Article改进粒子滤波的弱小目标跟踪Dimsmalltargettrackingbased.PDFVIP

Opto-Electronic Engineering Article 光 电 工 程 2018 年，第45 卷，第8 期 DOI: 10.12086/oee.2018.170569 改进粒子滤波的弱小目标跟踪 1,2,3 1,3 1,3* 樊香所 ，徐智勇 ，张建林 1 610209 2 610054 3 100049 摘要：针对低信噪比(SNR3 dB)场景下弱小目标跟踪问题，提出了改进的粒子滤波跟踪方法。本文首先通过空间位置 加权的方式来获取灰度特征，并将邻域运动模型和灰度概率图相结合来获取弱小目标运动特征，然后构建灰度与运动 特性的联合观测模型来计算粒子权值。同时在跟踪过程中考虑到目标的灰度分布特性并不稳定，加入了自适应更新参 考目标灰度模板的策略，最后采用几组真实场景来验证本文算法的跟踪效果。实验证明：和传统算法相比，本文算法 增强了低信噪比(SNR3 dB)场景下红外弱小目标跟踪能力。 关键词：弱小目标；跟踪；粒子滤波；特征融合 中图分类号：TP391 文献标志码：A 引用格式：樊香所，徐智勇，张建林. 改进粒子滤波的弱小目标跟踪[J]. 光电工程，2018 ，45(8): 170569 Dim small target tracking based on improved particle filter Fan Xiangsuo1,2,3, Xu Zhiyong1,3, Zhang Jianlin1,3* 1Institute of Optics and Electronics of Chinese Academy of Sciences, Chengdu, Sichuan 601209, China; 2School of Optoelectronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan 610054, China; 3University of Chinese Academy of Sciences, Beijing 100049, China Abstract: As to solve the problem of dim small target tracking in low signal-to-noise ratio (SNR3 dB) scenes, an improved particle filter tracking method is proposed. This paper firstly obtains the gray feature by spatial position weighting method, and combines the neighborhood motion model and the gray probability graph to get the motion features of dim small target. Then construct the joint observation model of gray and motion features to calculate the particle weights. At the same time, in the process of tracking, the gray distribution of the target is not stable, and the strategy of adaptively updating the gray template of reference target is added. Finally, the sequence image is used to prove the tracking effect of dim small target. Experiments sho