基于运动约束二步聚类Hough变换航迹起始算法  

Hough Transform Track Initiation Algorithm Based on Two-stage Clustering with Motion Constraints

作　　者：李静[1] 潘泉[2] 

机构地区：[1]中国空空导弹研究院,河南洛阳471009 [2]西北工业大学自动化学院,陕西西安710072

出　　处：《计算机测量与控制》2011年第11期2759-2762,共4页Computer Measurement &Control

基　　金：国家自然基金重点项目(60434030);航空基金(20090853013)

摘　　要：针对基于减法聚类的Hough变换航迹起始法存在的虚假航迹起始率高、目标航迹点缺失严重的问题,提出了一种基于运动二步约束聚类的Hough变换航迹起始法;该算法首先采用直观法滤除部分杂波点;随后利用Hough变换进行低阈值筛选;然后利用减法聚类得到多个聚类中心;最后由最近邻法判断出每个样本点所归属于聚类中心,得到目标航迹的数目以及参数;仿真表明,在密集杂波环境下,文章提出的算法的航迹起始概率近似是多级Hough变化航迹起始算法的1.2倍,同时虚假航迹起始概率是多级Hough变化航迹起始算法的三分之一,结果表明该算法改善了航迹起始的性能,特别适合于密集杂波下低信噪比目标的目标检测问题。Aiming to solve the problem of high false alarm and seriously missing target tracking from the Track Initiation Algorithm based on Hough Transform and Subtractive Clustering, a new Hough Transform track initiation method based on two--stage clustering with motion constraints is proposed. In this algorithm, first, the Object Method is used to filtrate parts of clutter, then the Hough Transform is adopted and filtrate the data by a low threshold values, following, the subtractive clustering is used to obtain the number and parameters of the target tracking, at last, the Nearest Neighbor method is used to decide which cluster center each sample point belong to. The simulation shows that under the density clutter environment, the initial probability of the proposed algorithm is 1.2 time than that of multi-- Hough track initiation and the false track initiation probability of the present method is one third of the multi-- Hough track initiation algorithm, which show that the present algorithm can improve the performance of track Initiation effectively, especially detect the targets in density clutter and low SNR environment.

关 键 词：HOUGH变换 减法聚类 航迹起始 最近邻法 直观法 运动约束 

分 类 号：TN953[电子电信—信号与信息处理]