Hyperspectral image stripe missing restoring method based on edge constraint and self-adaptive morphological filter

A hyperspectral image and morphological filtering technology, which is applied in image enhancement, image data processing, instruments, etc., can solve the problems of strip loss, hyperspectral image strip loss, and ineffective restoration.

Inactive Publication Date: 2016-01-20
HARBIN INST OF TECH
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem that in the acquisition process of the existing hyperspectral image, the continuous spectral segment cannot be effectively recovered when there is a band-like deletion, and to provide a hyperspectral image band-deletion based on edge constraints and adaptive morphological filtering Repair method

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 stripe missing restoring method based on edge constraint and self-adaptive morphological filter
  • Hyperspectral image stripe missing restoring method based on edge constraint and self-adaptive morphological filter
  • Hyperspectral image stripe missing restoring method based on edge constraint and self-adaptive morphological filter

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0011] Specific implementation mode one: the following combination figure 1 Describe this embodiment, the hyperspectral image strip loss repair method based on edge constraints and adaptive morphological filtering described in this embodiment, the specific process of the repair method is:

[0012] Step 1, detect the band, and determine the specific position of the missing band in the hyperspectral image;

[0013] Step 2, restore the edge, and give priority to restoring the edge information in the missing strip;

[0014] Step 3. Generate an adaptive structural element based on edge constraints for each damaged pixel missing from the strip. The adaptive structural element can protect the hyperspectral image information. The structural element is larger than the width of the missing strip to ensure that the structural element can coverage to undamaged areas;

[0015] Step 4. Adaptive morphological filtering to determine the recovery value of the damaged pixel missing from the f...

specific Embodiment approach 2

[0016] Specific implementation mode two: the following combination figure 1 Describe this implementation mode, this implementation mode will further explain implementation mode 1, the specific process of step 1 is:

[0017] Step 1.1, use the Canny operator to obtain the gradient of the image, and use high and low double thresholds and non-maximum suppression to obtain two kinds of continuously refined edges;

[0018] Step 1.2, using the two results obtained in step 1.1 to trace the straight line using Hough transform to obtain two vertical straight lines or horizontal straight lines running through the hyperspectral image;

[0019] Step 1.3, detect the pixel value of the area between the two straight lines obtained in step 1.2, the position where the pixel value is lower than other surrounding areas is the specific position where the band is missing in the hyperspectral image.

specific Embodiment approach 3

[0020] Specific implementation mode three: the following combination figure 1 Describe this implementation mode, this implementation mode will further explain implementation mode 2, the specific process of step 2 is:

[0021] Step 2.1. According to the missing position of the strip in the acquired hyperspectral image, the edge distribution of the damaged pixel with the missing strip is used as the output vector of the SVM, and the edge distribution of the undamaged pixel in the neighborhood of the damaged pixel is used as the SVM Input the vector, train a series of SVMs according to the width of the missing strip and the position of the damaged pixel to be restored in the strip, and select a group of intact hyperspectral images or the part without strips in the damaged image to be restored as the training set;

[0022] Step 2.2. Select the corresponding SVM according to the width of the missing strip and the position of the damaged pixel to be restored in the strip, and use th...

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 stripe missing restoring method based on an edge constraint and self-adaptive morphological filtering, belongs to the field of hyperspectral image processing in the remote sensing image processing, and aims to solve the problem of incapability of restoration when stripe missing occurs in continuous spectrum bands in the acquisition process of a hyperspectral image. The hyperspectral image stripe missing restoring method comprises the steps of detecting a stripe and determining a specific position of the stripe missing in the hyperspectral image; restoring the edge and preferably restoring edge information in the stripe missing; generating a self-adaptive structural element based on the edge constraint for each damaged pixel of stripe missing, the self-adaptive structural element being capable of protecting the hyperspectral image information and greater than the width of the stripe missing so as to ensure the structural element can cover an undamaged region; and performing self-adaptive morphological filtering and determining a final restoring value of the damaged pixels of the stripe mission. The invention is used for hyperspectral image restoration.

Description

technical field [0001] The invention belongs to the field of hyperspectral image processing in remote sensing image processing. Background technique [0002] The hyperspectral image acquisition device is an imaging spectrometer, and the non-linear response of the sensor CCD in the spectrometer or errors in the data conversion process, improper data correction, or even damage to some functional units will cause the acquired hyperspectral data to produce abnormal pixels. , resulting in the absence of striped areas at the same position in the continuous band of the hyperspectral image. Such degradation not only affects the subjective quality and recognizability of hyperspectral images, but also affects the performance of machine classification and recognition, so restoration of hyperspectral images is important and indispensable. Although there are some recovery methods for this phenomenon, the model-based methods are often ineffective, and many methods can only restore bad li...

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): G06T5/00
Inventor 滕艺丹张晔提纯利陈雨时
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
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