基于模糊空时线索的多目标在线跟踪算法

发布时间：2018-03-09 21:40

本文选题：视频监控　切入点：在线跟踪　出处：《电子学报》2017年03期 　论文类型：期刊论文

【摘要】：多目标在线跟踪是视频监控中的关键问题之一.针对日益增长的智能化视频监控的需求,提出了一种基于模糊空时线索的多目标在线跟踪算法.在该算法中,引入模糊空时多属性特征定义距离函数,利用模糊C均值聚类优化得到交叉隶属度矩阵,实现目标与观测间的数据关联.为了减少错误的轨迹起始,利用空时线索定义了遮挡度函数,判别出新目标并起始相应的目标轨迹.实验结果表明,本文算法能够准确地估计出目标的运动轨迹.本文算法可应用于视频监控、安防以及自动驾驶等领域.
[Abstract]:Multi-target online tracking is one of the key problems in video surveillance. Aiming at the increasing demand of intelligent video surveillance, a multi-target online tracking algorithm based on fuzzy space-time clues is proposed. The distance function is defined by fuzzy space-time multi-attribute feature, and the cross-membership matrix is obtained by fuzzy C-means clustering optimization. The data correlation between target and observation is realized. The occlusion function is defined by space-time cues to distinguish new targets and start the corresponding target trajectories. The experimental results show that the proposed algorithm can accurately estimate the moving trajectories of the targets, and the proposed algorithm can be applied to video surveillance. Areas such as security and autopilot.
【作者单位】：深圳大学ATR国防科技重点实验室;
【基金】：国家自然科学基金(No.61301074,No.61271107) 广东省自然科学基金(No.S2012010009417) 广东省科技厅产学研协同创新成果转化项目(No.509111098127) 深圳市科技计划项目(No.JCYJ20140418095735618) 国防预研基金项目(No.91400C800501140C80340)
【分类号】：TP391.41;TN948.6

【相似文献】