Dense Optical Flow Estimation Using Sparse Regularizers From Reduced Measurements

<p dir="ltr">Optical flow is the pattern of apparent motion of objects in a scene. The computation of optical flow is a critical component in numerous computer vision tasks such as object detection, visual object tracking, and activity recognition. Despite a lot of research, efficien...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Muhammad Wasim Nawaz (19325677) (author)
مؤلفون آخرون: Abdesselam Bouzerdoum (17900021) (author), Muhammad Mahboob Ur Rahman (19325680) (author), Ghulam Abbas (764241) (author), Faizan Rashid (17541690) (author)
منشور في: 2024
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513509721636864
author Muhammad Wasim Nawaz (19325677)
author2 Abdesselam Bouzerdoum (17900021)
Muhammad Mahboob Ur Rahman (19325680)
Ghulam Abbas (764241)
Faizan Rashid (17541690)
author2_role author
author
author
author
author_facet Muhammad Wasim Nawaz (19325677)
Abdesselam Bouzerdoum (17900021)
Muhammad Mahboob Ur Rahman (19325680)
Ghulam Abbas (764241)
Faizan Rashid (17541690)
author_role author
dc.creator.none.fl_str_mv Muhammad Wasim Nawaz (19325677)
Abdesselam Bouzerdoum (17900021)
Muhammad Mahboob Ur Rahman (19325680)
Ghulam Abbas (764241)
Faizan Rashid (17541690)
dc.date.none.fl_str_mv 2024-01-02T03:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2024.3382818
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Dense_Optical_Flow_Estimation_Using_Sparse_Regularizers_From_Reduced_Measurements/26490946
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Computer vision and multimedia computation
Energy minimization
motion discontinuities
optical flow
sparse regularizers
total variation
Optical flow
TV
Estimation
Anisotropic
Computer vision
Minimization
Image motion analysis
Energy management
Motion control
dc.title.none.fl_str_mv Dense Optical Flow Estimation Using Sparse Regularizers From Reduced Measurements
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Optical flow is the pattern of apparent motion of objects in a scene. The computation of optical flow is a critical component in numerous computer vision tasks such as object detection, visual object tracking, and activity recognition. Despite a lot of research, efficiently managing abrupt changes in motion remains a challenge in motion estimation. This paper proposes novel variational regularization methods to address this problem since they allow combining different mathematical concepts into a joint energy minimization framework. In this work, we incorporate concepts from signal sparsity into variational regularization for motion estimation. The proposed regularization uses robust ℓ1 norm, which promotes sparsity and handles motion discontinuities. By using this regularization, we promote the sparsity of the optical flow gradient. This sparsity helps recover a signal even with just a few measurements. We explore recovering optical flow from a limited set of linear measurements using this regularizer. Our findings show that leveraging the sparsity of the derivatives of optical flow reduces computational complexity and memory needs.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2024.3382818" target="_blank">https://dx.doi.org/10.1109/access.2024.3382818</a></p>
eu_rights_str_mv openAccess
id Manara2_1c855bd144df210fae5b96f6b19820cc
identifier_str_mv 10.1109/access.2024.3382818
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/26490946
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Dense Optical Flow Estimation Using Sparse Regularizers From Reduced MeasurementsMuhammad Wasim Nawaz (19325677)Abdesselam Bouzerdoum (17900021)Muhammad Mahboob Ur Rahman (19325680)Ghulam Abbas (764241)Faizan Rashid (17541690)Information and computing sciencesComputer vision and multimedia computationEnergy minimizationmotion discontinuitiesoptical flowsparse regularizerstotal variationOptical flowTVEstimationAnisotropicComputer visionMinimizationImage motion analysisEnergy managementMotion control<p dir="ltr">Optical flow is the pattern of apparent motion of objects in a scene. The computation of optical flow is a critical component in numerous computer vision tasks such as object detection, visual object tracking, and activity recognition. Despite a lot of research, efficiently managing abrupt changes in motion remains a challenge in motion estimation. This paper proposes novel variational regularization methods to address this problem since they allow combining different mathematical concepts into a joint energy minimization framework. In this work, we incorporate concepts from signal sparsity into variational regularization for motion estimation. The proposed regularization uses robust ℓ1 norm, which promotes sparsity and handles motion discontinuities. By using this regularization, we promote the sparsity of the optical flow gradient. This sparsity helps recover a signal even with just a few measurements. We explore recovering optical flow from a limited set of linear measurements using this regularizer. Our findings show that leveraging the sparsity of the derivatives of optical flow reduces computational complexity and memory needs.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2024.3382818" target="_blank">https://dx.doi.org/10.1109/access.2024.3382818</a></p>2024-01-02T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2024.3382818https://figshare.com/articles/journal_contribution/Dense_Optical_Flow_Estimation_Using_Sparse_Regularizers_From_Reduced_Measurements/26490946CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/264909462024-01-02T03:00:00Z
spellingShingle Dense Optical Flow Estimation Using Sparse Regularizers From Reduced Measurements
Muhammad Wasim Nawaz (19325677)
Information and computing sciences
Computer vision and multimedia computation
Energy minimization
motion discontinuities
optical flow
sparse regularizers
total variation
Optical flow
TV
Estimation
Anisotropic
Computer vision
Minimization
Image motion analysis
Energy management
Motion control
status_str publishedVersion
title Dense Optical Flow Estimation Using Sparse Regularizers From Reduced Measurements
title_full Dense Optical Flow Estimation Using Sparse Regularizers From Reduced Measurements
title_fullStr Dense Optical Flow Estimation Using Sparse Regularizers From Reduced Measurements
title_full_unstemmed Dense Optical Flow Estimation Using Sparse Regularizers From Reduced Measurements
title_short Dense Optical Flow Estimation Using Sparse Regularizers From Reduced Measurements
title_sort Dense Optical Flow Estimation Using Sparse Regularizers From Reduced Measurements
topic Information and computing sciences
Computer vision and multimedia computation
Energy minimization
motion discontinuities
optical flow
sparse regularizers
total variation
Optical flow
TV
Estimation
Anisotropic
Computer vision
Minimization
Image motion analysis
Energy management
Motion control