English

应用科学学报 ›› 2013, Vol. 31 ›› Issue (6): 564-568.doi: 10.3969/j.issn.0255-8297.2013.06.003

• 信号与信息处理 • 上一篇    下一篇

用于水下目标跟踪的多特征融合PSOPF 算法

刘立昕， 卞红雨   

  1. 哈尔滨工程大学水声技术重点实验室，哈尔滨，150001
  • 收稿日期:2012-06-16 修回日期:2012-12-26 出版日期:2013-11-29 发布日期:2012-12-26
  • 作者简介:刘立昕，博士生，研究方向：水声图像处理与水下机器人视觉，E-mail: liulixin521@163.com；卞红雨，教授，博导，研究方向：水下目标探测与定位，E-mail: bianhongyu@hrbeu.edu.cn
  • 基金资助:

    国家自然科学基金(No. 51179038)；中央高校基本科研业务费专项资金(No. HEUCF120501)资助

Multi-feature Fused PSOPF for Underwater Target Tracking

LIU Li-xin, BIAN Hong-yu   

  1. Science and Technology on Underwater Acoustic Laboratory, Harbin Engineering University, Harbin 150001, China
  • Received:2012-06-16 Revised:2012-12-26 Online:2013-11-29 Published:2012-12-26

PDF

1091

被引次数

15

摘要： 针对前视声纳的成像特点，研究了目标多特征提取、多特征与粒子群优化粒子滤波(particle swarm optimized particle filter, PSOPF)的融合方法，设计了以自适应加权特征值为适应度值的优化跟踪算法. 该算法通过不断更新粒子群在搜索空间中的速度和位置，可实现粒子向高似然概率区域运动. 对声纳图像序列进行水下
目标跟踪实验，结果表明多特征融合PSOPF 算法可有效控制粒子贫乏和发散，提高系统鲁棒性，在降低粒子数目的同时提高了跟踪精度，满足水下目标跟踪的要求.

关键词: 目标跟踪, 粒子群优化, 粒子滤波, 多特征融合, 前视声纳

Abstract: Particle swarm optimized particle filter (PSOPF) can deal with leanness and divergence of the traditional particle filter to some extent. However, robustness and tracking precision need to be improved as the system observation model is limited to the use of observed data. Based on the imaging mechanism of the
forward-looking sonar, extraction of multiple features and fusion of the features with PSOPF are discussed.An optimized algorithm using adaptive weighted eigenvalues as fitness is proposed. It makes particles move to the high likelihood zone by updating their speed and position. Experiments are performed to track underwater targets from sonar image sequences. The results show that the multi-feature fused PSOPF can improve robustness and decrease risk of leanness and divergence. It can achieve high tracking precision with fewer particles. The advantages make it suitable for underwater target tracking.

Key words:  target tracking, particle swarm optimization, particle filter, multi-feature fusion, forward-looking sonar

中图分类号: