dc.identifier.uri | http://dx.doi.org/10.15488/5029 | |
dc.identifier.uri | https://www.repo.uni-hannover.de/handle/123456789/5073 | |
dc.contributor.author | Klinger, Tobias | |
dc.contributor.author | Rottensteiner, Franz | |
dc.contributor.author | Heipke, Christian | |
dc.contributor.editor | Christophe, S. | |
dc.contributor.editor | Raimond, A.-M. | |
dc.contributor.editor | Yang, M. | |
dc.contributor.editor | Çöltekin, A. | |
dc.contributor.editor | Mallet, C. | |
dc.contributor.editor | Rottensteiner, F. | |
dc.contributor.editor | Dowman, I. | |
dc.contributor.editor | Paparoditis, N. | |
dc.contributor.editor | Brédif, M. | |
dc.contributor.editor | Oude Elberink, S. | |
dc.date.accessioned | 2019-06-26T12:57:10Z | |
dc.date.available | 2019-06-26T12:57:10Z | |
dc.date.issued | 2015 | |
dc.identifier.citation | Klinger, Tobias; Rottensteiner, Franz; Heipke, Christian : Probabilistic multi-person tracking using dynamic bayes networks. In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences II-3/W5 (2015), S. 435-442. DOI: https://doi.org/10.5194/isprsannals-ii-3-w5-435-2015 | |
dc.description.abstract | Tracking-by-detection is a widely used practice in recent tracking systems. These usually rely on independent single frame detections that are handled as observations in a recursive estimation framework. If these observations are imprecise the generated trajectory is prone to be updated towards a wrong position. In contrary to existing methods our novel approach uses a Dynamic Bayes Network in which the state vector of a recursive Bayes filter, as well as the location of the tracked object in the image are modelled as unknowns. These unknowns are estimated in a probabilistic framework taking into account a dynamic model, and a state-of-the-art pedestrian detector and classifier. The classifier is based on the Random Forest-algorithm and is capable of being trained incrementally so that new training samples can be incorporated at runtime. This allows the classifier to adapt to the changing appearance of a target and to unlearn outdated features. The approach is evaluated on a publicly available benchmark. The results confirm that our approach is well suited for tracking pedestrians over long distances while at the same time achieving comparatively good geometric accuracy. | eng |
dc.language.iso | eng | |
dc.publisher | Göttingen : Copernicus GmbH | |
dc.relation.ispartof | ISPRS Geospatial Week 2015 | |
dc.relation.ispartofseries | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences ; II-3/W5 | |
dc.rights | CC BY 3.0 Unported | |
dc.rights.uri | https://creativecommons.org/licenses/by/3.0/ | |
dc.subject | Recursion | eng |
dc.subject | Machine learning | eng |
dc.subject | Trajectory | eng |
dc.subject | Tracking system | eng |
dc.subject | Artificial intelligence | eng |
dc.subject | Bayes' theorem | eng |
dc.subject | State vector | eng |
dc.subject | Computer vision | eng |
dc.subject | Bayesian network | eng |
dc.subject | Recursive Bayesian estimation | eng |
dc.subject | Computer science | eng |
dc.subject | Probabilistic logic | eng |
dc.subject.classification | Konferenzschrift | ger |
dc.subject.ddc | 550 | Geowissenschaften | ger |
dc.title | Probabilistic multi-person tracking using dynamic bayes networks | |
dc.type | Article | |
dc.type | Text | |
dc.relation.essn | 2194-9050 | |
dc.relation.issn | 2194-9050 | |
dc.relation.doi | https://doi.org/10.5194/isprsannals-ii-3-w5-435-2015 | |
dc.bibliographicCitation.volume | II-3/W5 | |
dc.bibliographicCitation.firstPage | 435 | |
dc.bibliographicCitation.lastPage | 442 | |
dc.description.version | publishedVersion | |
tib.accessRights | frei zug�nglich |
Die folgenden Lizenzbestimmungen sind mit dieser Ressource verbunden: