High spectral image classification method based on NSCT transformation and DCNN

A technology of hyperspectral image and classification method, applied in the field of hyperspectral image classification based on non-subsampling contourlet transform and deep convolutional neural network, and the field of hyperspectral image classification, can solve the problem of compressing the spatial resolution of hyperspectral images, which cannot be effectively Extracting hyperspectral image detail information, hyperspectral image edge and texture detail information mining and other issues to improve classification performance and performance

Active Publication Date: 2017-11-03
XIDIAN UNIV
View PDF4 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these hyperspectral image classification methods are all carried out in the spatial and spectral domains, and do not mine the potential edge and texture details of the hyperspectral image, while the hyperspectral image will inevitably compress the spectral resolution while improving the sp

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
  • High spectral image classification method based on NSCT transformation and DCNN
  • High spectral image classification method based on NSCT transformation and DCNN
  • High spectral image classification method based on NSCT transformation and DCNN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] Hyperspectral remote sensing is a technology that uses imaging spectrometers to simultaneously image the ground surface with a band width of less than 10nm from the ultraviolet to the thermal infrared band of the electromagnetic spectrum. It can not only reflect the surface characteristics of the object, but also reflect the internal characteristics of the object. Therefore, it has been widely used in the field of remote sensing. Hyperspectral image classification is a very important field in the application of hyperspectral remote sensing, and it is also the basis of many other applications of hyperspectral remote sensing, so it is currently the most extensive field of hyperspectral remote sensing research.

[0029] At present, most of the classification methods of hyperspectral images are carried out in the spatial domain. While the spectral resolution of hyperspectral images is improved, the spatial resolution of hyperspectral images will inevitably be compressed, result...

Embodiment 2

[0041] The hyperspectral image classification method based on NSCT transform and DCNN is the same as that in Embodiment 1. The non-downsampled contourlet (NSCT) transform in step (2) of the present invention is performed according to the following steps:

[0042] (2a) Principal component analysis (PCA) is used to perform dimensionality reduction operations on the original hyperspectral image in the spectral direction, combining the energy retention of the principal components and the computational complexity of the subsequent NSCT transformation, the present invention retains the first three principal components.

[0043] (2b) Perform 3-level non-downsampled contourlet (NSCT) transformation on the three principal components obtained after dimensionality reduction. The sub-band coefficient matrix obtained by the transformation has an exponential relationship with the number of transformation stages, that is, the k-th transformation The low-frequency subband coefficient matrix obtaine...

Embodiment 3

[0048] The hyperspectral image classification method based on NSCT transform and DCNN is the same as that of embodiment 1-2. The block fetching operation described in step (4) of the present invention is performed according to the following steps:

[0049] (4a) In order to classify each pixel in the original hyperspectral image, before fetching the block, perform 2-layer 0 filling operation on the periphery of the stereo block obtained by superimposing the high-frequency subband coefficient matrix to obtain a size of (h+4 )×(w+4)×c three-dimensional block;

[0050] (4b) Taking each pixel as the center, use a 5×5 sliding window to fetch the three-dimensional block, and the size of the fetched block is 5×5×c;

[0051] (4c) Remove the block with the category label value of the center pixel point of 0, complete the block fetching operation, and obtain the sample set.

[0052] Because the spatial resolution of hyperspectral images is generally low, it is impossible to directly classify the...

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 high spectral image classification method based on NSCT transformation and DCNN. The objective of the invention is to solve the problem that texture details and directivity information of to-be-classified high spectral images cannot be sufficiently excavated in the prior art. The method comprises steps of inputting a high spectral image; carrying out NSCT transformation; carrying out normalization and block taking operation on the transformed stereo blocks; randomly selecting training, verification and test sample sets in a sample set; constructing a depth convolution neural network and setting network super-parameters; training the network; inputting the test samples into the network to obtain actual classification tags and drawing terrain classification result graph; and comparing the classification tags and the reference tags of the test samples, calculating classification evaluation indexes, drawing loss curve graphs of the training and verification samples of increasing along with the iteration times, thereby finishing the terrain classification. According to the invention, more texture details, directivity information and space information of the high spectral image are kept; the classification is quietly precise; and the method can be applied to meteorology and environmental monitoring, land utilization, urban planning and disaster prevention and reduction.

Description

Technical field [0001] The invention belongs to the technical field of image processing, and relates to hyperspectral image classification, in particular to a hyperspectral image classification method based on non-subsampled contour wave (NSCT) transformation and deep convolutional neural network (DCNN). It can be applied to weather monitoring, environmental monitoring, land use, urban planning, disaster prevention and mitigation, etc. Background technique [0002] Because hyperspectral remote sensing images continuously image objects in a wide range of wavelengths, they have the advantages of high spectral resolution and rich information. Therefore, hyperspectral images have been widely used in the field of remote sensing. Hyperspectral image classification has important applications in the fields of geological prospecting, food safety, environmental monitoring, etc. It is also the basis for other applications in the field of hyperspectral remote sensing. Its purpose is to divid...

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): G06K9/00G06K9/62
CPCG06V20/13G06F18/2135G06F18/2411
Inventor 白静徐敏陈盼焦李成张向荣缑水平
Owner XIDIAN UNIV
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