A target fusion method, apparatus, electronic device, and storage medium

By filtering and associating radar and video targets that meet the criteria, the problem of low accuracy in target recognition by radar and video equipment is solved, and efficient target fusion is achieved.

CN115393681BActive Publication Date: 2026-06-30ZHEJIANG DAHUA TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
ZHEJIANG DAHUA TECH CO LTD
Filing Date
2022-08-11
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

Existing radar and video acquisition equipment each have their own limitations in target identification and cannot be effectively integrated, resulting in low target identification accuracy, especially when video targets and radar targets are close to each other, which can easily lead to incorrect association.

Method used

By acquiring target data from radar and video acquisition equipment, video targets that meet the positional deviation conditions are screened out. Target association is performed based on attribute similarity and association credibility to screen out accurate target-associated video targets, and finally, the data is fused.

Benefits of technology

It improves the accuracy of radar and video target fusion, avoids erroneous associations, and ensures the accuracy of the fusion results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115393681B_ABST
    Figure CN115393681B_ABST
Patent Text Reader

Abstract

This application discloses a target fusion method, apparatus, electronic device, and storage medium, relating to the field of data fusion technology. In this application, a first attribute set associated with a radar target and a second attribute set associated with each of M video targets are used. Then, from the obtained M second attribute sets, N second attribute sets that satisfy a preset attribute similarity condition with the first attribute set are selected, thereby obtaining N video targets associated with the radar target. Further, based on the actual association credibility between each of the N associated video targets and the radar target, target-associated video targets that satisfy a preset association credibility condition are selected from the N associated video targets. Finally, the radar target and the target-associated video targets are fused to obtain the corresponding fused target. This method improves the accuracy of fusing radar targets and video targets.
Need to check novelty before this filing date? Find Prior Art