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

Sea surface small target detection method based on random forest

A technology of small target detection and random forest, which is used in measurement devices, radio wave measurement systems, reflection/re-radiation of radio waves, etc.

Active Publication Date: 2020-12-29
NANJING UNIV OF INFORMATION SCI & TECH
View PDF13 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But at the same time, it will introduce the design problem of two classifiers in the high-dimensional feature space, and the classifier must have the characteristics of false alarm controllability

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 small target detection method based on random forest
  • Sea surface small target detection method based on random forest
  • Sea surface small target detection method based on random forest

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0071] Such as figure 1 The random forest-based sea surface small target detection method shown includes the following steps

[0072] S1, get the echo vector z

[0073] S1.1. The N pulse echo vectors of a certain distance unit received by the radar are z=[z(1),z(2),...,z(N)] T , that is, the echo vector z of the cell under test (CUT) and P reference distance cells around the CUT p ,p=1,2,...,P.

[0074] S1.2. The essence of detection is whether there is a target echo in the echo sequence. Therefore, the detection problem can be reduced to a binary hypothesis test:

[0075]

[0076] Among them, c represents the sea clutter vector, s represents the target echo vector. h 0 Assume that there is only sea clutter in the echo vector, that is, there is no target echo; H 1 Assume that the representation echo vector contains ...

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 small target detection method based on a random forest. The method comprises the following steps of: acquiring an echo vector of a distance unit to be detected and an echo vector of a surrounding reference distance unit; extracting multi-dimensional features in a time domain, a frequency domain and a time-frequency domain; constructing a high-dimensional feature vector; performing normalization processing on the feature vector; extracting a normalized feature vector according to simulated target-containing echo data and sea clutter data, and constructing two types of balanced training samples; taking the two types of training samples as input of the random forest, establishing a mathematical function expression between a splitting factor and a false alarm rate, and obtaining a false alarm controllable random forest two-classifier; and substituting the normalized feature vector into the random forest two-classifier to obtain an output classificationlabel, and judging whether a target exists in the echo vector or not. According to the invention, the detection performance of the radar under the low SCR condition can be improved, the difficulty ofdesigning the false alarm controllable two-classifier in the high-dimensional feature domain is solved, and a new idea is provided for sea surface small target detection.

Description

technical field [0001] The invention relates to the technical field of radar signal processing, in particular to a random forest-based sea surface small target detection method. Background technique [0002] Small target detection under high-resolution sea clutter background has always been a research hotspot and difficulty. The main difficulty in detection lies in the complex space-time variation characteristics of sea clutter and the weak self-echo of low-speed small targets, resulting in low signal-to-clutter ratio (SCR) during detection. The traditional single feature detector has many false alarm points and low detection probability. Therefore, it is necessary to develop a detection method based on multi-dimensional feature union to improve the detection probability of small targets on the sea surface. [0003] The detection method of multi-dimensional feature combination refers to mining the difference between sea clutter and target echo from multiple domains such as...

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): G01S13/02G01S7/41
CPCG01S13/02G01S7/414Y02A90/10
Inventor 施赛楠杨静程思宇董泽远
Owner NANJING UNIV OF INFORMATION SCI & TECH
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