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

Hyperspectral image target detection method based on tensor spectrum matched filtering

A hyperspectral image and target detection technology, which is applied in image data processing, pattern recognition in signals, instruments, etc., can solve the problems of low detection accuracy and inability to mine the overall information of 3D data, and achieve the effect of improving detection accuracy

Active Publication Date: 2017-08-11
HARBIN INST OF TECH
View PDF4 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the problem that the existing hyperspectral image target detection method cannot carry out information mining from the three-dimensional data as a whole, and the detection accuracy is low, and propose a hyperspectral image target detection method based on tensor spectral matched filtering

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
  • Hyperspectral image target detection method based on tensor spectrum matched filtering
  • Hyperspectral image target detection method based on tensor spectrum matched filtering
  • Hyperspectral image target detection method based on tensor spectrum matched filtering

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0021] Specific implementation mode one: combine figure 1 To illustrate this embodiment, the specific process of a hyperspectral image target detection method based on tensor spectral matched filtering in this embodiment is as follows:

[0022] Step 1: Establish the signal representation model of the target and background under the tensor representation;

[0023] Step 2: Based on the model obtained in step 1, convert the hyperspectral image to be detected into the form of a third-order tensor through a given window size, and obtain the third-order empty X-empty Y-spectrum of the local neighborhood of the data to be detected Tensor, build a local neighborhood-based empty X-empty Y-spectrum-sample fourth-order tensor

[0024] Step 3: According to the tensor spectrum matching filter algorithm proposed in this patent, obtain the empty X-empty Y-spectrum-sample fourth-order tensor based on the local neighborhood obtained in step 2 The covariance matrix of the empty X, empty Y...

specific Embodiment approach 2

[0027] Specific embodiment two: the difference between this embodiment and specific embodiment one is: the signal representation model of the target and background under the tensor representation is established in the step one; the specific process is:

[0028] Target H under tensor representation 1 and background H 0 The signal representation model of is:

[0029]

[0030]

[0031] in, is a third-order tensor representation of hyperspectral data, Represents the third-order tensor quantum space formed by the target spectrum and its neighborhood, α represents the corresponding abundance coefficient, that is, the corresponding weight, is a third-order tensor representation of Gaussian random noise.

[0032] Other steps and parameters are the same as those in Embodiment 1.

specific Embodiment approach 3

[0033] Specific embodiment 3: The difference between this embodiment and specific embodiment 1 or 2 is that in step 2, based on the model obtained in step 1, the hyperspectral image to be detected is converted into a third-order sheet through a given window size. In the form of quantity, the third-order tensor of empty X-empty Y-spectrum of the local neighborhood of the data to be detected is obtained, and the fourth-order tensor of empty X-empty Y-spectrum-sample based on the local neighborhood is established The specific process is:

[0034] Based on the model obtained in step 1, given a 3×3 or 5×5 window, the hyperspectral image to be detected is converted into a third-order tensor form, and then all the hyperspectral images to be detected in the form of third-order tensor Spectral image data is built as a local neighborhood-based empty X-empty Y-spectrum-sample fourth-order tensor

[0035] The size of the local neighborhood is the window size.

[0036] Other steps and...

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 hyperspectral image target detection method based on tensor spectrum matched filtering. The invention relates to target detection of a hyperspectral image. The object of the invention is to solve problems of conventional hyperspectral image target detection methods such as low detection precision and inability of carrying out information mining from three-dimensional data integrally. The hyperspectral image target detection method comprises steps that 1, a target and background signal representation model is established under a tensor representation condition; 2, a to-be-detected hyperspectral image is converted into a three-order tensor form based on a predetermine window, and a hollow X-hollow Y-spectrum-sample four-order tensor 4D is established based on a local neighborhood; 3, covariance matrixes in the hollow X direction, the hollow Y direction, and the spectrum direction of the 4D are acquired; 4, a new three-order tensor after mapping is acquired; 5, the inner products of the target spectrum tensor, the hollow X-hollow Y-spectrum three-order tensor, and the new three-order tensor after the mapping are calculated respectively, and whether the pixel of the to-be-detected hyperspectral image is the detection target is determined. The hyperspectral image target detection method is used for the digital image processing field.

Description

technical field [0001] The invention relates to target detection of hyperspectral images. Background technique [0002] The hyperspectral sensor obtains the reflected radiation information of ground objects through hundreds of spectral channels, and its band range covers from visible light to near-infrared and even long-wave infrared regions. Hyperspectral images also contain spatial information, reflection or radiation information, and spectral information, a property often referred to as "unification of graphs". Moreover, hyperspectral image data provides nearly continuous spectral sampling information, which can record small reflectance differences of ground objects in the spectrum. This characteristic is called the diagnostic characteristic of ground objects, which can be used as the basis for classification and detection of ground objects. It has important theoretical significance and application value to study the new technology of hyperspectral image target detectio...

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): G06K9/00G06T17/00
CPCG06T17/00G06V2201/07G06F2218/22G06F2218/08G06F2218/12
Inventor 谷延锋刘永健
Owner HARBIN INST OF TECH
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

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