A Distributed Fusion Method of Labeled Random Set Filters

Abstract

The invention discloses a label random set filter distributed fusion method, which belongs to the field of multi-sensor fusion. Firstly, the labeled random set distribution is transformed into its unlabeled version; then, based on the matching characteristics of the first-order statistical properties, the unlabeled version of the multi-objective Bernoulli distribution is approximated as a multi-objective Bernoulli distribution; secondly, based on the assumption that the target states are non-adjacent , simplifies the fractional exponential power of the multi-objective Bernoulli distribution and brings it into the generalized covariance cross-information fusion expression. Finally, the set space of track-track mapping relationship between sensors is established. Based on this mapping space, the generalized covariance cross-information fusion expression of the above complex situation is simplified into a concise and easy-to-understand closed-form fusion expression. Therefore, it is robust to label space mismatch between distributions of different label random sets, the approximation cost is small, and the effect of realizing low complexity is achieved.

Description

technical field [0001] The invention belongs to the field of multi-sensor fusion, and in particular relates to the technical field of multi-target tracking and distributed multi-sensor fusion under random set theory. Background technique [0002] The rapid development of stealth technology makes radar detection technology face great challenges. The target stealth design is based on the backscattering detection mechanism of the single-station radar, which can significantly reduce the backscattered energy captured by the single-station radar, so that the power of a single radar drops sharply, "power clearing". The distributed multi-sensor network detection technology can make full use of the spatial multi-node layout form, effectively use the node multi-frequency, multi-polarization and multi-directional scattering energy of the target, and realize the detection of stealth targets in complex environments. Therefore, multi-sensor target fusion technology becomes an indispensab...

AI Technical Summary

Problems solved by technology

These algorithms are often based on the assumption that the sensors are independent of each other, but in most practical scenarios, this assumption is not valid

When different sensors observe the same target, there are common process noise and measurement noise between the sensors. These public information lead to unknown level correlations between the measurements from different sensors.

In the field of traditional multi-sensor tracking, although scholars have done relevant research based on the assumption of correlation between sensors, there are some problems in the traditional multi-sensor multi-target fusion algorithm: 1) There are a large number of data association algorithms: Data association and data association of targets between sensors; 2) Due to the correlation between sensors, a large number of calculations are required to calculate the correlation when performing target fusion

However, the label space of label random set distribution output by different sensors is inconsistent and there is no accurate closed expression for the posterior of label random set distributed fusion, which makes the realization of label random set distributed fusion face great challenges.

Images