Channel-independent spatially regularized discriminative correlation filter for visual object tracking

The study proposes the improvements for visual object trackers based on discriminative correlation filters. These improvements consist in the development of the channel-independent spatially regularized method for filter calculation, which is based on the alternating direction method of multipliers as well as in the use of additional features that are the result of the backprojection of normalized weighted object histogram. The VOT Challenge 2018 benchmark has confirmed that the proposed approaches allow to increase the tracking robustness. Particularly, by the value of expected average overlap (EAO = 0.1828), the tracker that uses these approaches (CISRDCF) can reach the level of more computationally complex competitors that utilize convolutional neural features. At the same time, the software-optimized version of the CISRDCF tracker, which implements the suggested improvements has moderate computational complexity and can operate in the real-time both on the PC and on the mid-range ARM-based processors, making the CISRDCF tracker promising for embedded applications.