SOTA: Sequential Optimal Transport Approximation for Visual Tracking in Wild Scenario

In this study, we introduce a probabilistic visual tracking method tailored for wild scenarios, where tracking environments experience abrupt changes over time. In probabilistic visual tracking, particularly when utilizing sequential Monte Carlo (MC) sampling, the careful choice of a proposal functi...

Full description

Saved in:
Bibliographic Details
Main Authors: Seonghak Lee, Jisoo Park, Radu Timofte, Junseok Kwon
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10766609/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849731069277896704
author Seonghak Lee
Jisoo Park
Radu Timofte
Junseok Kwon
author_facet Seonghak Lee
Jisoo Park
Radu Timofte
Junseok Kwon
author_sort Seonghak Lee
collection DOAJ
description In this study, we introduce a probabilistic visual tracking method tailored for wild scenarios, where tracking environments experience abrupt changes over time. In probabilistic visual tracking, particularly when utilizing sequential Monte Carlo (MC) sampling, the careful choice of a proposal function is critical for attaining precise tracking results, where optimal transport techniques can assist in reducing the variance from important sampling and inducing a suitable proposal function. However, if a tracked object undergoes significant changes in appearance over time, it creates a large discrepancy between the proposal function and its target distribution. This situation presents the topological and representational challenges for conventional optimal transport techniques. To address this problem, the proposed visual tracker leverages the benefits of both MC sampling and optimal transport and presents the Sequential Optimal Transport Approximation (SOTA) visual tracker. For this, our method involves transforming the proposal function into its target distribution across successive temperature steps through sequential MC sampling. These MC steps can reduce the topological and representational burden on the optimal transport. Within each successive temperature step, one distribution is projected onto another one via optimal transport. By using optimal transport, the method can mitigate the variance from importance sampling. The experimental results demonstrate that the proposed method considerably outperforms other state-of-the-art methods across several benchmark dataset, particularly in tracking environments where abrupt changes occur.
format Article
id doaj-art-e2e5ef5b67de4c5db79c2543723469ad
institution DOAJ
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-e2e5ef5b67de4c5db79c2543723469ad2025-08-20T03:08:40ZengIEEEIEEE Access2169-35362024-01-011217702817703710.1109/ACCESS.2024.350585610766609SOTA: Sequential Optimal Transport Approximation for Visual Tracking in Wild ScenarioSeonghak Lee0Jisoo Park1Radu Timofte2https://orcid.org/0000-0002-1478-0402Junseok Kwon3https://orcid.org/0000-0001-9526-7549School of Computer Science and Engineering, Chung-Ang University, Seoul, South KoreaGraduate School of Artificial Intelligence, Chung-Ang University, Seoul, South KoreaComputer Vision Laboratory, CAIDAS & IFI, University of Würzburg, Würzburg, GermanySchool of Computer Science and Engineering, Chung-Ang University, Seoul, South KoreaIn this study, we introduce a probabilistic visual tracking method tailored for wild scenarios, where tracking environments experience abrupt changes over time. In probabilistic visual tracking, particularly when utilizing sequential Monte Carlo (MC) sampling, the careful choice of a proposal function is critical for attaining precise tracking results, where optimal transport techniques can assist in reducing the variance from important sampling and inducing a suitable proposal function. However, if a tracked object undergoes significant changes in appearance over time, it creates a large discrepancy between the proposal function and its target distribution. This situation presents the topological and representational challenges for conventional optimal transport techniques. To address this problem, the proposed visual tracker leverages the benefits of both MC sampling and optimal transport and presents the Sequential Optimal Transport Approximation (SOTA) visual tracker. For this, our method involves transforming the proposal function into its target distribution across successive temperature steps through sequential MC sampling. These MC steps can reduce the topological and representational burden on the optimal transport. Within each successive temperature step, one distribution is projected onto another one via optimal transport. By using optimal transport, the method can mitigate the variance from importance sampling. The experimental results demonstrate that the proposed method considerably outperforms other state-of-the-art methods across several benchmark dataset, particularly in tracking environments where abrupt changes occur.https://ieeexplore.ieee.org/document/10766609/Visual trackingoptimal transportsequential Monte Carlo
spellingShingle Seonghak Lee
Jisoo Park
Radu Timofte
Junseok Kwon
SOTA: Sequential Optimal Transport Approximation for Visual Tracking in Wild Scenario
IEEE Access
Visual tracking
optimal transport
sequential Monte Carlo
title SOTA: Sequential Optimal Transport Approximation for Visual Tracking in Wild Scenario
title_full SOTA: Sequential Optimal Transport Approximation for Visual Tracking in Wild Scenario
title_fullStr SOTA: Sequential Optimal Transport Approximation for Visual Tracking in Wild Scenario
title_full_unstemmed SOTA: Sequential Optimal Transport Approximation for Visual Tracking in Wild Scenario
title_short SOTA: Sequential Optimal Transport Approximation for Visual Tracking in Wild Scenario
title_sort sota sequential optimal transport approximation for visual tracking in wild scenario
topic Visual tracking
optimal transport
sequential Monte Carlo
url https://ieeexplore.ieee.org/document/10766609/
work_keys_str_mv AT seonghaklee sotasequentialoptimaltransportapproximationforvisualtrackinginwildscenario
AT jisoopark sotasequentialoptimaltransportapproximationforvisualtrackinginwildscenario
AT radutimofte sotasequentialoptimaltransportapproximationforvisualtrackinginwildscenario
AT junseokkwon sotasequentialoptimaltransportapproximationforvisualtrackinginwildscenario