基于改进粒子滤波的声图像多目标跟踪方法

上海交通大学学报（自然版） ›› 2013, Vol. 47 ›› Issue (12): 1848-1855.

• 自动化技术、计算机技术 • 上一篇下一篇

基于改进粒子滤波的声图像多目标跟踪方法

马珊，张铁栋，庞永杰，万磊

（水下机器人技术重点实验室，哈尔滨 150001）

收稿日期:2013-01-21
基金资助:
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)

Acoustic Images Multi-Target Tracking Method Based on Modified Particle Filter

MA Shan,ZHANG Tiedong,PANG Yongjie,WAN Lei

(Science and Technology on Underwater Vehicle Laboratory, Harbin 150001, China)

Received:2013-01-21

摘要/Abstract

摘要：

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.

关键词：
联合概率数据关联；粒子滤波；目标跟踪；前视声纳

中图分类号： TP 39
文献标志码： A

Abstract:

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 probabilistic 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 algorithm. 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 looking sonar.

Key words: joint probabilistic data association, particle filter, target tracking, forward-looking sonar

马珊，张铁栋，庞永杰，万磊. 基于改进粒子滤波的声图像多目标跟踪方法[J]. 上海交通大学学报（自然版）, 2013, 47(12): 1848-1855.

MA Shan,ZHANG Tiedong,PANG Yongjie,WAN Lei. Acoustic Images Multi-Target Tracking Method Based on Modified Particle Filter[J]. Journal of Shanghai Jiaotong University, 2013, 47(12): 1848-1855.

参考文献

［1］Bruzzone G, Bruzzone G, Bibuli M, et al. Autonomous Mine Hunting Mission for the Charlie USV ［C］ //OCEANS. Santander, Spain: IEEE Press, 2011: 16.

［2］Williams D P. On optimal AUV trackspacing for underwater mine detection ［C］ //Robotics and Automation. Anchorage, A K: IEEE Press, 2010: 47554762.

［3］Kimball P, Rock S. Sonarbased icebergrelative AUV navigation ［C］ // Autonomous Underwater Vehicles. Woods Hole, M A: IEEE Press, 2008:16.

［4］Pebody M, Sutton R. Autonomous underwater vehicle collision avoidance for underice exploration ［J］. Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment, 2008, 222(2): 5366.

［5］ElHawary F. Adaptive underwater target tracking via a generalized kalman filter ［C］ //Autonomous Underwater Vehicle Technology. Halifax, N S: IEEE Press, 1990:275279.

［6］TenaRuiz I, Petillot Y, Lane D, et al. Tracking objects in underwater multibeam sonar images ［C］ //IEE Colloquium on Motion Analysis and Tracking. England: IEEE Press, 1999: 11/111/7.

［7］Sinha A, Ding Z, Kirubarajan T, et al. Track quality based multitarget tracking approach for global nearestneighbor association ［C］ //Aerospace and Electronic Systems, IEEE Transactions on. Adelphi, M D: IEEE Press, 2012: 11791191.

［8］Braca P, Grasso R, Vespe M, et al. Application of the JPDAUKF to HFSW radars for maritime situational awareness ［C］ //Information Fusion (FUSION). Singapore: IEEE Press, 2012：25852592.

［9］Clark D E, TenaRuiz I, Petillo Y. Multiple target tracking and data association in sonar images ［C］ //The 2006 IEEE Seminar on Target Tracking: Algorithms and Application. USA: IEEE Press, 2006: 147156.

［10］Lane D M, Chantler M J, Dai D. Robust tracking of multiple objects in sectorscan sonar image sequences using optical flow motion estimation ［J］. Oceanic Engineering， 1998, 23(1): 3146.

［11］高剑,严卫生,徐德民,等.基于采样卡尔曼滤波的水下被动目标跟踪［J］.火力与指挥控制， 2006, 31(12): 2529.

GAO Jian, YAN Weisheng, XU Demin, et al. Unscented Kalman filter for passive underwater target tracking ［J］. Fire Control and Command Control， 2006, 31(12): 2529.

［12］马悦.水下目标的声探测与跟踪技术研究［D］. 哈尔滨：哈尔滨工程大学, 2008.

［13］张铁栋,万磊,王博,等.基于改进粒子滤波算法的水下目标跟踪［J］.上海交通大学学报， 2012, 46(6): 3843.

ZHANG Tiedong, WAN Lei, WANG Bo, et al. Underwater object tracking based on improved particle filter ［J］. Journal of Shanghai Jiaotong University， 2012, 46(6): 3843.

［14］Fortmann T E, BarShalom Y, Scheffe M. Sonar tracking of multiple targets using joint probabilistic data association ［J］. IEEE Journal of Oceanic Engineering， 1983, 8(7): 173183.

［15］马珊,庞永杰,张铁栋.基于GRNN的声图像特征选择研究［C］ //第十五届中国海洋（岸）工程学术讨论会.太原:海洋出版社, 2011: 247252.