Convolutional neural network-based sea surface weak target detection method and system

A convolutional neural network, weak target detection technology, applied in neural learning methods, biological neural network models, neural architecture and other directions, can solve difficult radar echo target signals, limited detection capabilities, echo energy dispersion and other problems, Achieve the effect of low false alarm probability, reduce difficulty, and suppress interference

Inactive Publication Date: 2019-09-20
HUAZHONG UNIV OF SCI & TECH
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Sea radar detection of weak targets on the sea often faces the following challenges: ① Strong clutter generated by the complex ocean environment makes the echo signals received by the radar present non-Gaussian, nonlinear, and non-stationary properties, making it difficult to accurately construct radar echoes; ②Single-dimensional feature extraction methods often provide limited essential information and are easily affected by the sea peak phenomenon, resulting in the difficulty in reducing the probability of false alarms; ③The echo signal of the weak target itself is weak and the echo energy is scattered , is easily covered by clutter signals, and the difference between the target signal and clutter signals is small, which makes it difficult to manually establish a feature space with sufficient discrimination; ④Traditional weak target detectors on the sea often use a single threshold threshold classification method, which is complex and multi- Under changing sea conditions, it will be difficult to select the threshold, and the detection ability is limited, making it difficult to achieve accurate detection

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
  • Convolutional neural network-based sea surface weak target detection method and system
  • Convolutional neural network-based sea surface weak target detection method and system
  • Convolutional neural network-based sea surface weak target detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not constitute a conflict with each other.

[0040] Due to the complex reasons for the formation of sea clutter and the multiple influences of the external environment and radar parameters, the sea peaks caused by wind speed and waves are difficult to filter out and have strong interference, which is easy to cause false alarms in radar detection. An important bottleneck for accurate detection of weak objects. In complex sea conditions, it...

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 weak target detection method and system based on a convolutional neural network, and belongs to the technical field of radar signal processing. The method comprises the following steps: firstly, acquiring a sea surface radar echo signal, and extracting features of the radar echo signal to obtain time domain feature data of sea clutter; constructing a time-distance-amplitude two-dimensional image according to the time domain characteristic data of the sea clutter; then, taking the two-dimensional image as a training set / test set; training a constant false alarm detector based on the CNN; classifying a sea clutter two-dimensional image to be detected according to the learned features by using the features of the input two-dimensional image autonomously extracted by the CNN, and adjusting the CNN to optimize a constant false alarm detector according to a constant false alarm detection requirement in a radar signal detection problem, thereby realizing accurate detection of a target signal. According to the invention, the sea clutter image is combined to construct and the convolutional neural network is used to design the detector, and accurate detection of the sea surface weak target can be realized under the conditions of low signal-to-clutter ratio, low false alarm probability and short observation duration.

Description

technical field [0001] The invention belongs to the technical field of radar signal processing, and more specifically, relates to a method and system for detecting weak targets on the sea surface based on a convolutional neural network. Background technique [0002] The ocean is rich in resources, and exploring this vast treasure has been a tireless pursuit of people since ancient times. With people's emphasis on the ocean and the development of modern science and technology, seawater desalination technology, sea surface detection technology, deep-sea detection technology, deep-sea diving technology, marine communication technology, marine remote sensing technology and marine navigation technology and other marine development support technologies have also flourished. Among them, sea surface detection technology has crucial applications in military and civilian fields, and is closely related to the interests of each of us. Among the many sea targets to be detected, it is mo...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F2218/08G06F2218/12G06F18/2415
Inventor 李渝舟许桂桂
Owner HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products