Tracking of Deformable Objects Using Dynamically and Robustly Updating Pictorial Structures
The problem posed by complex, articulated or deformable objects has been at the focus of much tracking research for a considerable length of time. However, it remains a major challenge, fraught with numerous difficulties. The increased ubiquity of technology in all realms of our society has made the...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-07-01
|
Series: | Journal of Imaging |
Subjects: | |
Online Access: | https://www.mdpi.com/2313-433X/6/7/61 |
_version_ | 1797563486607245312 |
---|---|
author | Connor Charles Ratcliffe Ognjen Arandjelović |
author_facet | Connor Charles Ratcliffe Ognjen Arandjelović |
author_sort | Connor Charles Ratcliffe |
collection | DOAJ |
description | The problem posed by complex, articulated or deformable objects has been at the focus of much tracking research for a considerable length of time. However, it remains a major challenge, fraught with numerous difficulties. The increased ubiquity of technology in all realms of our society has made the need for effective solutions all the more urgent. In this article, we describe a novel method which systematically addresses the aforementioned difficulties and in practice outperforms the state of the art. Global spatial flexibility and robustness to deformations are achieved by adopting a pictorial structure based geometric model, and localized appearance changes by a subspace based model of part appearance underlain by a gradient based representation. In addition to one-off learning of both the geometric constraints and part appearances, we introduce a continuing learning framework which implements information discounting i.e., the discarding of historical appearances in favour of the more recent ones. Moreover, as a means of ensuring robustness to transient occlusions (including self-occlusions), we propose a solution for detecting unlikely appearance changes which allows for unreliable data to be rejected. A comprehensive evaluation of the proposed method, the analysis and discussing of findings, and a comparison with several state-of-the-art methods demonstrates the major superiority of our algorithm. |
first_indexed | 2024-03-10T18:44:19Z |
format | Article |
id | doaj.art-2ebd00d238344cb4a91296d8b5c29a66 |
institution | Directory Open Access Journal |
issn | 2313-433X |
language | English |
last_indexed | 2024-03-10T18:44:19Z |
publishDate | 2020-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Imaging |
spelling | doaj.art-2ebd00d238344cb4a91296d8b5c29a662023-11-20T05:37:29ZengMDPI AGJournal of Imaging2313-433X2020-07-01676110.3390/jimaging6070061Tracking of Deformable Objects Using Dynamically and Robustly Updating Pictorial StructuresConnor Charles Ratcliffe0Ognjen Arandjelović1School of Computer Science, University of St Andrews, North Haugh, St Andrews KY16 9SX, Fife, Scotland, UKSchool of Computer Science, University of St Andrews, North Haugh, St Andrews KY16 9SX, Fife, Scotland, UKThe problem posed by complex, articulated or deformable objects has been at the focus of much tracking research for a considerable length of time. However, it remains a major challenge, fraught with numerous difficulties. The increased ubiquity of technology in all realms of our society has made the need for effective solutions all the more urgent. In this article, we describe a novel method which systematically addresses the aforementioned difficulties and in practice outperforms the state of the art. Global spatial flexibility and robustness to deformations are achieved by adopting a pictorial structure based geometric model, and localized appearance changes by a subspace based model of part appearance underlain by a gradient based representation. In addition to one-off learning of both the geometric constraints and part appearances, we introduce a continuing learning framework which implements information discounting i.e., the discarding of historical appearances in favour of the more recent ones. Moreover, as a means of ensuring robustness to transient occlusions (including self-occlusions), we propose a solution for detecting unlikely appearance changes which allows for unreliable data to be rejected. A comprehensive evaluation of the proposed method, the analysis and discussing of findings, and a comparison with several state-of-the-art methods demonstrates the major superiority of our algorithm.https://www.mdpi.com/2313-433X/6/7/61computer visionposeBBCarticulatedmotionvideo |
spellingShingle | Connor Charles Ratcliffe Ognjen Arandjelović Tracking of Deformable Objects Using Dynamically and Robustly Updating Pictorial Structures Journal of Imaging computer vision pose BBC articulated motion video |
title | Tracking of Deformable Objects Using Dynamically and Robustly Updating Pictorial Structures |
title_full | Tracking of Deformable Objects Using Dynamically and Robustly Updating Pictorial Structures |
title_fullStr | Tracking of Deformable Objects Using Dynamically and Robustly Updating Pictorial Structures |
title_full_unstemmed | Tracking of Deformable Objects Using Dynamically and Robustly Updating Pictorial Structures |
title_short | Tracking of Deformable Objects Using Dynamically and Robustly Updating Pictorial Structures |
title_sort | tracking of deformable objects using dynamically and robustly updating pictorial structures |
topic | computer vision pose BBC articulated motion video |
url | https://www.mdpi.com/2313-433X/6/7/61 |
work_keys_str_mv | AT connorcharlesratcliffe trackingofdeformableobjectsusingdynamicallyandrobustlyupdatingpictorialstructures AT ognjenarandjelovic trackingofdeformableobjectsusingdynamicallyandrobustlyupdatingpictorialstructures |