Hyperspectral image anomaly target detection method based on pixel selection process

A technology of hyperspectral images and abnormal targets, applied in image analysis, image data processing, instruments, etc., can solve the problems of low detection ability, poor adaptability, insufficient difference between background and target, etc., to improve detection ability and suppress noise. The effect of interference and improving the applicability of the algorithm

Active Publication Date: 2016-10-05
XI'AN INST OF OPTICS & FINE MECHANICS - CHINESE ACAD OF SCI
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a detection method for abnormal targets in hyperspectral images, which solves the technical problems that the existin

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 anomaly target detection method based on pixel selection process
  • Hyperspectral image anomaly target detection method based on pixel selection process
  • Hyperspectral image anomaly target detection method based on pixel selection process

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] refer to figure 1 , the realization method of the present invention is mainly as follows:

[0033] (1) Adopt the sliding window strategy to extract the image blocks for each processing.

[0034] (1a) Firstly, normalization preprocessing is performed on the obtained hyperspectral image. Then, using the inner and outer windows, (the inner window is used as a protection window to reduce the interference of abnormal targets; the outer window is to limit the detection range) to extract the hyperspectral image block X∈R N×D , where N is the number of pixels in the image block, and D is the number of spectral bands of the hyperspectral data.

[0035] (2) Using manifold learning technology to calculate the reconstruction error of each pixel.

[0036] (2a) In a high-dimensional space, find each pixel X in the image block X i The K nearest neighbors of , and perform local linear representation to minimize the reconstruction error The linear representation coefficient can be...

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 provides a hyperspectral image anomaly target detection method based on a pixel selection process. The method comprises the following steps: 1) normalization preprocessing is carried out on the hyperspectral image, and the size of a detection window is set; 2) a sliding window technique is adopted, a to-be-detected hyperspectral image block X is acquired, wherein X belongs to R<N*D>, R is real number space, N is the pixel point number in the image block, and D is the spectral waveband number for the hyperspectral data; 3) a reconstruction error epsiloni of each pixel point Xi is calculated; 4) a vertex-edge weight graph is constructed; 5) a pixel selection process model is constructed; and 6) steps from the second to the fifth are repeated until detection on the anomaly target on the whole hyperspectral image is completed, and a final anomaly probability graph is acquired. The hyperspectral image anomaly target detection method has the advantages of solving technical problems that background distribution needs to be hypothesized in the existing detection technology, the adaptability is poor, differences between the background and the target are not enough, and the detection ability is low.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for detecting abnormal targets on hyperspectral images. Background technique [0002] Hyperspectral images contain rich spectral information, which can provide discriminative clues for the identification of small differences in ground objects. The abnormal target detection of hyperspectral images is a typical application based on this characteristic, and its main purpose is to identify targets in the image scene that deviate significantly from the spectral characteristics of the background. The essence of this detection is a binary classification problem, which is to classify the pixels to be observed as background or target. Unlike the supervised target detection problem, hyperspectral abnormal target detection does not have any prior spectral information about the target or background, it only relies on modeling the set reference background, looki...

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): G06T7/00
Inventor 袁媛王琦马单丹
Owner XI'AN INST OF OPTICS & FINE MECHANICS - CHINESE ACAD OF SCI
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