ROI Pooled Correlation Filters for Visual Tracking

TL;DR

This paper introduces a novel ROI pooled correlation filter (RPCF) for visual tracking, integrating ROI-based pooling into correlation filters to improve robustness and efficiency, and demonstrates superior performance on standard benchmarks.

Contribution

The paper proposes a new RPCF algorithm that incorporates ROI pooling into correlation filters through mathematical constraints, enabling more effective and efficient visual tracking.

Findings

RPCF outperforms state-of-the-art trackers on benchmarks

Efficient Fourier solvers enable fast training

ROI pooling enhances localization accuracy

Abstract

The ROI (region-of-interest) based pooling method performs pooling operations on the cropped ROI regions for various samples and has shown great success in the object detection methods. It compresses the model size while preserving the localization accuracy, thus it is useful in the visual tracking field. Though being effective, the ROI-based pooling operation is not yet considered in the correlation filter formula. In this paper, we propose a novel ROI pooled correlation filter (RPCF) algorithm for robust visual tracking. Through mathematical derivations, we show that the ROI-based pooling can be equivalently achieved by enforcing additional constraints on the learned filter weights, which makes the ROI-based pooling feasible on the virtual circular samples. Besides, we develop an efficient joint training formula for the proposed correlation filter algorithm, and derive the Fourier solvers for efficient model training. Finally, we evaluate our RPCF tracker on OTB-2013, OTB-2015 and VOT-2017 benchmark datasets. Experimental results show that our tracker performs favourably against other state-of-the-art trackers.