Method and device for processing hyperspectral image

A technology of hyperspectral image and processing method, which is applied in the field of hyperspectral image processing method and device, can solve the problems of affecting positioning accuracy and high false alarm rate of detection results, and achieve the effect of improving positioning accuracy and reducing false alarm rate

Active Publication Date: 2014-02-26
ACAD OF OPTO ELECTRONICS CHINESE ACAD OF SCI
View PDF0 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, this method is easily affected by the distribution of background noise and the area of ​​abnormal points, a

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
  • Method and device for processing hyperspectral image
  • Method and device for processing hyperspectral image
  • Method and device for processing hyperspectral image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Such as figure 1 As shown, the present embodiment provides a hyperspectral image processing method, which can be implemented by a high-spectrum image processing device, and the method includes:

[0049] 11. Determine the hyperspectral image to be processed.

[0050] 12. Extract abnormal targets from hyperspectral images to be processed.

[0051] 13. Separating and processing abnormal targets to obtain abnormal detection results.

[0052] In the hyperspectral image processing method of this embodiment, by determining the hyperspectral image to be processed, extracting the abnormal target from the hyperspectral image to be processed, separating and processing the abnormal target, and obtaining the abnormal detection result. In this way, the abnormal target is extracted from the hyperspectral image, and the abnormal target is separated and processed to obtain the abnormal detection result, which can reduce the false alarm rate and improve the positioning accuracy.

Embodiment 2

[0054] Such as figure 2As shown, the present embodiment provides a hyperspectral image processing method, which can be implemented by a high-spectrum image processing device, and the method includes:

[0055] 21. Obtain hyperspectral images.

[0056] In this embodiment, the hyperspectral image acquired by the high-light general image processing device may be a hyperspectral image input to the high-light general image processing device.

[0057] 22. After removing the error spectrum segment from the acquired hyperspectral image, select the data cube to be detected composed of the target band image to obtain the hyperspectral image to be processed.

[0058] In this embodiment, the hyperspectral image processing device can remove error spectrum segments from acquired hyperspectral images according to user operations, and can also perform the operation of removing error spectrum segments from acquired hyperspectral images autonomously, which is not done in this embodiment. limi...

Embodiment 3

[0072] Such as Figure 8 As shown, this embodiment provides a hyperspectral image processing device, including:

[0073] Determining module 81, for determining the hyperspectral image to be processed;

[0074] An extraction module 82, configured to extract abnormal targets from the hyperspectral image to be processed;

[0075] The processing module 83 is configured to separate and process the abnormal object to obtain an abnormal detection result.

[0076] Optionally, the extraction module 82 is specifically used for:

[0077] According to δ rxd (r)=(r-μ b ) T K -1 (r-μ b ) to extract abnormal targets from the hyperspectral image to be processed, where δ rxd (r) is the RXD detection operator, r is the spectral vector of any pixel in the hyperspectral image, is the spectral covariance matrix of hyperspectral image samples, is the hyperspectral image sample mean vector;

[0078] If δ rxd The value of (r) is less than the preset threshold and corresponds to the smal...

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 method and device for processing a hyperspectral image. The method comprises the steps that the hyperspectral image to be processed is determined; an abnormal target is extracted from the hyperspectral image to be processed; the abnormal target is separated to obtain an abnormal detection result. According to the method for processing the hyperspectral image, the hyperspectral image to be processed is determined, the abnormal target is extracted from the hyperspectral image to be processed, and the abnormal target is separated to obtain the abnormal detection result. Therefore, the abnormal target is extracted from the hyperspectral image and is separated to obtain the abnormal detection result, the false alarm rate can be lowered, and therefore locating precision is improved.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to a hyperspectral image processing method and device. Background technique [0002] As a three-dimensional data cube, hyperspectral image data not only provides the texture and position information of the spatial dimension of the ground object, but also contains the rich spectral feature information of the ground object in the third-dimensional spectral dimension, so it has other advantages in the recognition ability of the ground object. Detect the incomparable advantages of imaging. [0003] The hyperspectral image adopts the spectral recognition method to identify the ground objects, and uses statistical knowledge to find the target points with spectral differences from the background environment, which can complete the detection of abnormal targets without prior information. For example, localizing outliers with significant spectral differences from the neighborhood bac...

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 曾晓茹吕群波张桂峰
Owner ACAD OF OPTO ELECTRONICS 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