Method for extracting pixel purity index based on end member of image processor

A graphics processor and endmember extraction technology, which is applied in image data processing, processor architecture/configuration, image analysis, etc. It can reduce the running time, improve the running efficiency, and improve the speed.

Inactive Publication Date: 2015-01-07
XIDIAN UNIV
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this algorithm has been widely used in the field of spectral unmixing, with the increase of the accuracy of hyperspectral images, the time consumption of this algorithm is increasing, which can no longer meet the requirements of no-load real-time processing; second, the pure pixel index The computational complexity of the PPI algorithm is very high; third, the output of the final terminal set is unstable and susceptible to the influence of the initial terminal set

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
  • Method for extracting pixel purity index based on end member of image processor
  • Method for extracting pixel purity index based on end member of image processor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031]The present invention will be further described below in conjunction with the accompanying drawings.

[0032] Refer to attached figure 1 , the steps of the present invention are as follows.

[0033] Step 1, enter data.

[0034] Copy the hyperspectral image cube data set to be processed from the memory to the video memory to obtain the hyperspectral image cube data.

[0035] Step 2, generate random vectors.

[0036] A set of random vectors is composed of k n-dimensional random unit vectors, where the value range of the number k of random unit vectors is 1×10 4 ~9×10 4 , the random unit vector dimension n has a value equal to the number of spectral bands of the hyperspectral image.

[0037] The unified computing device architecture CUDA is used to directly generate all random numbers required for simulating random vectors in the graphics processor GPU, and store the obtained random numbers in the initial random vectors to obtain simulated random vectors, which are sto...

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 method for extracting a pixel purity index based on an end member of an image processor. By means of the method, the defects that in the prior art, computation complexity of a pixel purity index PPI algorithm is high and time consumption is constantly increased along with improvement of hyperspectral image precision and accordingly the requirement of no-load real-time processing cannot be met are overcome. The method includes the steps of (1) inputting data, (2) generating random vectors, (3) projecting an extreme value, and (4) determining the end member. By means of the method, information of the end member in hyperspectral image cubic data can be extracted in real time, a reliable guarantee is provided for following data processing, operation efficiency of an algorithm is obviously improved, operation time is reduced, and the requirement of no-load real-time processing of a hyperspectral scene graph is met, good performance is achieved and the complexity is improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a method for extracting pure pixel index based on a graphics processor in the technical field of hyperspectral imaging and remote sensing. The invention can be used for spectral unmixing of hyperspectral images with higher precision. Background technique [0002] Hyperspectral imaging is an emerging technology in the field of remote sensing. It generates observation images with hundreds of bands by responding to different wavelength radiation responses of objects in the same area on the surface. A hyperspectral data cube usually has gigabytes of data, and hyperspectral images are playing an increasingly important role in civilian and military fields due to their high spectral resolution and the integration of maps. [0003] But in the analysis of hyperspectral cube image data, the main problem is the existence of mixed pixels. This problem is especially prominent...

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): G06T7/00
CPCG06T1/20G06V10/58G06V10/42
Inventor 吴宪云郭杰曹金彦李云松雷杰王珂俨刘凯
Owner XIDIAN 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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap