• Home
  • Search
  • Good Features to Correlate for Visual Tracking.
  • Open Access IconOpen Access
  • Cite Icon190
  • https://doi.org/10.1109/tip.2018.2806280Copy DOI Icon

Good Features to Correlate for Visual Tracking.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

During the recent years, correlation filters have shown dominant and spectacular results for visual object tracking. The types of the features that are employed in these family of trackers significantly affect the performance of visual tracking. The ultimate goal is to utilize robust features invariant to any kind of appearance change of the object, while predicting the object location as properly as in the case of no appearance change. As the deep learning based methods have emerged, the study of learning features for specific tasks has accelerated. For instance, discriminative visual tracking methods based on deep architectures have been studied with promising performance. Nevertheless, correlation filter based (CFB) trackers confine themselves to use the pre-trained networks which are trained for object classification problem. To this end, in this manuscript the problem of learning deep fully convolutional features for the CFB visual tracking is formulated. In order to learn the proposed model, a novel and efficient backpropagation algorithm is presented based on the loss function of the network. The proposed learning framework enables the network model to be flexible for a custom design. Moreover, it alleviates the dependency on the network trained for classification. Extensive performance analysis shows the efficacy of the proposed custom design in the CFB tracking framework. By fine-tuning the convolutional parts of a state-of-the-art network and integrating this model to a CFB tracker, which is the top performing one of VOT2016, 18% increase is achieved in terms of expected average overlap, and tracking failures are decreased by 25%, while maintaining the superiority over the state-of-the-art methods in OTB-2013 and OTB-2015 tracking datasets.

Similar Papers
  • Supplementary Content

Person Re-identification and Tracking in Video Surveillance

  • Jun 16, 2020
  • University of Liverpool
  • Yanchun Xie
  • PDF
  • Research Article
  • Citations2

MFCFSiam: A Correlation-Filter-Guided Siamese Network with Multifeature for Visual Tracking

  • Dec 23, 2020
  • Wireless Communications and Mobile Computing
  • Chenpu Li +3
  • Research Article
  • Citations40

Visual Object Tracking by Structure Complexity Coefficients

  • Aug 01, 2015
  • IEEE Transactions on Multimedia
  • Yuan Yuan +3
  • Conference Article
  • Citations3

Deep Features in Correlation Filters for Thermal Image Tracking

  • Nov 01, 2018
  • Milan Stojanovic +3
  • Research Article
  • Citations74

Dual Model Learning Combined With Multiple Feature Selection for Accurate Visual Tracking

  • Jan 01, 2019
  • IEEE Access
  • Jianming Zhang +4
  • Conference Article

Multiple model adaptive visual tracking with correlation filters

  • Sep 01, 2015
  • Gokhan Tanisik +1
  • Research Article
  • Citations56

When Correlation Filters Meet Convolutional Neural Networks for Visual Tracking

  • Oct 01, 2016
  • IEEE Signal Processing Letters
  • Chao Ma +3
  • Research Article
  • Citations17

Learning spatially correlation filters based on convolutional features via PSO algorithm and two combined color spaces for visual tracking

  • Dec 29, 2017
  • Applied Intelligence
  • Djamel Eddine Touil +2
  • Conference Article

Visual tracking with kernelized correlation filters based on multiple features

  • Sep 07, 2018
  • Zhi Cai +6
  • Research Article
  • Citations2

Visual tracking with multilayer filter fusion network

  • Oct 17, 2020
  • Multimedia Tools and Applications
  • Wei Quan +5
  • Conference Article
  • Citations5

Visual tracking with sparse correlation filters

  • Sep 01, 2016
  • Yanmei Dong +2
  • PDF
  • Research Article
  • Citations38

Association of Visual Tracking Metrics With Post-concussion Symptomatology

  • Jul 26, 2018
  • Frontiers in Neurology
  • Jun Maruta +3
  • Research Article

Real-time robust tracking with part-based and spatio-temporal context

  • Jan 01, 2021
  • International Journal of Computer Applications in Technology
  • Xinli Xu +3
  • Research Article
  • Citations220

Robust Visual Tracking via Hierarchical Convolutional Features.

  • Aug 13, 2018
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Chao Ma +3
  • Research Article
  • Citations20

Visual tracking via shallow and deep collaborative model

  • Aug 29, 2016
  • Neurocomputing
  • Bohan Zhuang +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.