Weight-modifying variable structure multi-model maneuvering object tracking method

Abstract

The invention belongs to the field of maneuvering object tracking, and discloses a weight-modifying variable structure multi-model maneuvering object tracking method. The method comprises the steps: initializing a radar observation value, and obtaining an initial state vector and an initial covariance matrix; selecting an initial angular velocity, and determining a state transition matrix of a motion model; carrying out multi-model filtering, obtaining a state estimation vector and an estimation covariance matrix, and obtaining multi-model weights; employing a variable structure and the idea of the graph theory, and carrying out the adjustment of the angular velocity (the multi-model structure) through the multi-model weights till the tracking is completed. The method is good in tracking performance, is small in calculation amount, and can be used for the tracking of a high-speed strong maneuvering target.

Description

technical field [0001] The invention relates to the field of maneuvering target tracking, in particular to a variable-structure multi-model maneuvering target tracking method with improved weight, which can be used for tracking high-speed maneuvering targets. Background technique [0002] Due to the important value of target tracking in various fields of national defense and civilian use, many scholars have been working on the research of target tracking algorithms. With the rapid development of modern aviation, the maneuverability and movement speed of various aircraft are getting higher and higher. It is difficult for the single-model algorithm to meet the requirements of tracking speed and accuracy. The inaccuracy of the model can improve the performance of maneuvering target tracking, so as to realize the precise tracking of strong maneuvering targets. [0003] However, the adaptive change of the weight of each model in the multi-model is a difficult point. At present, ...

AI Technical Summary

Problems solved by technology

However, the prior probability and transition matrix in the IMM algorithm are artificially set, which greatly affects the change of weights, and the interaction between multiple models requires a huge amount of calculation when there are many models.

[0004] In addition, because each model in the IMM algorithm is fixed, if the set models do not conform to the actual motion model, the tracking performance of the IMM algorithm will undoubtedly be poor.

Now there is an improved variable structure IMM algorithm for this purpose. Although it solves the problem of fixed models in the IMM algorithm, it needs to set as many model sets as possible in advance, and the rules for adding and deleting model sets are also very complicated and the amount of calculation is very large.

Images