Willert, Volker ; Eggert, Julian ; Toussaint, Marc ; Körner, Edgar (2008)
Probabilistic Exploitation of the Lucas and Kanade Smoothness Constraint.
7th International Conference on Machine Learning and Applications. San Diego, USA (11.12.2008-13.12.2008)
doi: 10.1109/ICMLA.2008.54
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
The basic idea of Lucas and Kanade is to constrain the local motion measurement by assuming a constant velocity within a spatial neighborhood. We reformulate this spatial constraint in a probabilistic way assuming Gaussian distributed uncertainty in spatial identification of velocity measurements and extend this idea to scale and time dimensions. Thus, we are able to combine uncertain velocity measurements observed at different image scales and positions over time. We arrive at a new recurrent optical flow filter formulated in a Dynamic Bayesian Network applying suitable factorisation assumptions and approximate inference techniques. The introduction of spatial uncertainty allows for a dynamic and spatially adaptive tuning of the constraining neighborhood. Here, we realize this tuning dependenton the local Structure Tensor of the intensity patterns of the image sequence. We demonstrate that a probabilistic combination of spatiotemporal integration and modulation of a purely local integration area improves the Lucas and Kanade estimation.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2008 |
| Autor(en): | Willert, Volker ; Eggert, Julian ; Toussaint, Marc ; Körner, Edgar |
| Art des Eintrags: | Bibliographie |
| Titel: | Probabilistic Exploitation of the Lucas and Kanade Smoothness Constraint |
| Sprache: | Englisch |
| Publikationsjahr: | 22 Dezember 2008 |
| Verlag: | IEEE |
| Buchtitel: | IEEE Proceedings of the International Conference on Machine Learning and Applications |
| Veranstaltungstitel: | 7th International Conference on Machine Learning and Applications |
| Veranstaltungsort: | San Diego, USA |
| Veranstaltungsdatum: | 11.12.2008-13.12.2008 |
| DOI: | 10.1109/ICMLA.2008.54 |
| Kurzbeschreibung (Abstract): | The basic idea of Lucas and Kanade is to constrain the local motion measurement by assuming a constant velocity within a spatial neighborhood. We reformulate this spatial constraint in a probabilistic way assuming Gaussian distributed uncertainty in spatial identification of velocity measurements and extend this idea to scale and time dimensions. Thus, we are able to combine uncertain velocity measurements observed at different image scales and positions over time. We arrive at a new recurrent optical flow filter formulated in a Dynamic Bayesian Network applying suitable factorisation assumptions and approximate inference techniques. The introduction of spatial uncertainty allows for a dynamic and spatially adaptive tuning of the constraining neighborhood. Here, we realize this tuning dependenton the local Structure Tensor of the intensity patterns of the image sequence. We demonstrate that a probabilistic combination of spatiotemporal integration and modulation of a purely local integration area improves the Lucas and Kanade estimation. |
| Fachbereich(e)/-gebiet(e): | 18 Fachbereich Elektrotechnik und Informationstechnik 18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Automatisierungstechnik und Mechatronik 18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Automatisierungstechnik und Mechatronik > Regelungsmethoden und Robotik (ab 01.08.2022 umbenannt in Regelungsmethoden und Intelligente Systeme) |
| Hinterlegungsdatum: | 16 Aug 2010 14:33 |
| Letzte Änderung: | 18 Apr 2023 12:47 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum