Self-adaptive target tracking method based on multi-filter information fusion

Abstract

The invention discloses a self-adaptive target tracking method based on multi-filter information fusion. The method comprises the following steps: step 1, constructing a multi-Kalman filter data fusion tracking model; 2, judging whether the adaptive Kalman filter needs to update parameters or not; 3, calculating uncertain information of a plurality of fixed parameter Kalman filters; 4, convertingthe uncertain information of the plurality of fixed parameter Kalman filters into evidences; 5, converting the fused evidences into probabilities; and step 6, updating parameters of the adaptive Kalman filter. According to the invention, the Kalman filter with self-adaptive parameter adjustment is added on the basis of a plurality of Kalman filters, so that the method has better anti-interferenceperformance; uncertain information of the innovation information is fused by using an evidence theory to generate a probability value; the parameters of the plurality of Kalman filters are used as reference values, and the parameters of the adaptive Kalman filters are updated in combination with the probability values, so that the accuracy of target tracking in an interference environment is improved.

Description

technical field [0001] The invention belongs to the technical field of target tracking, and in particular relates to a fuzzy Kalman filter target tracking method improved by evidence theory. Background technique [0002] With the advent of the Internet of Everything era, all kinds of electronic devices and sensors have spread in every corner of life, work and work. Combining technologies such as communication and artificial intelligence, people's lives have been greatly improved. At the same time, the upgrading of manufacturing industry and intelligent manufacturing have brought about the update and iteration of industrial production equipment. Automatically produced equipment often needs to have the ability to identify and track items; Applications such as video surveillance and face recognition have become more intelligent, and these applications have also made target recognition and tracking more popular. Therefore, the development of technology has greatly enriched the ...

AI Technical Summary

Problems solved by technology

However, in the process of target tracking, the sensor is affected by a series of environmental uncertainties such as noise interference in a complex environment, and there may be inconsistencies and conflicts between multi-source data, which will affect the performance of the sensor and cause the observed data to have inconsistencies. However, it is difficult to directly integrate multi-source data. These uncertainties will bring troubles to target recognition and tracking under multi-source data. Therefore, when tracking targets, it is necessary to combine uncertainty theory to deal with uncertain information.

Images