摘要
针对UAV采集视频图像在与地面站进行数据通信过程中,由于传输转换延迟等因素造成的目标脱靶量问题,首先采用基于Meanshift采样的辅助粒子滤波跟踪算法进行跟踪实验。该算法采用辅助变量粒子滤波算法作为跟踪的主体框架,利用Meanshift算法将辅助采样粒子转移到最佳位置。基于跟踪结果,采用Kalman滤波预测目标轨迹,再用预测结果来修正跟踪结果并解决脱靶量问题。结果表明,加入预测算法后的跟踪结果更加接近目标的真实值,可以满足UAV在工程实际应用中的需求。
To solve the problems of target miss distance,which caused by the time delay during the communication in the UAV and the ground control station,firstly,an auxiliary variable particle filter tracking algorithm based on Meanshift sampling is used to track experiment. It adopts the AVPF as the main framework of the tracking algorithm,then the Meanshift is applied to cal-culate the offset of a few auxiliary particle and move them to the local optimum position of the observed values. Then based on the tracking result,Kalman filter is used to predict the target trajectory and the results in turn act on correcting the tracking results and solving the miss distance problem. The results show that having the prediction algorithm is closer to the true value and could satisfy the UAV target trajectory forecasting requirements.
出处
《计算机与数字工程》
2017年第8期1523-1527,共5页
Computer & Digital Engineering
基金
国家自然科学基金项目(编号:21273100)资助
