A vehicle-road cooperative asynchronous fusion target tracking method and system
By using timestamp compensation and quality gating weighting, the problem of low target tracking accuracy in multi-source perception data fusion in vehicle-road cooperative systems was solved, achieving high-accuracy and stable target tracking under asynchronous and unstable communication conditions.
CN122365334APending Publication Date: 2026-07-10HEFEI QUANZHI AEROSPACE INFORMATION UHF SEMICONDUCTOR RESEARCH INSTITUTE CO LTD
View PDF 0 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HEFEI QUANZHI AEROSPACE INFORMATION UHF SEMICONDUCTOR RESEARCH INSTITUTE CO LTD
- Filing Date
- 2026-03-30
- Publication Date
- 2026-07-10
Smart Images

Figure CN122365334A_ABST
Abstract
The application provides a vehicle-road cooperation asynchronous fusion target tracking method and system, and relates to the field of data processing. The method comprises the following steps: acquiring vehicle-end perception data, roadside perception data and historical perception data within a processing period of a preset fusion time; based on timestamp information and the preset fusion time, calculating the time deviation of the vehicle-end perception data and the roadside perception data respectively, and acquiring corresponding communication link state information, wherein the communication link state information comprises a time delay, a jitter and a packet loss rate; based on the time deviation, selecting perception data matched with the preset fusion time from the historical perception data as to-be-aligned data; and performing continuous time compensation on the to-be-aligned data according to the time deviation to obtain space-time aligned data aligned to the fusion time, which is used for target tracking. The application is used in the target tracking process of vehicle-road cooperation asynchronous fusion, and solves the technical problem of low accuracy of the prior art in target tracking based on vehicle-road multi-source perception data.
Need to check novelty before this filing date? Find Prior Art