SAR image target classification method based on multi-kernel scale convolutional neural network
A convolutional neural network and target classification technology, which is applied in the field of SAR image target classification based on multi-core scale convolutional neural network, can solve the problem that the overall contour features of the target in SAR images are easily lost, the local detail features are easily lost, and the classification performance is easy to be lost. It can reduce the number of parameters to be trained, reduce the calculation time, and reduce the sensitivity.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0033] The present invention will be further described below in conjunction with the examples, and the present invention includes but not limited to the following examples.
[0034] In this example, if figure 1 As shown, a SAR image target classification method based on multi-core scale convolutional neural network includes the following steps:
[0035] Step 1: Select different types of SAR images as the sample set of the multi-core scale convolutional neural network, and unify the size of the SAR images in the sample set to 88×88 by downsampling, so as to obtain the sample set X={ x 1 ,X 2 ,...,X i ,...,X n},X i Represents the i-th SAR image sample in the sample set X after uniform size, i∈[1,n], n represents the sample size;
[0036] Step 2: For the convolution kernel with a scale of l×l in the jth convolutional layer The weight value is initialized, and the specific initialization method is a truncated Gaussian distribution; among them, j=1,2,3 represent the shallow l...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com