SAR (Synthetic Aperture Radar) image recognition method based on sparse representation and multi-feature decision level fusion

A decision-level fusion and sparse representation technology, applied in the field of SAR image recognition based on sparse representation and multi-feature decision-level fusion, can solve the problems of long training time, deep model optimization design, lack of training samples, etc., and achieve high classification accuracy, The algorithm has strong applicability and the effect of improving the recognition rate

Active Publication Date: 2018-06-05
HANGZHOU DIANZI UNIV
View PDF2 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the following problems need to be solved when performing feature learning based on deep convolutional neural networks: (1) lack of training samples; (2) deep model needs to be optimized; (3) long training time

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 (Synthetic Aperture Radar) image recognition method based on sparse representation and multi-feature decision level fusion
  • SAR (Synthetic Aperture Radar) image recognition method based on sparse representation and multi-feature decision level fusion
  • SAR (Synthetic Aperture Radar) image recognition method based on sparse representation and multi-feature decision level fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] The present invention will be further described below in conjunction with accompanying drawing.

[0016] Depend on figure 1 Shown, the specific implementation steps of the present invention are as follows:

[0017] Step (1). Preprocessing the original SAR image to obtain the target slice image I. The specific operation is:

[0018] The mean filter algorithm is used to filter the original SAR image, and the filter kernel size is 3×3. Taking the two-dimensional center point of the image plane as the coordinate origin, extract the SAR slice image I with a size of 64×64, and divide it by 255.0, so that the gray level of the image is in the interval [0, 1].

[0019] Step (2). Extract the target gray feature vector. The specific operation is:

[0020] Arrange the target slice image I in columns to convert it into a vector f 1 . the vector f 1 To normalize, first divide by the vector f 1 The 2 norm of , and then subtract the mean value of the vector to obtain the gray...

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 relates to an SAR (Synthetic Aperture Radar) image recognition method based on sparse representation and multi-feature decision level fusion. In order to increase a recognition rate anda recognition speed of an SAR target recognition algorithm, the SAR image recognition method extracts gray scale features and dimension-reduced random convolution feature vectors from an SAR slice image, then optimizes a dictionary composed of the feature vectors extracted from each type of training samples by adopting a dictionary learning algorithm to form a dictionary, and finally, recovers a sample sparse coefficient through the dictionary to obtain a classification result. According to the method provided by the invention, the recognition speed is greatly increased, and the recognition precision is improved; the method has a better application prospect.

Description

technical field [0001] The invention belongs to the field of SAR (Synthetic Aperture Radar) image automatic target recognition, and relates to a SAR image recognition method based on sparse representation and multi-feature decision-making level fusion. Background technique [0002] SAR image automatic target recognition is one of the core problems that need to be solved urgently in SAR image interpretation. Its working process is to first find out the region of interest in the SAR image, and then classify it to determine the target category. SAR image target recognition has been widely used in national economy and national defense construction, including marine monitoring system, mineral detection and so on. [0003] Feature extraction and classifier design are two key factors affecting the accuracy of target recognition in SAR images. The features extracted from SAR images mainly include features based on mathematical transformation, computer vision features, and electroma...

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): G06K9/62G06K9/46G06N3/04
CPCG06V10/56G06N3/045G06F18/217G06F18/25
Inventor谷雨彭冬亮冯秋晨刘俊陈华杰
OwnerHANGZHOU DIANZI UNIV