Feature-Based Multi-Object Tracking With Maximally One Object per Class
| dc.contributor.author | Krejčí, Jan | |
| dc.contributor.author | Straka, Ondřej | |
| dc.contributor.author | Vyskočil, Jiří | |
| dc.contributor.author | Jiřík, Miroslav | |
| dc.contributor.author | Dahmen, Uta | |
| dc.date.accessioned | 2023-01-02T11:00:10Z | |
| dc.date.available | 2023-01-02T11:00:10Z | |
| dc.date.issued | 2022 | |
| dc.description.abstract-translated | This paper deals with the problem of tracking multiple objects, in which each object is known to belong to a unique class. We follow the tracking by detection paradigm and assume that the object detector provides scores in addition to each detection. The problem is tackled as simultaneous classification and tracking using random finite sets. Inspired by the multi-Bernoulli mixture (MBM) filter, we propose a solution to the problem by modifying the target birth process. To simplify the implementation and to mitigate the computational costs, we develop tractable solutions with linear complexity. The algorithms are subsequently used for visual tracking of surgical instruments. As a by-product, we derive the prediction step of the Bernoulli filter using the probability generating functionals (PGFLs). | en |
| dc.format | 8 s. | cs |
| dc.format.mimetype | application/pdf | |
| dc.identifier.citation | KREJČÍ, J. STRAKA, O. VYSKOČIL, J. JIŘÍK, M. DAHMEN, U. Feature-Based Multi-Object Tracking With Maximally One Object per Class. In Proceedings of the 25th International Conference on Information Fusion, FUSION 2022. New York: IEEE, 2022. s. 1-8. ISBN: 978-1-73774-972-1 , ISSN: neuvedeno | cs |
| dc.identifier.document-number | 855689000104 | |
| dc.identifier.doi | 10.23919/FUSION49751.2022.9841332 | |
| dc.identifier.isbn | 978-1-73774-972-1 | |
| dc.identifier.issn | neuvedeno | |
| dc.identifier.obd | 43936987 | |
| dc.identifier.uri | 2-s2.0-85136562114 | |
| dc.identifier.uri | http://hdl.handle.net/11025/50805 | |
| dc.language.iso | en | en |
| dc.project.ID | SGS-2019-027/Inteligentní metody strojového vnímání a porozumění 4 | cs |
| dc.project.ID | EF19_073/0016931/Zvyšování kvality interních grantových schémat na ZČU | cs |
| dc.project.ID | SGS-2022-022/Rozvoj a využití kybernetických systémů identifikace, diagnostiky a řízení 5 | cs |
| dc.project.ID | LM2018140/E-infrastruktura CZ | cs |
| dc.project.ID | IDEG-2021-009/Multiple object visual tracking | cs |
| dc.publisher | IEEE | en |
| dc.relation.ispartofseries | Proceedings of the 25th International Conference on Information Fusion, FUSION 2022 | en |
| dc.rights | Plný text je přístupný v rámci univerzity přihlášeným uživatelům. | cs |
| dc.rights | © International Society of Information Fusion | en |
| dc.rights.access | restrictedAccess | en |
| dc.subject.translated | Visual tracking, random finite sets, multi-Bernoulli mixture, joint tracking and classification | en |
| dc.title | Feature-Based Multi-Object Tracking With Maximally One Object per Class | en |
| dc.type | konferenční příspěvek | cs |
| dc.type | ConferenceObject | en |
| dc.type.status | Peer-reviewed | en |
| dc.type.version | publishedVersion | en |