DCFNet: Discriminant Correlation Filters Network for Visual Tracking

TL;DR

This paper introduces DCFNet, an end-to-end lightweight neural network that integrates discriminant correlation filters for real-time visual tracking, improving accuracy and speed over traditional methods.

Contribution

The paper presents a novel end-to-end network architecture that learns features and performs correlation tracking simultaneously, maintaining efficiency in the Fourier domain.

Findings

Runs at over 60 FPS during testing

Achieves significant accuracy improvements over KCF with HoGs

Competitive performance on standard benchmarks

Abstract

Discriminant Correlation Filters (DCF) based methods now become a kind of dominant approach to online object tracking. The features used in these methods, however, are either based on hand-crafted features like HoGs, or convolutional features trained independently from other tasks like image classification. In this work, we present an end-to-end lightweight network architecture, namely DCFNet, to learn the convolutional features and perform the correlation tracking process simultaneously. Specifically, we treat DCF as a special correlation filter layer added in a Siamese network, and carefully derive the backpropagation through it by defining the network output as the probability heatmap of object location. Since the derivation is still carried out in Fourier frequency domain, the efficiency property of DCF is preserved. This enables our tracker to run at more than 60 FPS during test time, while achieving a significant accuracy gain compared with KCF using HoGs. Extensive evaluations on OTB-2013, OTB-2015, and VOT2015 benchmarks demonstrate that the proposed DCFNet tracker is competitive with several state-of-the-art trackers, while being more compact and much faster.