Deep bidirectional correlation filters for visual object tracking

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

4 Scopus citations


Visual Object Tracking (VOT) is an essential task for many computer vision applications. VOT becomes challenging when a target object faces severe occlusion, drastic illumination changes, and scale variation problems. In the literature, Discriminative Correlation Filters (DCFs)-based tracking methods have achieved promising results in terms of accuracy and efficiency in many complex VOT scenarios. A plethora of DCFs trackers have been proposed which exploit information observed in past frames to create and update DCFs for VOT. To adapt to target appearance variations, the DCFs are enhanced by incorporating spatial and temporal consistency constraints. Nevertheless, the performance degradation is observed for these methods because of the aforementioned limitations. To address these issues, we propose a novel algorithm based on bidirectional DCFs for VOT. In this algorithm, we propose the original idea of leveraging information from both past and future frames. The proposed algorithm first tracks the target object forward in the video sequence and then its uses the predicted location of the last window frame and track the target object backward towards the current frame. We design an appearance consistency loss function by taking the L2 norm between the regression target of the forward tracking and response map of the backward tracking to obtain the resulting response map. Our proposed algorithm realizes a highly accurate DCFs because forward and backward tracking information are fused together for consistent VOT. Although, a result will be output with some small delay because information is taken from a future to the present period, our proposed algorithm has the merit of addressing the drastic appearance variations VOT challenges. We evaluate our proposed tracker using deep features on three publicly available challenging datasets. Our results demonstrate the superior performance of the proposed tracker compared to the existing state-of-the-art trackers.

Original languageBritish English
Title of host publicationProceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9780578647098
StatePublished - Jul 2020
Event23rd International Conference on Information Fusion, FUSION 2020 - Virtual, Pretoria, South Africa
Duration: 6 Jul 20209 Jul 2020

Publication series

NameProceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020


Conference23rd International Conference on Information Fusion, FUSION 2020
Country/TerritorySouth Africa
CityVirtual, Pretoria


  • Correlation Filters
  • Deep Learning
  • Visual Object Tracking


Dive into the research topics of 'Deep bidirectional correlation filters for visual object tracking'. Together they form a unique fingerprint.

Cite this