自适应HLBP纹理特征的Meanshift目标跟踪算法

Meanshift Target Tracking Algorithm of Adaptive HLBP Texture Feature

结合Haar型特性局部二元模式(HLBP)的图像纹理特征提取方法,提出一种新的目标跟踪算法,并将其运用到Meanshift框架中。将Visual Studio 2010和opencv2.4.9作为实验平台,将所提算法的实验结果与传统Meanshift跟踪算法、基于局部二元模式(LBP)纹理特征的Meanshift跟踪算法进行对比分析。实验结果表明,所提算法在背景复杂或背景简单的情况下都表现出了稳健而准确的跟踪特性,且在部分遮挡的情况下仍可以正确地跟踪目标。

In combination of the image texture feature extraction method,which is based on Haar local binary pattern (HLBP),a new target tracking algorithm was proposed,and applied to Meanshift tracking framework.Visual Studio 2010 and the opencv2.4.9 were the experimental platforms.We compared the results of the new algorithm with the results of other two kinds of algorithms,which are traditional Meanshift target tracking algorithm and the target tracking algorithm based on local binary pattern texture feature (LBP).Experimental results show that,in the case of simple or complicated background,the proposed tracking approach always shows steady and accurate tracking features,and in the event of partial occlusions,it can correctly track the target.