基于自适应聚概率矩阵的JPDA算法研究

发布时间：2018-11-21 08:38

【摘要】：为了降低联合概率数据关联(joint probabilispic data association,JPDA)算法的计算复杂度,解决跟踪临近目标时出现的航迹合并问题,基于量测自适应消除方法,提出了一种改进JPDA算法.该算法首先通过Cheap JPDA算法计算互联概率,降低算法计算量;其次对聚概率矩阵加以阈值处理,通过重建确认矩阵,进一步优化算法复杂度;最后采用自适应消除方法,去掉聚概率矩阵中易引起错误关联的量测,减小JPDA算法在关联临近目标时的误差.仿真实验结果表明:相较于JPDA算法及Scaled JPDA(SJPDA)算法,本文算法在保证跟踪精度的前提下,降低了算法复杂度,提高了时效性;在跟踪临近目标及交叉目标时,改进算法能避免航迹合并现象及跟错目标情况的发生.
[Abstract]:In order to reduce the computational complexity of the joint probabilistic data association (joint probabilispic data association,JPDA) algorithm and solve the problem of track merging when tracking near the target, an improved JPDA algorithm is proposed based on the measurement adaptive cancellation method. The algorithm firstly calculates the interconnection probability by Cheap JPDA algorithm and reduces the computational complexity of the algorithm; secondly, the clustering probability matrix is treated by threshold, and the complexity of the algorithm is further optimized by reconstructing the confirmation matrix. Finally, the adaptive elimination method is adopted to eliminate the measurement in the aggregation probability matrix which is prone to error correlation, and to reduce the error of JPDA algorithm when the association is near the target. The simulation results show that compared with JPDA algorithm and Scaled JPDA (SJPDA) algorithm, this algorithm can reduce the complexity of the algorithm and improve the timeliness of the algorithm on the premise of ensuring the tracking accuracy. When tracking near and crossing targets, the improved algorithm can avoid the phenomenon of track merging and misalignment.
【作者单位】：中国民用航空飞行学院;空军工程大学航空航天工程学院;
【基金】：国家自然科学基金委员会-中国民用航空局联合研究基金资助项目(U1433126)
【分类号】：TP301.6

【相似文献】