Maneuvering target tracking algorithm based on road network

Abstract

The invention provides a maneuvering target tracking algorithm based on a road network. According to the algorithm, a tracking algorithm model adaptive strategy realized through road information is given by aid of a prior road information base, and a variable-structure multi-model method is adopted to realize ground multi-maneuvering-target tracking. In this way, state estimation precision of maneuvering target tracking can be improved, and the target missing rate is lowered; meanwhile, computing burden brought by multiple models adopted in a fixed multi-model algorithm is avoided, and operating time is greatly shortened; and the scheme has practical value in terms of ground target tracking.

Description

technical field [0001] The invention belongs to the field of target tracking, and relates to a road network-based maneuvering target tracking algorithm, in particular to a variable-structure multi-model probability hypothesis density algorithm using road information to assist ground target tracking. Background technique [0002] Ground target tracking has extremely broad application prospects in military and civilian fields. The ground target has the characteristics of strong motion ability and multiple motion states. The filter based on a single model cannot satisfy its maneuver tracking. The traditional method is to use multi-model filtering methods, such as interactive multi-model-multi-hypothesis tracking algorithm and interactive The multi-model-joint probabilistic data association algorithm is used to track the ground target. However, the performance of this fixed model set algorithm depends largely on the model set it uses. In order to cover the entire motion of the ...

AI Technical Summary

Problems solved by technology

However, like other filtering methods, the multi-target tracking algorithm based on random finite sets also needs to model the target motion pattern, and the Gaussian mixture probability hypothesis density filter based on a single model cannot effectively identify target maneuvers.

In this regard, some multi-model-based methods have been proposed, such as using multiple models for parallel filter estimation, using the best-fit Gaussian to match the target dynamic model, etc., but these methods are still fixed model set methods, and have the inherent characteristics of fixed model set methods. Disadvantages, at the same time, it is impossible to consider and utilize the external conditions of the target movement, such as the surrounding environment information of the target, etc.

Images