Learning disruptor-suppressed response variation-aware multi-regularized correlation filter for visual tracking

Discriminative correlation filters (DCF) are widely used in object tracking for their high accuracy and computational efficiency. However, conventional DCF methods, which rely only on consecutive frames, often lack robustness due to limited temporal information and can suffer from noise introduced by historical frames. To address these limitations, we propose a novel disruptor-suppressed response variation-aware multi-regularized tracking (DSRVMRT) method. This approach improves tracking stability by incorporating historical interval information in filter training, thus leveraging a broader temporal context. Our method includes response deviation regularization to maintain consistent response quality and introduces a receptive channel weight distribution to enhance channel reliability. Additionally, we implement a disruptor-aware scheme using response bucketing, which detects and penalizes areas affected by similar objects or partial occlusions, reducing tracking disruptions. Extensive evaluations on public tracking benchmarks demonstrate that DSRVMRT achieves superior accuracy, robustness, and effectiveness compared to existing methods.