Augmented Memory for Correlation Filters in Real-Time UAV Tracking
This work addresses robustness issues in real-time UAV tracking, but it is incremental as it builds on the DCF framework with memory enhancements.
The authors tackled the problem of discriminative correlation filters (DCF) losing robustness due to forgetting historical appearances in UAV tracking, and proposed a tracker that augments memory to memorize previous views while adapting to new ones, achieving competitive performance against 26 top trackers with over 40 FPS on CPU.
The outstanding computational efficiency of discriminative correlation filter (DCF) fades away with various complicated improvements. Previous appearances are also gradually forgotten due to the exponential decay of historical views in traditional appearance updating scheme of DCF framework, reducing the model's robustness. In this work, a novel tracker based on DCF framework is proposed to augment memory of previously appeared views while running at real-time speed. Several historical views and the current view are simultaneously introduced in training to allow the tracker to adapt to new appearances as well as memorize previous ones. A novel rapid compressed context learning is proposed to increase the discriminative ability of the filter efficiently. Substantial experiments on UAVDT and UAV123 datasets have validated that the proposed tracker performs competitively against other 26 top DCF and deep-based trackers with over 40 FPS on CPU.