| 摘要 |
A parallel processing approach for use in multiple hypothesis tracking applications that provides partitioning and load balancing to achieve greater processing efficiency. The present invention comprises a plurality of processors that are each coupled to a shared memory, and which communicate to a central database stored in the shared memory. The central database is organized as a collection of radar tracks. Radar data is supplied to the processors as an input data stream organized in terms of radar tracks. The parallel processors are configured so that the next available processor retrieves the next successive measurement data point from the input data stream, updates tracks in the database using each retrieved measurement data point, wherein all processors operate independently without external synchronization, partitions the database into noninteracting clusters, wherein partitioning is executed in parallel by the plurality of processors which operate independently without external synchronization, retrieves the next successive cluster, forms and selects hypotheses based on the retrieved cluster, and updates the database based on the selected hypotheses. The present invention achieves an efficient implementation of multiple hypothesis tracking to provide for real-time multiprocessing. Parallelization of non-interactive and interactive multiple hypothesis tracking functions is readily achieved using the present invention. A parallel processing method for use in multiple hypothesis tracking applications is also disclosed.
|
