Symbiotic trackers’ ensemble with trackers’ re-initialization for face tracking

Victor H. Ayma, Patrick N. Happ, Raul Q. Feitosa, Gilson A.O.P. Costa, Bruno Feijó

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Visual object tracking aims to deliver accurate estimates about the state of the target in a sequence of images or video frames. Nevertheless, tracking algorithms are sensitive to different kinds of image perturbations that frequently cause tracking failures. Indeed, tracking failures result from the insertion of imprecise target-related data into the trackers’ appearance models, which leads the trackers to lose the target or drift away from it. Here, we propose a tracking fusion approach, which incorporates feedback and re-initialization mechanisms to improve overall tracking performance. Our fusion technique, called SymTE-TR, enhances trackers’ overall performance by updating their appearances models with reliable information of the target’s states, while resets the imprecise trackers. We evaluated our approach on a facial video dataset, which characterizes a particular challenging tracking application under different imaging conditions. The experimental results indicate that our approach contributes to enhancing individual tracker performances by providing stable results across the video sequences and, consequently, contributes to stable overall tracking fusion performances.

Original languageEnglish
Title of host publicationInformation Management and Big Data - 7th Annual International Conference, SIMBig 2020, Proceedings
EditorsJuan Antonio Lossio-Ventura, Jorge Carlos Valverde-Rebaza, Eduardo Díaz, Hugo Alatrista-Salas
PublisherSpringer Science and Business Media Deutschland GmbH
Number of pages14
ISBN (Print)978-3-030-76227-8
StatePublished - 2021
Externally publishedYes
Event7th Annual International Conference on Information Management and Big Data, SIMBig 2020 - Virtual, Online
Duration: 1 Oct 20203 Oct 2020

Publication series

NameCommunications in Computer and Information Science
Volume1410 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937


Conference7th Annual International Conference on Information Management and Big Data, SIMBig 2020
CityVirtual, Online

Bibliographical note

Publisher Copyright:
© 2021, Springer Nature Switzerland AG.


  • Face tracking
  • Online object tracking
  • Tracking fusion
  • Tracking re-initialization


Dive into the research topics of 'Symbiotic trackers’ ensemble with trackers’ re-initialization for face tracking'. Together they form a unique fingerprint.

Cite this