Hyperspectral remote sensing image super-resolution method based on space-spectral information deep utilization
A hyperspectral remote sensing and super-resolution technology, which is applied in image analysis, image enhancement, image data processing, etc. Resolution effect, fast speed effect
Active Publication Date: 2019-08-09
XIAN UNIV OF TECH
View PDF7 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 provide a hyperspectral remote sensing image super-resolution method based on the deep utilization of space-spectral information, which solves the problem of low spatial resolution of hyperspectral remote sensing images in the prior art and makes it difficult to achieve high-precision classification and attribute analysis. 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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0046] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0047] The present invention is a hyperspectral image super-resolution method based on space-spectral information depth utilization, the specific process is as follows figure 1 As shown, the specific steps are as follows:
[0048] Step 1. Select bands from the input hyperspectral remote sensing images according to the set sampling interval, and perform super-resolution processing on the selected bands. Specifically, follow the steps below:
[0049] Step 1.1 sets sampling interval d=1, temporary variable d_tem=1;
[0050] Step 1.2. Calculate the current band L in the input low-resolution hyperspectral remote sensing image L one by one i with adjacent band L i+1 The correlation coefficient CCS, where L∈R w×h×n , i represents the serial number of the current band, and the value ranges from 1 to n-1;
[0051] Step 1.3, counting all CCS, if m...
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 super-resolution method based on space-spectral information deep utilization, which comprises the following steps: firstly, selecting wavebands from an input hyperspectral remote sensing image according to a set sampling interval, and carrying out super-resolution processing on the selected wave bands; interpolating unselected wavebandsby utilizing correlation among spectrums to obtain a complete hyperspectral image; and finally, performing internal self-fusion on the hyperspectral remote sensing image obtained through interpolation and the initially input low-resolution hyperspectral remote sensing image, and further utilizing the space-spectrum information of the unselected wave band to realize depth utilization of all the space-spectrum information contained in the input image so as to obtain a final high-resolution image. The method solves the problem that high-precision classification and attribute analysis are difficult to realize due to low spatial resolution of the hyperspectral remote sensing image in the prior art.
Description
technical field [0001] The invention belongs to the technical field of remote sensing images, and in particular relates to a method for super-resolution of hyperspectral remote sensing images based on deep utilization of space-spectral information. Background technique [0002] As one of the core loads in current deep space exploration, the hyperspectral imager can simultaneously obtain spectral information and spatial information of ground objects. Among them, spectral information can be used to invert the material composition of ground objects, while spatial information reflects the shape, texture, layout and other information of ground objects. Through the combination of the two, applications such as accurate detection and identification of ground objects and quantitative attribute analysis can be realized. [0003] However, limited by technology and cost, existing hyperspectral remote sensing images have low spatial resolution and low contrast between targets and backgr...
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 IPC IPC(8): G06T5/00
CPCG06T5/00G06T2207/10036G06T2207/20221
Inventor 胡静岳丽琴
Owner XIAN UNIV OF TECH