Multi-target tracking method in non-Gaussian noise environment

By employing a Dirichlet process-hidden Markov chain hybrid model within a generalized labeled multi-Bernoulli filter, the method effectively addresses non-Gaussian noise challenges in multi-target tracking, enhancing accuracy and robustness in environments with complex interference.

CN119716831AActive Publication Date: 2025-03-28NORTHWESTERN POLYTECHNICAL UNIV
2 Cites 0 Cited by

Patent Information

Application Number
CN202411318758.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-20
Publication Date
2025-03-28
Estimated Expiration
2044-09-20

AI Technical Summary

Technical Problem

In non-Gaussian noise environments, existing multi-target tracking methods face challenges due to signal interference and uncertainty, leading to inaccurate target state estimation and increased tracking errors, particularly in scenarios involving unmanned underwater vehicles where sensor noise does not follow a Gaussian distribution.

Method used

The method employs a spatial coordinate system to process sensor data using a generalized labeled multi-Bernoulli filter and a Dirichlet process-hidden Markov chain hybrid model for iterative updates of target state posterior probabilities, accounting for non-Gaussian noise and improving tracking accuracy and robustness.

Benefits of technology

This approach significantly reduces tracking errors and enhances the precision and completeness of trajectory estimation by adapting to non-Gaussian noise conditions, preventing model mismatch and providing accurate target state estimates.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a multi-target tracking method in a non-Gaussian noise environment, and the method comprises the steps: building a space coordinate system, and obtaining the position coordinates of a sensor and a monitoring region; periodically acquiring a measurement set by a sensor, and acquiring the number of targets and an associated measurement set of each target; based on the target state-measurement model, performing iterative updating of the target state posterior probability density on the associated measurement set through a Dirichlet process-hidden Markov chain hybrid model; and outputting each target track according to the iterative update of each frame. According to the method, the tracking error is remarkably reduced, and the track estimation precision and the track integrity are improved. The probability density distribution of the target state and the observation noise is adaptively and jointly estimated in real time through variational inference, the tracking error is remarkably reduced, and the track estimation precision and the track integrity are improved.
Need to check novelty before this filing date? Find Prior Art