Deep Ensemble Tracking

Jie Guo, Tingfa Xu*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)

Abstract

In this letter, we cast visual tracking as a template matching problem in a Siamese deep convolutional neural network architecture. In contrast to traditional or other deep feature-based tracking methods, the proposed model exploits multilevel convolutional features from a partial view. The model matches candidate patch and template patch from the feature dimension of convolutional features, leading to hundreds of thousands of base matchers. The base matchers from low-level convolutional features have small receptive fields which contain partial details of targets while the base matchers from high-level convolutional features have big receptive fields which capture semantic information of targets. The model achieves the final strong matcher as a weighted ensemble of all the base matchers. We design an effective weights propagation strategy to update the weights of base matchers. Moreover, we propose to use Cosine as the distance metric and a customized squared-loss function as cost function for robust. Experiments show that our tracker outperforms the state-of-the-art trackers in a wide range of tracking scenarios.

Original languageEnglish
Article number8026140
Pages (from-to)1562-1566
Number of pages5
JournalIEEE Signal Processing Letters
Volume24
Issue number10
DOIs
Publication statusPublished - Oct 2017

Keywords

  • Convolutional neural network (CNN)
  • Siamese neural network
  • ensemble tracking
  • template matching

Fingerprint

Dive into the research topics of 'Deep Ensemble Tracking'. Together they form a unique fingerprint.

Cite this