Quaternion-Based Robust PCA for Efficient Moving Target Detection and Background Recovery in Color Videos Article Swipe
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2507.19730
Moving target detection is a challenging computer vision task aimed at generating accurate segmentation maps in diverse in-the-wild color videos captured by static cameras. If backgrounds and targets can be simultaneously extracted and recombined, such synthetic data can significantly enrich annotated in-the-wild datasets and enhance the generalization ability of deep models. Quaternion-based RPCA (QRPCA) is a promising unsupervised paradigm for color image processing. However, in color video processing, Quaternion Singular Value Decomposition (QSVD) incurs high computational costs, and rank-1 quaternion matrix fails to yield rank-1 color channels. In this paper, we reduce the computational complexity of QSVD to o(1) by utilizing a quaternion Riemannian manifold. Furthermor, we propose the universal QRPCA (uQRPCA) framework, which achieves a balance in simultaneously segmenting targets and recovering backgrounds from color videos. Moreover, we expand to uQRPCA+ by introducing the Color Rank-1 Batch (CR1B) method to further process and obtain the ideal low-rank background across color channels. Experiments demonstrate our uQRPCA+ achieves State Of The Art (SOTA) performance on moving target detection and background recovery tasks compared to existing open-source methods. Our implementation is publicly available on GitHub at https://github.com/Ruchtech/uQRPCA
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2507.19730
- https://arxiv.org/pdf/2507.19730
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4417267272
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4417267272Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2507.19730Digital Object Identifier
- Title
-
Quaternion-Based Robust PCA for Efficient Moving Target Detection and Background Recovery in Color VideosWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-07-26Full publication date if available
- Authors
-
Liyang Wang, Shiqian Wu, Shun Fang, Qile Zhu, Jiaxin Wu, Sos AgainList of authors in order
- Landing page
-
https://arxiv.org/abs/2507.19730Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2507.19730Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2507.19730Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4417267272 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2507.19730 |
| ids.doi | https://doi.org/10.48550/arxiv.2507.19730 |
| ids.openalex | https://openalex.org/W4417267272 |
| fwci | |
| type | preprint |
| title | Quaternion-Based Robust PCA for Efficient Moving Target Detection and Background Recovery in Color Videos |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2507.19730 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2507.19730 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2507.19730 |
| locations[1].id | doi:10.48550/arxiv.2507.19730 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2507.19730 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100749347 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-4698-1900 |
| authorships[0].author.display_name | Liyang Wang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Wang, Liyang |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5068171246 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-6383-7663 |
| authorships[1].author.display_name | Shiqian Wu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wu, Shiqian |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5070380712 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-5074-1833 |
| authorships[2].author.display_name | Shun Fang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Fang, Shun |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5102592958 |
| authorships[3].author.orcid | https://orcid.org/0009-0009-1598-2223 |
| authorships[3].author.display_name | Qile Zhu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Zhu, Qile |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5101880563 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-2015-8206 |
| authorships[4].author.display_name | Jiaxin Wu |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Wu, Jiaxin |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5114755109 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Sos Again |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Again, Sos |
| authorships[5].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2507.19730 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Quaternion-Based Robust PCA for Efficient Moving Target Detection and Background Recovery in Color Videos |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-12-12T09:43:47.566033 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2507.19730 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2507.19730 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2507.19730 |
| primary_location.id | pmh:oai:arXiv.org:2507.19730 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2507.19730 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2507.19730 |
| publication_date | 2025-07-26 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 4, 55, 101, 115 |
| abstract_inverted_index.If | 24 |
| abstract_inverted_index.In | 87 |
| abstract_inverted_index.Of | 158 |
| abstract_inverted_index.at | 10, 183 |
| abstract_inverted_index.be | 29 |
| abstract_inverted_index.by | 21, 99, 132 |
| abstract_inverted_index.in | 15, 64, 117 |
| abstract_inverted_index.is | 3, 54, 178 |
