Robust Object Tracking Using Manifold Regularized Convolutional Neural Networks

doi:10.1109/TMM.2018.2859831

Robust Object Tracking Using Manifold Regularized Convolutional Neural Networks

2019-02-01

40

OA

AI

DOI：10.1109/TMM.2018.2859831

Original

Save

View PDF

Abstract

En 中文

In visual tracking, usually only a small number of samples are labeled, and most existing deep learning based trackers ignore abundant unlabeled samples that could provide additional information for deep trackers to boost their tracking performance. An intuitive way to explain unlabeled data is to incorporate manifold regularization into the common classification loss functions, but the high computational cost may prohibit those deep trackers from practical applications. To overcome this issue, we propose a two-stage approach to a deep tracker that takes into account both labeled and unlabeled samples. The annotation of unlabeled samples is propagated from its labeled neighbors first by exploring the manifold space that these samples are assumed to lie in. Then, we refine it by training a deep convolutional neural network using both labeled and unlabeled data in a supervised manner. Online visual tracking is further carried out under the framework of particle filters with the presented manifold regularized deep model being updated every few frames. Experimental results on different tracking datasets demonstrate that our tracker outperforms most existing tracking approaches. The source code and results are available at: https://github.com/shenjianbing/MRCNNTracking.

Keywords:

Convolutional neural networks

deep learning

deep tracker

manifold regularization

object tracking

online tracking

Robust Object Tracking Using Manifold Regularized Convolutional Neural Networks

Abstract

AI Summary

Journal

Organization