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

Outlier elimination method based on improved Kalman filtering

A Kalman filtering and outlier technology, applied in the reflection/re-radiation of radio waves, radio wave measurement system, image enhancement and other directions, to achieve the effect of good real-time performance and simple principle

Pending Publication Date: 2021-05-28
NANJING UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Zhu Zhuanmin and other scholars proposed a method to dynamically eliminate outliers, using the new information covariance to set the confidence interval, and then multiplying a constant factor by the prediction error covariance matrix to judge whether its value is within the confidence interval, so as to achieve The purpose of eliminating outliers, but the constant factor still needs to be manually set in advance

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
  • Outlier elimination method based on improved Kalman filtering
  • Outlier elimination method based on improved Kalman filtering
  • Outlier elimination method based on improved Kalman filtering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] Aiming at the state filtering part in the target tracking process, the invention proposes a method for dynamically improving the innovation. The innovation in the invention is the difference between the real measured value and the predicted value of the target on the distance. The actual measurement of the target can be expressed as Z(k)=[x, y]', where x, y represent the distance value of the target in two-dimensional space coordinates, which is obtained by various sensors such as radar and ultrasonic sensors in actual engineering , camera, etc. The state of the target can be expressed as X(k)=[x,v x ,a x ,y,v y ,a y ]'. The first three items and the last three items respectively represent the target distance, velocity, and acceleration in the x and y directions, which are the real motion attributes of the target. The measurement value Z is obtained by observing the real state X of the target through the sensor. Then, the present invention is used to judge and cor...

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 an outlier elimination method based on improved Kalman filtering. The method comprises the following steps: obtaining an innovation value v from a (k-N + 1) moment to a k moment through a windowing estimation method, and calculating the mathematical expectation of an innovation covariance according to the innovation value v; comparing the trace of the current prediction innovation covariance with the trace of the innovation covariance mathematical expectation matrix to obtain a regulatory factor lambda; and dynamically correcting the real measurement according to the adjustment factor to obtain the adjusted measurement, and performing state estimation by using the adjusted measurement. According to the method, the mathematical expectation of the innovation covariance is calculated according to the previously obtained measurement innovation, the mathematical expectation is compared with the currently predicted innovation covariance value to obtain a specific value, and the real measurement is dynamically corrected by using the specific value, so that the self-adaptive adjustment effect is achieved without manual setting.

Description

technical field [0001] The invention relates to an outlier elimination method, in particular to an outlier elimination method based on an improved Kalman filter. Background technique [0002] In the field of multi-target tracking, there are a lot of clutter and noise in the observation background, as well as the observation error of the sensor itself. The obtained measurements will have "outliers" that do not match the actual situation. However, if such "outlier" targets are not removed, it will bring great errors to subsequent data processing, and even lead to subsequent data association errors and filter divergence. [0003] Therefore, when processing the measurement data, it is first necessary to eliminate some impossible "outlier" targets according to the engineering requirements and the parameters of the sensor itself. [0004] Zhu Zhuanmin and other scholars proposed a method to dynamically eliminate outliers, using the new information covariance to set the confidenc...

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): G01S7/02G01S13/66G01C23/00G06F17/18G06T7/277G06T5/00
CPCG01S7/02G01S13/66G01C23/00G06F17/18G06T7/277G06T2207/20076G06T5/70
Inventor 申明磊房挺戚湧刘豫晋
Owner NANJING UNIV OF 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