Target classification identification method used for distributed optical fiber sensing system

A distributed optical fiber and sensing system technology, applied in the field of target recognition, can solve the problems of high false alarm rate, fast processing speed, and long cabling distance, and achieve improved noise robustness, high classification accuracy, and improved accuracy sexual effect

Inactive Publication Date: 2018-06-22
NO 54 INST OF CHINA ELECTRONICS SCI & TECH GRP
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the long cabling distance and the complex and diverse environment in long-distance areas, the detection false alarm rate is high
In addition, since the distributed sensing system needs to process the target data in real time, the processing time resources are limited, so the complex target detection and classification methods cannot be adopted.
[0003] Currently, Distributed optical fiber sensing systems generally use time-domain processing methods with relatively simple calculations such as amplitude judgment. This type of method has a fast processing speed but a high false alarm rate, which seriously affects the performance of this type of sensing system.

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
  • Target classification identification method used for distributed optical fiber sensing system
  • Target classification identification method used for distributed optical fiber sensing system
  • Target classification identification method used for distributed optical fiber sensing system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0037] A kind of object classification recognition method for distributed optical fiber sensing system, it comprises the following steps:

[0038] Step 1, constructing a binary detection classifier, the binary detection classifier includes at least two stages of binary classification processing based on a binary detection method, wherein the first stage of processing is used to divide input data into noise and target categories, The second-level processing is used to divide the target class data output by the first-level processing into two types: the first-level target and the first-level other targets; from the second level of processing onwards, the latter level of processing is used to divide the output of the previous level of processing Other targets at the current level are further subdivided into two types of target at this le...

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 target classification identification method used for a distributed optical fiber sensing system, and relates to the technical field of target identification. The method mainly comprises the processing steps of data screening, feature extraction, classifier design, cross testing, actual application and the like. According to the method, multiple feature parameters of target data are subjected to maximum likelihood ratio detection method-based multilevel classification through a binary detection classifier, and information fusion processing is performed in time and space dimensions, so that high-efficiency and low-false-alarm-rate target detection and classification identification are realized; and the method has the characteristics of high target detection identification probability, low false alarm rate, high calculation speed and simple engineering realization, solves the problem of high false alarm rate of sensing detection in a complex working environment or a complex target detection identification algorithm, and is especially suitable for the target detection identification process under the conditions of long-distance detection, complex and diversified environments and the like.

Description

technical field [0001] The invention relates to the technical field of target recognition, in particular to a target classification and recognition method with a low false alarm rate for a distributed optical fiber sensing system. Background technique [0002] (Optical Time Domain Reflectometer, Optical Time Domain Reflectometer) Distributed optical fiber sensing system can be used to sense and detect active targets in long-distance areas where cables are laid. However, due to the long cable laying distance and the complex and diverse environment in long-distance areas, the detection false alarm rate is high. In addition, since the distributed sensing system needs to process the target data in real time, the processing time resources are limited, so the complex target detection and classification methods cannot be adopted. [0003] Currently, Distributed optical fiber sensing systems generally adopt time-domain processing methods with relatively simple calculations such...

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): G06K9/62
CPCG06F18/2413
Inventor 姚剑
Owner NO 54 INST OF CHINA ELECTRONICS SCI & TECH GRP
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