摘要
针对利用声图像实现水下多目标跟踪问题,提出一种改进的粒子滤波多目标跟踪算法.通过引入联合概率数据关联算法,建立了联合概率数据关联-粒子滤波算法模型,使粒子权值中得以反映量测与目标轨迹间的关联概率,有效保证了各目标跟踪轨迹的连续性.采用了包含距离及角度的双重跟踪门得到确定矩阵,使跟踪精度得以提高.补充了轨迹起始及轨迹终结方法,以对跟踪过程进行完善.最后,通过水下多目标跟踪试验,对比分析了不同数据关联算法的试验结果,验证了所提方法的有效性,为基于前视声纳的多目标跟踪提供了一种更为有效的方式.
Aimed at the problem of underwater multi-target tracking using forward looking sonar images, a modified particle filter （PF） multi-target tracking method was proposed. By introducing the joint probabi- listic data association （JPDA） method, a JPDA-PF algorithm was established. Thus particle weight could reflect the relationship between measurement and trajectory, which ensured the reliability and continuity of every trajectory. In order to increase the accuracy of tracking, the confirmation matrix was obtained by a double tracking threshold, including both relative distance and angle threshold. The methods of trajectory initialization and trajectory termination were complemented, which improved the whole tracking algo rithm. Contrast tests on multi-target tracking were conducted, and the better performance of JPDA-PF was verified. This paper provides a more effective method for multi-target tracking based on forward loo- king sonar.
出处
《上海交通大学学报》
EI
CAS
CSCD
北大核心
2013年第12期1848-1855,共8页
Journal of Shanghai Jiaotong University
基金
国家自然科学基金资助项目(51009040\E091002
51309066)
国家高技术研究发展计划(863)项目(2011AA09A106)
中国博士后基金(2012M510928)
黑龙江省博士后基金(LBH-Z11205)
关键词
联合概率数据关联
粒子滤波
目标跟踪
前视声纳
joint probabilistic data association
particle filter
target tracking
forward-looking sonar
