Hyperspectral remote sensing image reflectivity recovery method based on superpixel segmentation
A technology of superpixel segmentation and hyperspectral remote sensing, applied in image enhancement, image analysis, image data processing, etc., can solve the problem of poor reflectivity recovery accuracy of hyperspectral images
Active Publication Date: 2021-05-11
HARBIN INST OF TECH
View PDF5 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to solve the problem that existing object-based reflectance restoration methods have poor reflectivity restoration accuracy for hyperspectral images, and propose a hyperspectral remote sensing image reflectivity restoration method based on superpixel segmentation
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0050] Specific implementation mode one: the following combination figure 1 To illustrate this embodiment, the hyperspectral remote sensing image reflectance recovery method based on superpixel segmentation described in this embodiment specifically includes:
[0051] Step 1. Use the input hyperspectral remote sensing image to do fine superpixel segmentation, and calculate the segmentation matrix for fine segmentation;
[0052] Step 2. Perform rough superpixel segmentation on the input hyperspectral remote sensing image, and obtain a rough segmentation result set;
[0053] Step 3, using the finely segmented segmentation matrix and the rough segmented result set to calculate the constraint matrix;
[0054] Step 4, using the finely segmented segmentation matrix and constraint matrix to iteratively solve the reflectance of the input hyperspectral remote sensing image.
[0055] Further, in the present invention, in step 1, fine superpixel segmentation is performed on the input h...
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
Login to View More Abstract
The invention discloses a hyperspectral remote sensing image reflectivity recovery method based on superpixel segmentation, belongs to the field of remote sensing image processing, and relates to a hyperspectral image reflectivity recovery method. The method solves the problem that an existing object-based reflectivity recovery method is poor in reflectivity recovery precision of a hyperspectral image, and comprises: performing fine super-pixel segmentation by using an input hyperspectral remote sensing image, and obtaining a segmentation matrix of fine segmentation; performing rough super-pixel segmentation on the input hyperspectral remote sensing image to obtain a rough segmentation result set; calculating a constraint matrix by using the segmentation matrix of fine segmentation and the rough segmentation result set; and iteratively solving the reflectivity of the input hyperspectral remote sensing image by using the finely segmented segmentation matrix and the constraint matrix. The method is suitable for image reflectivity recovery.
Description
technical field [0001] The invention belongs to the field of remote sensing image processing and relates to a method for restoring reflectivity of hyperspectral images. Background technique [0002] In recent years, with the continuous development of remote sensing imaging technology, more and more hyperspectral cameras have been launched into space. Remote sensing systems carrying hyperspectral imagers can collect a large amount of surface reflectance data of different wavelengths, and perform target detection, image segmentation and It is of great significance for applications such as ground object classification. The rich spectral information obtained by the hyperspectral sensor can be further separated into two parts: light and shade information and reflectance information. The light and shade information is related to information such as ambient light and shadow, while the reflectance information reflects the properties of specific substances. The reflectance informati...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T7/11G06K9/62G06F17/16G06F7/78
CPCG06T7/0002G06T7/11G06F17/16G06F7/78G06T2207/10036G06F18/2411
Inventor 谷延锋谢雯金旭东
Owner HARBIN INST OF TECH