基于多阶段轨迹融合的交叉多目标检测与跟踪算法

被引:3
作者
张海英
张田文
机构
[1] 哈尔滨工业大学计算机科学与技术学院
[2] 哈尔滨工业大学计算机科学与技术学院 黑龙江哈尔滨哈尔滨理工大学计算机科学与技术学院
[3] 黑龙江哈尔滨
关键词
与管道; 局部对比度; 双向相关滤波器; 点目标检测;
D O I
暂无
中图分类号
TP274.4 [];
学科分类号
0804 ; 080401 ; 080402 ; 081002 ; 0835 ;
摘要
构建了一种多阶段轨迹融合算法,预处理阶段利用局部对比度自适应门限抑制杂波,同时结合高阶相关滤波器剔除噪声和杂波边缘.在轨迹互联阶段,多阶段的双向搜索算法辅佐以目标航迹的能量累积,能够尽早锁定目标.实验分析表明,该方法能够准确的检测和跟踪作任意轨迹运动的多个点目标,在搜索空间和时间复杂度上明显优于传统的相关性算法.
引用
收藏
页码:1109 / 1112
页数:4
相关论文
共 7 条
[1]  
Multiple targets detection using modified high order correlations. Liou R J,Azimi-Sadjadi M R. IEEE Transactions on Aerospace and Electronic Systems . 1998
[2]  
Dim target detection using high order correlation method. Liou R J,Azimi-Sadjadi M R. IEEE Transactions on Aerospace and Electronic Systems . 1993
[3]  
Single-pixel target detection and tracking system. Wang G,Rafael M I. Pattern Recognition 10th International Conference . 1990
[4]  
Optimization of point target tracking filters. Caefer C E,Silverman J,Mooney J M. IEEE Transactions on Aerospace and Electronic Systems . 2000
[5]  
Optical moving target detection with 3d matched filtering. REED I S,Gagliardi R M,Stotts L. IEEE Transactions on Aerospace and Electronic Systems . 1988
[6]  
Detecting small moving objects in image sequences using sequential hypothesis testing. Steven D B,Thomas S H. IEEE Transactions on Signal Processing . 1991
[7]  
A frequency domain algorithm for multiframe detection and estimation of dim targets. Porat B,Friedlander B. IEEE Transactions on Pattern Analysis and Machine Intelligence . 1990