Deep wavelet neural network-based polarimetric SAR (synthetic aperture radar) image classification method
A wavelet neural network and classification method technology, applied in the field of image processing, can solve the problems of inability to extract high-dimensional features and low classification accuracy, and achieve the effects of improving classification accuracy, strong approximation and fault tolerance, and good robustness.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0034] Example 1:
[0035] The present invention is a classification method of polarization synthetic aperture radar SAR image based on deep wavelet neural network. figure 1 , A detailed description of the specific implementation steps of the present invention:
[0036] Step 1: The input image is actually the coherence matrix of a polarized synthetic aperture radar SAR image to be classified, see figure 2 , figure 2 Shown is the L-band multi-view polarization SAR image of Flevoland, Netherlands obtained by the AIRSAR platform in 1989. The coherence matrix of the image is a matrix of size 3×3×N, where N is the polarization synthetic aperture radar SAR image The total number of pixels.
[0037] Step 2: Preprocessing. Use Lee filter with a window size of 7×7 to filter the above coherence matrix to obtain the filtered coherence matrix. In specific simulation experiments, 3×3, 5×5, 7 ×7 equal-size windows filter the coherence matrix of the polarized synthetic aperture radar SAR image, ...
Example Embodiment
[0054] Example 2:
[0055] The polarization synthetic aperture radar SAR image classification method based on the deep wavelet neural network is the same as in embodiment 1, wherein the calculation hidden layer output formula described in step 4b and step 4e is as follows:
[0056] ψ ( j ) = exp ( - ( X k = 1 m W jk ′ x k - b j a j ) 2 / 2 ) cos ( 5 X ( X k = 1 m W jk ′ x k - b j a j ) )
[0057] Among them, ψ(j) represents the output of the hidden layer node j, where ψ is a general representation of the output of the hidden layer node, and the output of the hidden layer node of the first layer network is ψ 1 Indicates that the output of the hidden layer node of the second layer network is ψ 2 Indicates that m is the number of input nodes. In this example, the number of input nodes of the first layer network is equal to the number of fea...
Example Embodiment
[0062] Example 3:
[0063] The polarization synthetic aperture mine SAR image classification method based on the deep wavelet neural network is the same as in the embodiment 1-2, and the mean square error formulas described in step 4c and step 4f are as follows:
[0064] E = X s = 1 S X i = 1 n ( h ( i ) - x i ) 2
[0065] Among them, E represents the mean square error of the sample, where E is a total representation of the mean square error, and the error of the first layer network is E 1 Indicates that the error of the first layer network is E 2 Indicates that S is the number of training samples and n is the number of output nodes. In this example, the number of output nodes of the first-layer network is equal to the number of input nodes, and the value here is 9, and the number of output nodes of the second-layer network is equal to the second layer The number of input nodes of the network, here is the value 100, h(i)...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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