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

Sea surface target one-dimensional range profile noise reduction convolutional neural network identification method

A technology of convolutional neural network and recognition method, which is applied in the field of one-dimensional range image noise reduction convolutional neural network recognition of sea surface targets, can solve the problem of low signal-to-noise ratio, and achieve strong versatility, enhanced robustness and intelligence level, the effect of reducing adverse effects

Active Publication Date: 2021-06-15
NAVAL AERONAUTICAL UNIV
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the actual radar detection process, the sea surface environment is complex and changeable, and the signal-to-noise ratio obtained from HRRP is often low. This problem is particularly prominent in long-distance detection scenarios. have a greater impact, resulting in great challenges to its recognition accuracy and robustness

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
  • Sea surface target one-dimensional range profile noise reduction convolutional neural network identification method
  • Sea surface target one-dimensional range profile noise reduction convolutional neural network identification method
  • Sea surface target one-dimensional range profile noise reduction convolutional neural network identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] The specific implementation of embodiment 1 is divided into the following steps:

[0065] Step A-1: ​​First, let M=200, randomly generate the noise sequence NOISE, use the formula (2) to calculate the effective power PS of the noise-free HRRP, and use the formula (1) to estimate the noise under the condition of a given signal-to-noise ratio SNR The effective power PN, and the random noise sequence NOISE is normalized to the effective power, and then the normalized noise is superimposed on the noise-free HRRP to complete the noise addition process of the HRRP data. After that, noises with different SNRs were added according to the above steps, and each SNR was added 5 times to expand the data set by 5 times. Then, the HRRP data were translated in the direction of distance to expand the data set. Each time, 10 distance units were translated, and a total of 21 translations were performed. The data set before and after was enlarged by 105 times. Finally, the entire set of ...

Embodiment 2

[0076] The specific implementation of embodiment 2 is divided into the following steps:

[0077] First, referring to Step A-1 in Embodiment 1, perform preprocessing such as noise addition, expansion, and division on HRRP, and then implement according to the following Step B-2.

[0078] Step B-2: Use method 2.2 to convert the HRRP into a binary image of 0 or 1, and explore the structural feature information of the HRRP curve. First divide the entire HRRP image into small pixels, then set the pixel where the curve is located to 1, and the remaining blank pixels to 0, and finally convert the vertical axis of HRRP to the Y axis of the two-dimensional image, and the horizontal axis The axis is converted to the X axis of the two-dimensional image, and the image conversion of HRRP is completed. The conversion effect is as follows Figure 8 shown.

[0079] Then, with reference to step A-3 and step A-4 in Example 1, a deep learning network model integrating noise reduction and recogn...

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 sea surface target one-dimensional range profile noise reduction convolutional neural network identification method, and belongs to the field of radar signal processing. Aiming at a low signal-to-noise ratio condition, original HRRP data is reasonably pre-processed to construct multiple types of sea surface target data sets under different signal-to-noise ratio conditions, a one-dimensional noise reduction convolutional neural network is constructed by using a deep learning technology, the signal-to-noise ratio of the low signal-to-noise ratio data is improved on the basis of keeping the high signal-to-noise ratio data free of fluctuation, and the residual structure of a convolutional neural network is utilized to reduce the learning burden of the deep neural network, so that an intelligent sea surface target classification and recognition model integrating noise reduction and classification is constructed, the recognition accuracy of the sea surface target is improved, the sea surface target recognition performance under the condition of low signal-to-noise ratio is improved, the classification and identification capability of the sea radar in a complex sea surface environment is enhanced, and the method has popularization and application values.

Description

technical field [0001] The invention belongs to the field of radar signal processing, and in particular relates to a noise reduction convolutional neural network recognition method for a one-dimensional range image of a sea surface target. Background technique [0002] Reliable sea surface target recognition method is very important to every link of sea target reconnaissance. At present, high-resolution broadband radar technology has been widely used in the field of target recognition. The high-resolution one-dimensional range profile (HRRP) characterizes the distribution of scattering centers along the radar line of sight, including the structural characteristics of the target, because it is easy to obtain and process, etc. It plays an important role in the field of radar sea surface target recognition. [0003] There are many HRRP target recognition methods, such as HRRP target recognition algorithm based on subspace, HRRP radar target recognition method based on scatteri...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06F2218/04G06F2218/08G06F2218/12G06F18/213
Inventor 简涛王哲昊王海鹏刘瑜刘传辉李刚李辉杨予昊张健
Owner NAVAL AERONAUTICAL 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

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