Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking

TL;DR

This paper introduces a robust object tracking method that combines multiple adaptive correlation filters with both long-term and short-term memory, improving accuracy and recovery from tracking failures.

Contribution

It proposes a novel multi-filter framework with long-term and short-term memory components, enhancing robustness and recovery in object tracking tasks.

Findings

Outperforms state-of-the-art methods in accuracy and robustness

Effectively recovers from tracking failures due to occlusion or disappearance

Demonstrates high efficiency on large-scale benchmark datasets

Abstract

Object tracking is challenging as target objects often undergo drastic appearance changes over time. Recently, adaptive correlation filters have been successfully applied to object tracking. However, tracking algorithms relying on highly adaptive correlation filters are prone to drift due to noisy updates. Moreover, as these algorithms do not maintain long-term memory of target appearance, they cannot recover from tracking failures caused by heavy occlusion or target disappearance in the camera view. In this paper, we propose to learn multiple adaptive correlation filters with both long-term and short-term memory of target appearance for robust object tracking. First, we learn a kernelized correlation filter with an aggressive learning rate for locating target objects precisely. We take into account the appropriate size of surrounding context and the feature representations. Second, we learn a correlation filter over a feature pyramid centered at the estimated target position for predicting scale changes. Third, we learn a complementary correlation filter with a conservative learning rate to maintain long-term memory of target appearance. We use the output responses of this long-term filter to determine if tracking failure occurs. In the case of tracking failures, we apply an incrementally learned detector to recover the target position in a sliding window fashion. Extensive experimental results on large-scale benchmark datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods in terms of efficiency, accuracy, and robustness.