A hyperspectral image target prior optimization method based on multi-task sparse learning

An image target and optimization method technology, applied in the field of hyperspectral imaging, can solve the problems of not taking into account the spectral similarity of the target objects, unable to fully utilize the target information, etc., and achieve the effects of high optimization accuracy, improved effect, and simple model.

Active Publication Date: 2022-06-21
CHINA UNIV OF GEOSCIENCES (WUHAN)
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method takes the background pixels into account, and the obtained prior spectrum of the target can be regarded as a linear mixture of the target spectrum and the background spectrum, not the pure target spectrum of the target object. In addition, this method does not take into account the target The spectral similarity between different pixels of the ground object cannot make full use of the target information in the hyperspectral image

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 hyperspectral image target prior optimization method based on multi-task sparse learning
  • A hyperspectral image target prior optimization method based on multi-task sparse learning
  • A hyperspectral image target prior optimization method based on multi-task sparse learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to have a clearer understanding of the technical features, objects and effects of the present invention, the specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0033] The embodiment of the present invention provides a hyperspectral image target prior optimization method based on multi-task sparse learning, which is used to avoid the problem of background pixels participating in the target prior optimization process in the traditional method, and at the same time fully consider the target in the hyperspectral image. The spectral similarity of pixels can improve the effect of target prior spectral optimization.

[0034] Please refer to figure 1 , figure 1 is a flow chart of a priori optimization method for hyperspectral image targets based on multi-task sparse learning in the embodiment of the present invention. m ,m=1,2,...,M are respectively input into the constrained energy minimizatio...

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 present invention provides a hyperspectral image target prior optimization method based on multi-task sparse learning. Through pre-detection and set operation, a complete target dictionary and target pixels to be reconstructed are obtained, and a multi-task sparse expression model is established. The spectral similarity of the target pixel performs complementary learning on the sparse expression models of different target pixels, and the average sparse coefficient of the target atom is used as the reconstruction weight of the target atom to the optimal target prior spectrum to improve the target prior optimization effect. The beneficial effect of the invention is that it can prevent the background pixel from participating in the prior optimization process of the target, make full use of the spectral similarity of the target pixel, and improve the prior optimization effect of the target.

Description

technical field [0001] The invention relates to the field of hyperspectral images, in particular to the technical field of hyperspectral image processing, and in particular to a hyperspectral image target prior optimization method based on multi-task sparse learning. Background technique [0002] Target detection refers to the process of separating interesting target objects from non-target background objects. Hyperspectral images have the characteristics of high spectral resolution and unified atlas, and can provide diagnostic spectral characteristic information for distinguishing different substances. Therefore, hyperspectral images have unique advantages in target detection. At present, hyperspectral image target detection has been applied to terrain survey, natural resource detection, maritime search and rescue, camouflage target recognition and other fields. [0003] For target detection in hyperspectral remote sensing images, scholars at home and abroad have proposed ...

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 & AuthorityPatents(China)
IPC IPC(8): G06T7/00G06T7/136
CPCG06T7/0002G06T7/136G06T2207/10036
Inventor张玉香李晨董燕妮陈涛吴柯
OwnerCHINA UNIV OF GEOSCIENCES (WUHAN)