Multi-period visual tracking via online DeepBoost learning

• We propose an adaptive visual tracking algorithm via online DeepBoost learning.
• We propose a combining-local–global visual representation.
• The capacity-conscious ability of online DeepBoost learning can avoid over-fitting.
• We propose a multi-period tracking framework to enhance the recovery ability.
• Our method can achieve higher level of accuracy and robustness.
• The proposed tracker outperforms the state-of-the-art trackers.

In this paper, we propose a novel accurate and robust boosting-style tracking-by-detection method. The proposed algorithm adopts a flexible and capacity-conscious object appearance model, which combines the strengths of both local and global visual representations. We firstly propose a joint local–global visual representation, in which main local and global spatial structure information of the target is flexibly embedded in the candidate classifier set with members from multiple complexity families. In addition, to avoid over-fitting our tracker adopts an effective online DeepBoost learning method (ODB). The key capacity-conscious ability of ODB helps to avoid over-fitting and generate a more adaptive and robust tracker. Furthermore, we propose a multi-period tracking framework (MPTF) to enhance the tracker׳s recovery ability for tracking failures. The proposed Multi-period DeepBoost-Tracker (MPDBT) can well encode the object spatial structures and excellently handle object appearance variations, and it can also recover from tracking failures with the help of the proposed MPTF. The experimental results demonstrate that our tracker outperforms the state-of-the-art trackers.