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

Hyperspectral image abnormal point detection method based on selective kernel principal component analysis

A technology of hyperspectral image and principal component analysis, applied in the field of hyperspectral image analysis and detection, can solve problems such as multiple false alarms, large amount of calculation, and inability to detect abnormal points.

Inactive Publication Date: 2009-07-01
HARBIN INST OF TECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] The purpose of the present invention is to solve the problem that the existing hyperspectral image detection technology cannot efficiently extract and select the features of abnormal points, which will generate more false alarms, and the calculation amount is large, and when there is serious background interference Unable to detect outliers

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 abnormal point detection method based on selective kernel principal component analysis
  • Hyperspectral image abnormal point detection method based on selective kernel principal component analysis
  • Hyperspectral image abnormal point detection method based on selective kernel principal component analysis

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0053] Specific embodiment one: the detection method step of this embodiment is:

[0054] Step 1. Input the three-dimensional hyperspectral image I(i, j, s), wherein, i=1, 2, ..., P represents the row of a band image, j=1, 2, ..., Q represents the column of the image, s =1, 2, ..., N represents the number of bands of hyperspectral data, the size of I(i, j, s) is P×Q×N, according to the band image mode, I(i, j, s) can be expressed as [ I 1 I 2 …I s ],in:

[0055]

[0056] In the above formula, is the gray value corresponding to the sth band (i, j) point;

[0057] Step 2. Find the maximum gray value of the hyperspectral image I(i, j, s) I max = max i , j , s ( I ( i , j , s ...

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

A hyperspectral image abnormal point detection method based on selective kernel principal component analysis relates to the technical field of hyperspectral image analysis and detection. It is to solve the problem that the existing hyperspectral image detection technology cannot efficiently extract the features of abnormal points, resulting in many false alarms, and cannot effectively detect abnormal points under severe background interference. Its steps are: normalize the data and perform kernel principal component analysis; construct a sliding window in the principal component; calculate the third and fourth moments of the pixels in the sliding window and compare them with the set values; traverse the principal components Finally, record the value; all principal components are processed; select the largest principal component; use the RX operator to detect outliers on the selected principal components, and output the detection results. The invention can efficiently extract and select the features of the abnormal point target in the hyperspectral image, reduce the false alarm rate, and realize the normal detection of the abnormal point under the condition of severe background interference.

Description

technical field [0001] The invention relates to the technical field of hyperspectral image analysis and detection. Background technique [0002] Abnormal signals are also called mutation signals. Abnormal points and irregular mutations in the signal often carry very important information, which is one of the important characteristics of the signal. In image analysis and processing, an outlier is usually defined as a part that is different from the background category in a small neighborhood, or a part that undergoes a mutation, which is defined with reference to a different background model. Outliers often only occupy a small number of pixels in the image, or even exist within one pixel. The background model is determined by selecting a large-scale area from the image or the reference data of the local neighborhood near the test pixel, and is mainly divided into a global background model and a local background model. The main difference in the definition of global and loca...

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): G01S17/89G01S7/48
Inventor 谷延锋张晔张钧萍陈浩
Owner HARBIN INST OF TECH
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