System and method for identifying targets by airborne multiple sensors

Abstract

The invention discloses a system and a method for identifying targets by airborne multiple sensors. The system is characterized by comprising an evidence conflict judgment and conflict reduction module, an evidence correction module based on discount factors, and a fusion module of corrected evidence. The identifying method comprises the following steps of calculating the similarity coefficient of every two airborne evidences, judging the conflicts, constructing the reference evidences, obtaining the updated airborne evidence list, measuring the reliability coefficient of the airborne evidences, measuring the uncertainty coefficient of the airborne evidences, constructing the discount factors of the airborne evidences, calculating the discounts, and calculating the fusion of Dempster combining rules. The system and the method have the advantage that the effective information in the airborne multi-sensor data can be fully mined and remained, so the problem of target identification when the high-conflict information exists in the airborne multiple sensors is solved, and the target identification efficiency of the unmanned vehicle multiple sensors is improved.

Description

Technical field [0001] The invention belongs to the field of information processing technology, and relates to evidence theory and multi-sensor data processing technology, in particular to an airborne multi-sensor target recognition system and method. Background technique [0002] UAVs are playing an increasingly important role in the current war. The accurate judgment of the target based on the information obtained by the airborne sensor group is the prerequisite for the UAV to effectively perform reconnaissance / strike decision-making tasks. The use of multi-sensor fusion can improve the overall detection and credibility of the UAV formation, enhance the robustness of detection results, expand the space-time perception range of UAVs, reduce the degree of inference ambiguity, improve detection accuracy and other performance, and increase the detection target Feature dimension, improved spatial resolution and other advantages. Information fusion among multiple sensors of UAV is ...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the deficiencies of the prior art, the present invention proposes an airborne multi-sensor target recognition system and method, which can fully excavate and retain effective information in the airborne multi-sensor data, thereby solving the problem of high conflicts in the airborne multi-sensor The problem of target recognition based on information can improve the efficiency of UAV multi-sensor target recognition

Images