多通道核相关滤波的实时跟踪方法

Real-time object tracking method based on multi-channel kernel correlation filter

现有跟踪算法大都需要构建复杂的外观模型、抽取大量训练样本来实现精确的目标跟踪,会产生庞大的计算量,不利于实时跟踪。鉴于此,提出了一种多通道核相关滤波的实时跟踪方法。首先,利用核化岭回归方法对视频帧的目标信息进行训练,学习得到滤波模板;接着,用滤波模板对待检测帧的可能区域进行相关性度量;最后,将相关度最高的位置作为跟踪结果,并通过对多通道的独立输入进行加权求和,解决多通道输入问题。与现有跟踪方法的大量对比实验表明,在不同的挑战因素下,该方法在保证跟踪精度的同时,跟踪速度也存在明显优势。该方法通过相关滤波的方式可避免抽取大量样本,并利用频域的点乘代替时域的相关运算,大大降低了计算复杂度,使跟踪速度完全满足实时场景的跟踪需求。

The most existing algorithms have to build the complex model and draw a large number of training samples to achieve accurate object tracking,which will produce large amount of calculation. The proposed problem is not conducive to real-time tracking. In order to solve the problem, a real-time tracking method based on multi-channel kernel correlation filter was presented. Firstly, the target information of video frames were trained by using the nucleation ridge regression method to get the filter template. Secondly, the filter template was utilized to carry out the correlation measure for the possible area of the frame to be detected. Finally, the most relevant location was considered as the tracking result and the independent inputs of multiple channels were weighted and then added to solve the problem of multi-channel input. A large number of comparison experiments with the existing tracking methods show that, the proposed method guarantees the tracking accuracy and its tracking speed also has obvious advantages under different challenge factors. The proposed method avoids to extract a large number of samples by the correlation filter and use the dot product of frequency domain to replace the correlation operation of time-domain, which greatly reduces the computational complexity and makes the tracking speed completely meet the tracking demand of real-time scenario.