Multi-target tracking method based on multi-sensor data fusion

Abstract

The invention discloses a multi-target tracking method based on multi-sensor data fusion. The method comprises the following steps of: step 1, respectively collecting position information of each target by multiple sensors to obtain observation data of each sensor on each target; step 2, performing track association on the observation data of each target to obtain track association data of each sensor on each target; step 3, performing filtering processing on the track association data of the target to obtain a filtering track of each sensor on each target, and obtaining position estimation data of each target; step 4, calculating an instant deviation of the sensor on the target, and calculating an instant optimal dynamic weight of the sensor on the target; and step 5, fusing the positionestimation data of each sensor on the same target with the instant optimal dynamic weight to obtain fused position information of the same target. The method is higher in fusion precision and more accurate in target tracking, updates the dynamic weight of the sensor at each sampling moment, and is good in real-time performance.

Description

technical field [0001] The invention belongs to the technical field of target tracking, and in particular relates to a multi-target tracking method based on multi-sensor data fusion, which is suitable for real-time tracking of multiple targets by multiple sensors in complex environments. Background technique [0002] Multi-target tracking based on multi-sensor data fusion refers to the fusion of observation data of multiple sensors for multiple targets to track the trajectory of multiple targets, so as to achieve measurement accuracy that cannot be achieved by a single sensor and a single signal source. With the advancement of technology, the locking and tracking of target positions based on multi-sensor data fusion has important value in various applications, and it is also a hot spot of research by scholars. For example, in terms of military affairs, the enemy target will be located, tracked and attacked during the execution of the interception mission. If the movement tra...

AI Technical Summary

Problems solved by technology

At present, the multi-target tracking system based on the fusion of multi-sensor position data information is not perfect, and the weight of each sensor in the weighted fusion algorithm is mostly fixed, and the weight of the sensor is mostly determined by the parameters of the sensor itself or experience, without consideration Factors such as environmental interference cannot be adjusted in real time according to actual environmental factors, resulting in unsatisfactory target tracking results, poor accuracy and real-time performance

Images