An acceleration method for correlation-based high-speed object tracking
An acceleration method for correlation-based high-speed object tracking
复制标题
DOI：
10.1016/j.measen.2021.100258
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
M. Hirano;Y. Yamakawa;T. Senoo;M. Ishikawa
中科院分区：
文献类型：
--
作者：
M. Hirano;Y. Yamakawa;T. Senoo;M. Ishikawa
提出了一种基于相关性的目标跟踪加速方法。基于相关性的跟踪方法涉及逆傅立叶变换，这是加速中的瓶颈。我们利用高速视觉的特点来加速这种计算：即，我们假设连续帧之间的位移在短帧采集间隔内不会发生显着变化。通过限制一个小的区域，位移被假定为，我们建议，以减少计算成本的逆傅立叶变换。我们实现了所提出的方法在相位相关，并进行了实验，使用模拟和真实的数据。我们在不牺牲精度的情况下，实现了比传统方法快5倍左右的计算速度。所提出的方法提供了一个有用的积木在加速相关的对象跟踪。
We propose an acceleration method for correlation-based object tracking. Correlation-based tracking methods involve an inverse Fourier transform, which is a bottleneck in acceleration. We exploit a trait of high-speed vision to accelerate this computation: namely, we assume that displacements between consecutive frames do not change dramatically within a short frame acquisition interval. By limiting a small region where the displacement is assumed to be, we propose to reduce computational cost in the inverse Fourier transform. We implemented the proposed method in phase-only correlation and conducted experiments using both simulated and real data. We achieved a computation speed around five-times faster than the conventional method without sacrificing accuracy. The proposed method provides as a useful building block in accelerating correlation-based object tracking.