Mean Shift和粒子滤波实现红外人体跟踪算法综述  

Review of Infrared Human Tracking Algorithm Using Mean Shift and Particle Filter

作　　者：耿建平[1] 雷梦英 GENG Jianping;LEI Mengying(School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin,Guangxi 541004,China)

机构地区：[1]桂林电子科技大学电子工程与自动化学院

出　　处：《计算机工程与应用》2019年第24期29-36,共8页Computer Engineering and Applications

摘　　要：红外摄像仪能够全天候工作且不会受限于像光线不足、漆黑夜晚等外界环境的干扰,但是红外图像成像质量差、分辨率低、信息单一等特点导致研究人体目标跟踪出现许多难点问题。主要贡献表现在以下三个方面:(1)对少有的公开的红外数据集进行详细归纳;(2)重点阐述了国内外在红外人体跟踪方面对Mean Shift算法和粒子滤波算法的改进方案;(3)重点介绍了融合红外成像与可见光成像实现红外人体跟踪的研究进展。The infrared camera works all day and is not limited by external environment such as insufficient light and dark night.However,the poor imaging quality,low resolution and single information of the infrared images lead to many difficult problems in researching human target tracking.The main contributions of this paper are shown in the following three aspects:(1)The rare public infrared datasets are summarized in detail.(2)The improvement schemes of Mean Shift algorithm and particle filter algorithm in infrared human tracking at home and abroad are elaborated emphatically.(3)The research progress of infrared human tracking by fusing infrared imaging and visible imaging is mainly introduced.

关 键 词：红外人体跟踪 红外数据集 Mean SHIFT算法 粒子滤波算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]