Learning Hierarchical Features for Visual Object Tracking with Recursive Neural Networks

TL;DR

This paper introduces a recursive neural network-based approach to learn hierarchical features for visual object tracking, reducing the number of parameters needed and improving tracking accuracy on benchmark datasets.

Contribution

The paper proposes a novel recursive neural network method for hierarchical feature learning in object tracking, with fewer parameters and an online dictionary update mechanism.

Findings

Significant improvement in tracking accuracy on benchmark datasets.

Effective handling of appearance changes through online dictionary updates.

Reduced model complexity compared to CNN-based methods.

Abstract

Recently, deep learning has achieved very promising results in visual object tracking. Deep neural networks in existing tracking methods require a lot of training data to learn a large number of parameters. However, training data is not sufficient for visual object tracking as annotations of a target object are only available in the first frame of a test sequence. In this paper, we propose to learn hierarchical features for visual object tracking by using tree structure based Recursive Neural Networks (RNN), which have fewer parameters than other deep neural networks, e.g. Convolutional Neural Networks (CNN). First, we learn RNN parameters to discriminate between the target object and background in the first frame of a test sequence. Tree structure over local patches of an exemplar region is randomly generated by using a bottom-up greedy search strategy. Given the learned RNN parameters, we create two dictionaries regarding target regions and corresponding local patches based on the learned hierarchical features from both top and leaf nodes of multiple random trees. In each of the subsequent frames, we conduct sparse dictionary coding on all candidates to select the best candidate as the new target location. In addition, we online update two dictionaries to handle appearance changes of target objects. Experimental results demonstrate that our feature learning algorithm can significantly improve tracking performance on benchmark datasets.