| abstract_inverted_index.of | 48, 95 |
| abstract_inverted_index.on | 163, 181 |
| abstract_inverted_index.to | 82, 97, 130, 140, 172 |
| abstract_inverted_index.we | 90, 106, 128 |
| abstract_inverted_index.Art | 160 |
| abstract_inverted_index.Our | 176 |
| abstract_inverted_index.The | 159 |
| abstract_inverted_index.and | 26, 32, 43, 77, 121, 143, 167 |
| abstract_inverted_index.can | 28, 37 |
| abstract_inverted_index.for | 59 |
| abstract_inverted_index.our | 154 |
| abstract_inverted_index.the | 45, 92, 108, 134, 145 |
| abstract_inverted_index.QSVD | 96 |
| abstract_inverted_index.RPCA | 52 |
| abstract_inverted_index.data | 36 |
| abstract_inverted_index.deep | 49 |
| abstract_inverted_index.from | 124 |
| abstract_inverted_index.high | 74 |
| abstract_inverted_index.maps | 14 |
| abstract_inverted_index.o(1) | 98 |
| abstract_inverted_index.such | 34 |
| abstract_inverted_index.task | 8 |
| abstract_inverted_index.this | 88 |
| abstract_inverted_index.Batch | 137 |
| abstract_inverted_index.Color | 135 |
| abstract_inverted_index.QRPCA | 110 |
| abstract_inverted_index.State | 157 |
| abstract_inverted_index.Value | 70 |
| abstract_inverted_index.aimed | 9 |
| abstract_inverted_index.color | 18, 60, 65, 85, 125, 150 |
| abstract_inverted_index.fails | 81 |
| abstract_inverted_index.ideal | 146 |
| abstract_inverted_index.image | 61 |
| abstract_inverted_index.tasks | 170 |
| abstract_inverted_index.video | 66 |
| abstract_inverted_index.which | 113 |
| abstract_inverted_index.yield | 83 |
| abstract_inverted_index.(CR1B) | 138 |
| abstract_inverted_index.(QSVD) | 72 |
| abstract_inverted_index.(SOTA) | 161 |
| abstract_inverted_index.GitHub | 182 |
| abstract_inverted_index.Moving | 0 |
| abstract_inverted_index.Rank-1 | 136 |
| abstract_inverted_index.across | 149 |
| abstract_inverted_index.costs, | 76 |
| abstract_inverted_index.enrich | 39 |
| abstract_inverted_index.expand | 129 |
| abstract_inverted_index.incurs | 73 |
| abstract_inverted_index.matrix | 80 |
| abstract_inverted_index.method | 139 |
| abstract_inverted_index.moving | 164 |
| abstract_inverted_index.obtain | 144 |
| abstract_inverted_index.paper, | 89 |
| abstract_inverted_index.rank-1 | 78, 84 |
| abstract_inverted_index.reduce | 91 |
| abstract_inverted_index.static | 22 |
| abstract_inverted_index.target | 1, 165 |
| abstract_inverted_index.videos | 19 |
| abstract_inverted_index.vision | 7 |
| abstract_inverted_index.(QRPCA) | 53 |
| abstract_inverted_index.ability | 47 |
| abstract_inverted_index.balance | 116 |
| abstract_inverted_index.diverse | 16 |
| abstract_inverted_index.enhance | 44 |
| abstract_inverted_index.further | 141 |
| abstract_inverted_index.models. | 50 |
| abstract_inverted_index.process | 142 |
| abstract_inverted_index.propose | 107 |
| abstract_inverted_index.targets | 27, 120 |
| abstract_inverted_index.uQRPCA+ | 131, 155 |
| abstract_inverted_index.videos. | 126 |
| abstract_inverted_index.(uQRPCA) | 111 |
| abstract_inverted_index.However, | 63 |
| abstract_inverted_index.Singular | 69 |
| abstract_inverted_index.accurate | 12 |
| abstract_inverted_index.achieves | 114, 156 |
| abstract_inverted_index.cameras. | 23 |
| abstract_inverted_index.captured | 20 |
| abstract_inverted_index.compared | 171 |
| abstract_inverted_index.computer | 6 |
| abstract_inverted_index.datasets | 42 |
| abstract_inverted_index.existing | 173 |
| abstract_inverted_index.low-rank | 147 |
| abstract_inverted_index.methods. | 175 |
| abstract_inverted_index.paradigm | 58 |
| abstract_inverted_index.publicly | 179 |
| abstract_inverted_index.recovery | 169 |
| abstract_inverted_index.Moreover, | 127 |
| abstract_inverted_index.annotated | 40 |
| abstract_inverted_index.available | 180 |
| abstract_inverted_index.channels. | 86, 151 |
| abstract_inverted_index.detection | 2, 166 |
| abstract_inverted_index.extracted | 31 |
| abstract_inverted_index.manifold. | 104 |
| abstract_inverted_index.promising | 56 |
| abstract_inverted_index.synthetic | 35 |
| abstract_inverted_index.universal | 109 |
| abstract_inverted_index.utilizing | 100 |
| abstract_inverted_index.Quaternion | 68 |
| abstract_inverted_index.Riemannian | 103 |
| abstract_inverted_index.background | 148, 168 |
| abstract_inverted_index.complexity | 94 |
| abstract_inverted_index.framework, | 112 |
| abstract_inverted_index.generating | 11 |
| abstract_inverted_index.quaternion | 79, 102 |
| abstract_inverted_index.recovering | 122 |
| abstract_inverted_index.segmenting | 119 |
| abstract_inverted_index.Experiments | 152 |
| abstract_inverted_index.Furthermor, | 105 |
| abstract_inverted_index.backgrounds | 25, 123 |
| abstract_inverted_index.challenging | 5 |
| abstract_inverted_index.demonstrate | 153 |
| abstract_inverted_index.in-the-wild | 17, 41 |
| abstract_inverted_index.introducing | 133 |
| abstract_inverted_index.open-source | 174 |
| abstract_inverted_index.performance | 162 |
| abstract_inverted_index.processing, | 67 |
| abstract_inverted_index.processing. | 62 |
| abstract_inverted_index.recombined, | 33 |
| abstract_inverted_index.segmentation | 13 |
| abstract_inverted_index.unsupervised | 57 |
| abstract_inverted_index.Decomposition | 71 |
| abstract_inverted_index.computational | 75, 93 |
| abstract_inverted_index.significantly | 38 |
| abstract_inverted_index.generalization | 46 |
| abstract_inverted_index.implementation | 177 |
| abstract_inverted_index.simultaneously | 30, 118 |
| abstract_inverted_index.Quaternion-based | 51 |
| abstract_inverted_index.https://github.com/Ruchtech/uQRPCA | 184 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |