自动全局上下文感知相关滤波器跟踪算法

在相关滤波器跟踪算法中引入正则化后可以有效提高跟踪效率，但需要花费大量精力调整预定义参数，此外还有目标响应发生在非目标区域会导致跟踪漂移等问题，因此提出一种自动全局上下文感知相关滤波器(Automatic Global Context Awareness Correlation Filter, AGCACF)跟踪算法.首先，在跟踪过程中利用目标局部响应变化实现自动空间正则化，将自动空间正则化模块加入目标函数，使滤波器专注于目标对象的学习；其次，跟踪器利用目标全局上下文信息，结合自动空间正则化，使滤波器能及时学习到更多与目标有关的信息，减少背景对跟踪性能的影响；接着，在滤波器中加入时间正则化项，来充分学习目标在相邻帧之间的变化，从而获得更准确的模型样本.实验结果表明，与其他跟踪算法相比，AGCACF跟踪算法在距离精度和成功率方面具备更好的跟踪效果.

Correlation filter tracking algorithm based on automatic global context awareness

Introducing regularization into the correlation filter tracking algorithm can effectively improve the tracking efficiency,but it takes a lot of effort to adjust the predefined parameters.In addition,the target response occurring in non-target areas will lead to tracking drift.Therefore,an Automatic Global Context Awareness Correlation Filter (AGCACF) tracking algorithm is proposed.First,during the tracking process,the automatic spatial regularization is realized using the target local response change,then its module is added into the target function to enable the filter to focus on the learning of the target object.Second,the tracker utilizes the global context information of the target,which can avail the filter learn more information related to the target and reduce the impact of background on tracking performance. Then a temporal regularization term is added to the filter to fully learn the change of targets between adjacent frames to obtain more accurate model samples.Experimental results show that the proposed AGCACF tracking algorithm has better tracking effect in distance accuracy and success rate compared with other tracking algorithms.