A hyperspectral image classification method based on triple GAN
A technology of hyperspectral image and classification method, which is applied in the field of hyperspectral image classification to achieve the effect of ensuring practical work efficiency, reducing feature dimensions and efficient classification
Active Publication Date: 2022-08-05
HOHAI UNIV
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, it is worth noting that there are still some problems that need to be solved urgently (1) applying advanced deep learning network structure to solve hyperspectral image classification problems, (2) semi-supervised classification of hyperspectral images based on deep learning
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
[0059] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.
[0060] The present invention designs a hyperspectral image classification method based on Triple GAN. In practical applications, such as figure 1 As shown, firstly perform the following steps A to F to realize the acquisition of the image classification model.
[0061] Step A. Collect each hyperspectral sample image corresponding to each preset actual classification, construct a sample image set, and then proceed to step B.
[0062] Step B. For each hyperspectral sample image in the sample image set, perform the principal component analysis method to perform dimension reduction operation, update each hyperspectral sample image in the sample image set, and then proceed to step C. In practical applications, the PCA principal component analysis method can be used for dimensionality reduction operation, and the spectral features of hype...
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 relates to a hyperspectral image classification method based on Triple GAN. First, a principal component algorithm is used to compress the spectral features of hyperspectral images to reduce feature dimensions and redundancy; Select image features; then use the Triple GAN classification network to complete the classification operation of hyperspectral sample images based on various image features to be selected. Combined with the actual classification of hyperspectral sample images, select the image features to be selected corresponding to the highest classification accuracy. As the target image feature corresponding to the sample image set; finally, the target image feature is used as input, the actual classification of the hyperspectral sample image is output, and the training of the Triple GAN classification network is completed to obtain an image classification model; in practical applications, through The target image features can be classified by applying the image classification model, thereby realizing the efficient classification of the hyperspectral images and ensuring the actual work efficiency.
Description
technical field [0001] The invention relates to a hyperspectral image classification method based on Triple GAN, and belongs to the technical field of remote sensing image processing. Background technique [0002] Remote sensing refers to an information collection method in which the electromagnetic spectrum of the observation target is collected by a specific imaging instrument on an aerospace platform, and imaged to obtain various characteristic information of the observation object. Since the modern remote sensing technology was put into use in the 1960s, it has played a huge role in various fields. Therefore, modern remote sensing technology has become an important symbol to measure a country's technological development level and comprehensive strength. In order to further strengthen human's ability to explore and develop the earth's resources, natural environment and extraterrestrial space, and at the same time expand the means of human beings to monitor various abnorma...
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 Patents(China)
IPC IPC(8): G06V20/13G06V10/40G06V10/774G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/13G06V10/40G06N3/047G06N3/045G06F18/2431G06F18/241G06F18/214
Inventor 薛朝辉郑晓菡
Owner HOHAI UNIV