基于多特征融合的机场场面运动目标实时并行跟踪

Real-Time Parallel Tracking of Moving Targets on Airport Surface Based on Multi-Feature Fusion

本文根据机场场面监视雷达(SurfaceMovementRadar,SMR)实时处理的要求,提出基于多特征融合的SMR目标实时并行跟踪算法。首先,给出SMR扇区实时并行处理的框图,在极坐标系下,雷达图像被划分成相同大小的扇区,采用多核多线程技术实现扇区之间的并行处理,使得数据和信息通信互相独立;其次,对波门内挑选最优量测的问题在传统跟踪算法中融入目标多特征信息;最后,利用实测数据对比分析了传统算法和所提算法的跟踪结果。实测数据处理结果表明所提算法提升了运动目标跟踪效果,减少了航迹断裂和虚假航迹的现象。

In this paper step according to the requirements of real-time processing of airport SMR(surface movement radar),a real-time parallel SMR target tracking algorithm based on multi feature fusion is proposed.Firstly,the block diagram of realtime parallel processing of SMR sector is given.In the polar coordinate system,the radar image is divided into sectors of the same size.The parallel processing between sectors is realized by multi-core and multi thread technology,so that the data and information communication are independent of each other;Secondly,for the problem of selecting the optimal measurement in the wave gate,the multi feature information of the target is integrated into the traditional tracking algorithm;Finally,the tracking results of the traditional algorithm and the proposed algorithm are compared and analyzed by using the measured data.The measured data processing results show that the proposed algorithm improves the moving target tracking effect and reduces the phenomenon of track fracture and false track.