首页 | 本学科首页   官方微博 | 高级检索  
     

自适应的免疫粒子滤波车辆跟踪算法
引用本文:李文辉,陈昱昊,王莹. 自适应的免疫粒子滤波车辆跟踪算法[J]. 吉林大学学报(理学版), 2016, 54(5): 1055-1063
作者姓名:李文辉  陈昱昊  王莹
作者单位:1. 吉林大学 计算机科学与技术学院, 长春 130012; 2. 吉林大学 软件学院, 长春 130012
摘    要:针对真实场景中的车辆跟踪问题, 提出一种改进的粒子滤波车辆跟踪算法. 通过免疫重采样框架减少粒子退化, 保证粒子滤波的有效性, 并参照人工免疫算法的思想建立记忆库, 使算法可较长时间地跟踪目标; 利用背景权重直方图和分块判别机制减少因遮挡导致的跟踪偏离, 同时在运动模型和抗体变异过程中加入自适应学习参数, 提高算法的鲁棒性. 实验结果表明, 在光照变化、 运动突变、 目标遮挡等不同条件下, 该算法具有稳定跟踪的能力, 验证了算法的有效性.

关 键 词:粒子滤波  人工免疫算法  自适应学习  车辆跟踪  
收稿时间:2016-06-16

Vehicle Tracking Algorithm Based on Adaptive Immune Particle Filter
LI Wenhui,CHEN Yuhao,WANG Ying. Vehicle Tracking Algorithm Based on Adaptive Immune Particle Filter[J]. Journal of Jilin University: Sci Ed, 2016, 54(5): 1055-1063
Authors:LI Wenhui  CHEN Yuhao  WANG Ying
Affiliation:1. College of Computer Science and Technology, Jilin University, Changchun 130012, China;2. College of Software, Jilin University, Changchun 130012, China
Abstract:Aiming at the problem of vehicle tracking in real scene, we proposed an improved particle filter for vehicle tracking algorithm. By using the framework of immune resampling, it reduced particle degeneracy and ensured the effectiveness of particle filter. Meanwhile, a memory base was establishedwhich refers to the idea of artificial immune algorithm, so that the algorithm could track targets for a long time. The background weights histogram and sub block identification mechanisms were used to reduce occlusions which caused by off tracking.Moreover, the adaptive learning parameters were added to the movement model andantibody mutation, which could improve the robustness of the algorithm. The experimental results show the algorithm has ability of stable tracking under the different conditions of illumination change, sudden movement or target occlusion, which verifies the validity of the proposed algorithm.
Keywords:particle filter  artificial immune algorithm  adaptive learning  vehicle tracking  
本文献已被 CNKI 等数据库收录!
点击此处可从《吉林大学学报(理学版)》浏览原始摘要信息
点击此处可从《吉林大学学报(理学版)》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号