Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

SAR target recognizing algorithm based on guide reconstitution and norm constraint DBN

A target recognition and guidance technology, applied in the field of target recognition algorithms, can solve problems such as high complexity, many training times, and low recognition rate

Active Publication Date: 2019-03-22
NORTHWESTERN POLYTECHNICAL UNIV +1
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of the traditional DBN-based SAR target recognition algorithm, such as high network structure complexity, more training times, and low recognition rate, the present invention proposes a fast SAR target recognition algorithm based on guided reconstruction and weighted norm-constrained deep belief network

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
  • SAR target recognizing algorithm based on guide reconstitution and norm constraint DBN
  • SAR target recognizing algorithm based on guide reconstitution and norm constraint DBN
  • SAR target recognizing algorithm based on guide reconstitution and norm constraint DBN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0083] Now in conjunction with embodiment, accompanying drawing, the present invention will be further described:

[0084] Step 1: Two-scale image reconstruction based on guided filter

[0085] For target recognition, the two-scale reconstruction of the original image is to use the guided filter processing of the feature map in order to highlight the detail differences between different types of target images. The specific steps are as follows:

[0086] For the original image I n Do Laplace filtering to get high-frequency image H n :

[0087] h n = I n *L (1)

[0088] In the formula, I n is the nth source image, L is a 3×3 Laplacian filter, H n Take the absolute value and make a local average to reconstruct the feature map S n :

[0089] S n =|H n |*g r,σ (2)

[0090]In the formula, g is a (2r+1)×(2r+1) Gaussian low-pass filter, σ is the standard deviation of the Gaussian low-pass filter, r and σ are both 5. The feature map provides a good representation of 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 provides an SAR target recognizing algorithm based on guide reconstitution and norm constraint DBN. In order to solve the problems that an SAR target recognizing algorithm based on DBN is high in network structure complexity, large in training frequency, low in recognizing rate and the like, the guide reconstitution algorithm is put forward to conduct reconstitution preprocessing ontraining samples and testing samples, a one-dimensional image vector is formed through cutting and then extending, low-dimensional features are extracted through a weighted norm constraint deep beliefnetwork (DBN), and targets are classified through Softmax. It is shown through experimental results that the method can reduce the dimension of the image features and the frequency of network training and the network recognizing performance is further improved.

Description

technical field [0001] The invention relates to a target recognition algorithm based on guided reconstruction and norm-constrained deep belief network (Deep BeliefNetworks, DBN), which can be applied to various military or civilian image processing systems. Background technique [0002] In modern high-tech warfare, timely and accurate acquisition of battlefield information and efficient assessment of the battlefield situation play a very important role in competing for military dominance on the battlefield. As an important microwave imaging sensor, Synthetic Aperture Radar (SAR) is widely used in environmental monitoring, resource exploration, national defense and military fields. [0003] In recent years, target recognition technology based on deep neural network has achieved good results in various fields, promoting its research in SAR image target recognition. The document "SAR Automatic Target Recognition Based on Euclidean Distance Restricted Autoencoder, IEEE J.Sel.To...

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): G01S7/41
CPCG01S7/417
Inventor 王健秦春霞杨珂任萍
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products