Supercharge Your Innovation With Domain-Expert AI Agents!

Two-dimensional computable target detection, recognition and identification performance predicting method

A target detection and performance prediction technology, applied in the field of target recognition, can solve the problems of randomness, subjectivity, intelligence, flexibility and knowledge that are difficult to quantify, single parameter, etc., and achieve the effect of strong operability

Active Publication Date: 2014-03-26
HUAZHONG UNIV OF SCI & TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the randomness and subjectivity of human beings are great, and their intelligence, flexibility and knowledge are difficult to quantify. Therefore, Johnson's criterion lacks operability and repeatability, and computers cannot use this criterion
More importantly, the method of the Johnson criterion only uses the spatial resolution (line logarithm) as a variable parameter to define 50% detection probability, identification probability and identification probability. The parameter is single, and it is not suitable for complex conditions where multiple parameters are variable.

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
  • Two-dimensional computable target detection, recognition and identification performance predicting method
  • Two-dimensional computable target detection, recognition and identification performance predicting method
  • Two-dimensional computable target detection, recognition and identification performance predicting method

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0074] Detection example 1: SNR=5, imaging distance is a variable

[0075] Obtain the two-dimensional measured image or two-dimensional simulated image of the rotor helicopter 500D under the condition of signal-to-noise ratio SNR=5 from the target sample database, and then use the multi-stage filtering and binary segmentation method to detect the target in turn on the obtained image, Then the target detection results are analyzed to obtain the detection probability of the target two-dimensional image under different imaging distance conditions.

[0076] In this example, the exponential form is used to perform two-dimensional curve fitting on the detection results, such as Figure 7 As shown, the specific expression form of the exponential fitting curve function of f(X) is given in the figure, in this example b 3 =0,b 2 =0,b 1 =1.778,b 0 =-0.0008503,

[0077] That is, f(X)=1.778*exp(-0.0008503*X). It can be seen from the figure that under the condition of SNR=5, the detec...

example 2

[0078] Detection example 2: SNR=100, imaging distance is a variable

[0079] Obtain the two-dimensional measured image or two-dimensional simulation image of the rotor helicopter 500D under the condition of signal-to-noise ratio SNR=100 from the target sample database, and then use the multi-stage filtering and binary segmentation method to detect the target in sequence. Then the target detection results are analyzed to obtain the detection probability of the target two-dimensional image under different imaging distance conditions.

[0080] In this example, the 4th-order polynomial form is used to perform two-dimensional curve fitting on the detection results, such as Figure 8 As shown, the specific expression form of the 4th order polynomial fitting curve function of f(X) is given in the figure, in this example a 4 =0,a 3 =0,a 2 =0,a 1 =0.00028,a 0 =0.90211, that is, f(X)=0.00028×X+0.90211. It can be seen from the figure that under the condition of SNR=100, the detecti...

example 3

[0082] Detection example 3: Signal-to-noise ratio SNR=5, the number of line pairs is a variable

[0083] Obtain the two-dimensional measured image or two-dimensional simulated image of the fixed-wing aircraft F117 under the condition of signal-to-noise ratio SNR=5 from the target sample database. The detection probability of the two-dimensional image of the target under different logarithm conditions is obtained by analyzing the target detection results.

[0084] In this example, a 5th-order polynomial is used to fit the two-dimensional curve to the detection results, such as Figure 9 As shown, the specific expression form of the 5th order polynomial fitting curve function of f(X) is given in the figure, in this example

[0085] a 5 =0,a 4 =0,a 3 =0,a 2 =-0.0008,a 1 =0.0015,a 0 =0.2839, namely f(X)=-0.0008×X 2 +0.0015×X 1 +0.2839. It can be seen from the figure that under the condition of SNR=5, the detection probability of the target sample can be obtained under di...

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 two-dimensional computable target detection, recognition and identification performance predicting method. The method comprises the following steps of: using a polynomial or an exponential function as a curve fitting function, selecting a sample image database of specific imaging parameters for fitting to obtain a detection / recognition / identification probability computational formula, and adopting the formula to compute and obtain the detection / recognition / identification probability of a measured image. The method overcomes the subjectivity, randomness and non-repeatability of the current Johnson rule, the subjective judgment of people is approximately realized through the computer algorithm, and the operability is strong.

Description

technical field [0001] The invention belongs to the field of target recognition, and in particular relates to a two-dimensional computable target detection, recognition and recognition performance prediction method. Background technique [0002] The imager's ability to distinguish two-dimensional target images (sequences) is divided into three levels, namely detection, recognition and identification. The unique, main factors and basic laws that restrict the recognition ability have always been what human beings want to decipher, because human beings hope that computers can realize this function. [0003] At home and abroad, the research on 2D object image resolvability criterion is based on Johnson's artificially judged boundary criterion, but the research on objective, computer-implemented 2D computable criterion is still blank. The Johnson criterion is a statistical study of the criterion based on the judgment results of a group of human observers. However, human beings ...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/46
Inventor 张天序丁晓白易可佳汪小平王登位彭凡张力关静陈浩
Owner HUAZHONG UNIV OF SCI & TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com