Efficient Multi-level Correlating for Visual Tracking

TL;DR

This paper introduces MLCFT, a multi-level correlation filter tracking method that combines deep and shallow CNN features with a two-stage detection scheme, achieving high accuracy and real-time speed.

Contribution

The paper proposes a novel multi-level CF tracking approach with a cascaded detection scheme and entropy-based feature fusion, improving speed and accuracy over existing methods.

Findings

Outperforms state-of-the-art trackers on benchmarks.

Achieves tracking speed exceeding 16 fps.

Effectively prevents model drift with two-stage detection.

Abstract

Correlation filter (CF) based tracking algorithms have demonstrated favorable performance recently. Nevertheless, the top performance trackers always employ complicated optimization methods which constraint their real-time applications. How to accelerate the tracking speed while retaining the tracking accuracy is a significant issue. In this paper, we propose a multi-level CF-based tracking approach named MLCFT which further explores the potential capacity of CF with two-stage detection: primal detection and oriented re-detection. The cascaded detection scheme is simple but competent to prevent model drift and accelerate the speed. An effective fusion method based on relative entropy is introduced to combine the complementary features extracted from deep and shallow layers of convolutional neural networks (CNN). Moreover, a novel online model update strategy is utilized in our tracker, which enhances the tracking performance further. Experimental results demonstrate that our proposed approach outperforms the most state-of-the-art trackers while tracking at speed of exceeded 16 frames per second on challenging benchmarks.