基于改进型LTP的均值漂移目标跟踪算法

Mean Shift Tracking Algorithm Based on Improved LTP Feature Extraction

提出一种使用改进型LTP特征与颜色特征融合的均值漂移(Mean Shift)目标跟踪算法,该算法解决了均值漂移目标跟踪算法在变化的光强场景下跟踪难的问题。首先针对LTP模式过多的问题引入旋转不变的LTP模式,然后提出动态计算LTP算子阈值的方法,之后将改进的LTP特征与颜色特征通过自适应函数融合起来并嵌入均值漂移算法中。在变光强场景下与传统目标跟踪算法相比较,此算法跟踪结果明显优于其他算法,且鲁棒性较好。

A mean shift target tracking algorithm based on improved LTP feature and color feature fusion was proposed,which can solve the problem of tracking difficult of algorithm under varying light intensity scene.The rotation invariant is introduced aiming at the problem of LTP model,then the dynamic threshold method is put forward,and then the improved LIP feature and color feature are fused to embed into mean shift algorithm throught adaptive function.Compared with traditional target tracking algorithm in changing light intensity scenario,tracking result of this algorithm is superior to other algorithms,and has good robustness.