundance smoothness and abundance sparsity constraints, and minimum volume constraints The MVCNMF [11]. Among them, VCA can only get the spectral matrix, and other methods can directly solve the spectrum and abundance from the data. For VCA, the present invention uses the FCLS algorithm [8] on the basis of the spectrum it solves to obtain the corresponding abundance, and this method is recorded as VCA-FCLS.

[0160] The present invention uses two indexes of spectral angular distance (Spectral Angel Distance, SAD) and root mean square error (Root Mean Square Error, RMSE) to measure the pros and cons of the unmixing result. These two indicators are used to measure the approximation of the spec...

Embodiment 2

[0174] Embodiment 2 Actual data experiment

[0175] Three actual hyperspectral remote sensing image datasets are used to test the performance of the proposed algorithm.

[0176] The first dataset is the Indiana data captured by the Airborne Visible / Infrared Imaging Spectrometer (AVIRIS). It was imaged in June 1992. The imaging area is the Pine remote sensing test site in Indiana, USA. The data has 220 bands, the wavelength range is from 0.4:2.5μm, the spectral resolution is 10nm, and the spatial resolution is 17m. The image size used in the experiments is 145×145. This data has been widely used in the research and comparison of hybrid pixel decomposition algorithms for remote sensing images. Purdue University has given a field survey report on the area [12]. This area is a piece of farmland located about 10km northwest of West Lafayette, IN, Indiana. The area is mainly covered by various crops (about two-thirds, including corn, wheat, soybeans, haystacks) and natural veget...

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 new mixed pixel decomposition method based on an NMF (non-negative matrix factorization) algorithm. The method comprises the following steps: introducing constraint conditions for abundance separability and smoothness into the target functions of the NMF algorithm according to the spectrum and abundance characteristics of hyperspectral images; and removing the constraint conditions at the right time, and continuing to carry out iteration, thereby overcoming the defects that the NMF algorithm is easily sunk into local minimum, so that the mixed pixel decomposition method for high mixed remote sensing data can be implemented effectively. The method disclosed by the invention has especially important application value in the aspects of detecting and identifying ground targets and classifying topographical objects based on the high accuracies of multispectral and hyperspectral remote sensing images.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a new method based on a non-negative matrix decomposition algorithm that can solve the problem of high mixed remote sensing data mixed pixel decomposition. Background technique [0002] Remote sensing 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. In recent years, with the advancement of imaging technology, multi-band remote sensing images have been widely used in more and more fields. Due to the limitation of the spatial resolution of the imaging system and the complexity and variety of the surface, a pixel in the obtained remote sensing image often contains multiple types of ground objects, which forms a mixed pixel. How to accura...

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): G01S7/48G06T7/00G06K9/00G06K9/62
Inventor 刘雪松王斌张立明
Owner FUDAN 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