Object tracking method based on trace point quality evaluation by entropy weight method

Abstract

The invention relates to a nearest neighbor object tracking method based on trace point quality evaluation, belongs to the technical field of radar target tracking, and particularly relates to an object tracking method based on multiple-evaluation-index information fusion of entropy weight. The invention puts forward a method for improving the degree of nearest neighbor correlation based on comprehensive evaluation of multiple features of the trace point. In data correlation, four measurement indexes of a trace point dropping into a wave gate, including position, amplitude, Doppler and work frequency, are taken into comprehensive consideration, evaluation values under the indexes are obtained by referring to predicted values or prior information, weight values are determined by an entropy weight method so as to obtain a comprehensive evaluation value, and the optimal measurement in quality evaluation instead of the measurement nearest to a predication point in a traditional method is used as track update. Therefore, the sensor information utilization rate is improved, and the performance of weak target tracking under complex environments is improved.

Description

technical field [0001] The invention belongs to the technical field of radar target tracking, in particular to a target tracking method based on information fusion of multiple evaluation indexes based on entropy weight. technical background [0002] At present, due to the interference of strong clutter and strong noise backgrounds formed by mountains, cities, oceans, etc. in radar surveillance scenarios, as well as the influence of maneuvering and stealth of the target itself, radar target tracking technology is facing great challenges. In a complex background, some clutter is similar to the target in both the time domain and the frequency domain. It is difficult for the constant false alarm detection technology to effectively distinguish the clutter from the target. challenge. [0003] A central part of the object tracking problem is data association. The common data association methods mainly include the nearest neighbor method (NN) and the probabilistic data association...

AI Technical Summary

Problems solved by technology

In the document "Wang Jiegui, Luo Jingqing. Passive tracking method based on multi-target multi-feature information fusion data association [J]. Frequency, pulse width, and pulse repetition period are three kinds of knowledge auxiliary features, and they are regarded as different evidence sources respectively. Using the Dempste-Shafer evidence theory to carry out multi-feature information fusion, the correlation degree between each effective observation and the real target is obtained, but this method does not The relationship between features is not fully considered, and the distribution of information synthesis weights is "depending on the specific situation", that is, empirical weights are used, which leads to a certain degree of subjectivity in practical applications. Even if the same operator, in the Different times and environments often lead to inconsistent subjective judgments on the same object

This will inevitably make the information synthesis process with a large degree of subjective judgment, thus reducing the credibility of the information synthesis results, making it difficult to guarantee tracking performance and lack of versatility

Images