多特征融合的抗遮挡相关滤波目标跟踪算法

Anti-occlusion correlation filtering target tracking algorithm based on multi-feature fusion

针对传统相关滤波目标跟踪算法由于背景杂乱、目标尺度变化、目标遮挡等导致鲁棒性较差的问题,提出一种多特征融合抗遮挡的相关滤波目标跟踪算法。该算法对核相关滤波(kernel correlation filter,KCF)算法进行改进,通过将方向梯度直方图(histogram of oriented gradient,HOG)特征和多尺度块局部二值模式(multiscale block local binary pattern,MB-LBP)特征加权融合,并将所得特征再次与颜色(color name,CN)特征进行二次加权融合的方式来增强特征表达能力;增加尺度滤波器用于目标尺度估计;利用峰值旁瓣比(peak sidelobe ratio,PSR)和目标重定位算法对被遮挡目标进行判定和检测。选取OTB100数据集,将改进算法与几种主流算法进行了跟踪效果对比。实验结果表明,改进算法在背景杂乱、目标尺度变化、目标遮挡等情况下具有较好的鲁棒性。

To deal with the poor robustness of the traditional correlation filtering target tracking algorithm owing to background clutter,target scale change,target occlusion,a multi-feature fusion based anti-occlusion correlation filtering target tracking algorithm was proposed.The kernel correlation filter(KCF)algorithm was improved.By weighted fusing histogram of oriented gradient(HOG)features with multiscale block local binary pattern(MB-LBP)features,and secondary weighted fusing the obtained features with the features of the color name(CN),the feature expression ability was enhanced.A scaling filter was added for target scaling estimation.Peak sidelobe ratio(PSR)and target relocation algorithm were used to determine and detect the blocked target.OTB100 was selected as the data set,and the improved algorithm was compared with several mainstream algorithms in tracking effect.The experimental results show that the proposed algorithm has good robustness under the condition of background clutter,target scale change and target occlusion.