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

Hyperspectral image abnormality detection method based on homogeneous patches

An anomaly detection and hyperspectral technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of complex background types, low detection efficiency, and high false alarm rate

Inactive Publication Date: 2014-02-19
ACAD OF OPTO ELECTRONICS CHINESE ACAD OF SCI
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is: how to provide a hyperspectral image anomaly extraction method based on homogeneous patches, to solve the problem of complex background types, target participation in background feature calculation, high false alarm rate and low detection efficiency when background information is counted. question

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 abnormality detection method based on homogeneous patches
  • Hyperspectral image abnormality detection method based on homogeneous patches
  • Hyperspectral image abnormality detection method based on homogeneous patches

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0040] The flowchart of the hyperspectral anomaly detection method based on the homogeneous pattern provided by the present invention, such as Figure 1-2 As shown, it mainly includes the following steps:

[0041] Step 101 performs spectral dimensionality reduction on the hyperspectral image.

[0042] First calculate and change the 3-dimensional hyperspectral data into 2 dimensions, one of which is the spectral dimension, and the other is the serial number dimension of the pixel, and the serial number of each pixel is defined as Id ij =i×col+j, i, j are the rows and columns of pixels on the two-dimensional image respectively, and col is the number of columns of the image...

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 abnormality detection method based on homogeneous patches. The method includes the steps that (S1) conversion is carried out on original hyperspectral data X by the adoption of a spectrum dimensionality reduction method to obtain a converted feature vector Y; (S2) an image Y after dimensionality reduction is segmented by the adoption of a hyperspectral image segmentation method to obtain a tagged image L; (S3) pixels with the same tag number as the tagged image L are searched to form pixel sets, and each pixel set corresponds to one homogeneous patch; (S4) the mean value and the variance of each homogeneous patch are calculated in a weighting method; (S5) heterogeneities of pixels are sequentially calculated with the homogeneous patches as a unit, and (S6) the thresholds of the heterogeneities are determined to sequentially judge whether the pixels are abnormal points. The method overcomes the defects that background data statistic is complex in background variety, dimension is multiple and targets are involved in calculation, improves background data calculation precision, improves the conformity of a normal distribution function and a background distribution function, and improves detection probability under a false alarm rate condition.

Description

technical field [0001] The invention relates to the technical field of industrial automatic detection, in particular to a hyperspectral image anomaly detection method based on homogeneous patterns. Background technique [0002] Hyperspectral remote sensing, with its nanoscale spectral resolution and ultra-multi-band imaging characteristics in the visible light to short-wave infrared and even thermal infrared bands, has attracted great attention from the majority of people engaged in remote sensing and applications. Its application fields are also becoming more and more extensive, involving many fields such as global environment, land use, and resource survey. Especially in object detection, hyperspectral is especially important. Due to the limitation of ground sampling distance, in many cases, the target of interest exists in the form of sub-pixels, which is the main way for targets to exist on hyperspectral images. At this time, it is difficult to detect these small targe...

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
Inventor 相里斌张桂峰吕群波周锦松黄旻明星赵宝玮
Owner ACAD OF OPTO ELECTRONICS CHINESE ACAD OF SCI
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