dc.identifier.uri |
http://dx.doi.org/10.15488/16867 |
|
dc.identifier.uri |
https://www.repo.uni-hannover.de/handle/123456789/16994 |
|
dc.contributor.author |
Ali, R.
|
|
dc.contributor.author |
Mehltretter, M.
|
|
dc.contributor.author |
Heipke, C.
|
|
dc.contributor.editor |
El-Sheimy, Naser
|
|
dc.contributor.editor |
Abdelbary, Alaa Abdelwahed
|
|
dc.contributor.editor |
El-Bendary, Nashwa
|
|
dc.contributor.editor |
Mohasseb, Yahya
|
|
dc.date.accessioned |
2024-04-03T08:42:09Z |
|
dc.date.available |
2024-04-03T08:42:09Z |
|
dc.date.issued |
2023 |
|
dc.identifier.citation |
Ali, R.; Mehltretter, M.; Heipke, C.: Integrating Motion Priors For End-To-End Attention-Based Multi-Object Tracking. In: El-Sheimy, Naser; Abdelbary, Alaa Abdelwahed; El-Bendary, Nashwa; Mohasseb, Yahya (Eds.): ISPRS Geospatial Week 2023. Katlenburg-Lindau : Copernicus Publications, 2023 (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (ISPRS Archives) ; XLVIII-1/W2-2023), S. 1619-1626. DOI: https://doi.org/10.5194/isprs-archives-xlviii-1-w2-2023-1619-2023 |
|
dc.description.abstract |
Recent advancements in multi-object tracking (MOT) have heavily relied on object detection models, with attention-based models like DEtection TRansformer (DETR) demonstrating state-of-the-art capabilities. However, the utilization of attention-based detection models in tracking poses a limitation due to their large parameter count, necessitating substantial training data and powerful hardware for parameter estimation. Ignoring this limitation can lead to a loss of valuable temporal information, resulting in decreased tracking performance and increased identity (ID) switches. To address this challenge, we propose a novel framework that directly incorporates motion priors into the tracking attention layer, enabling an end-to-end solution. Our contributions include: I) a novel approach for integrating motion priors into attention-based multi-object tracking models, and II) a specific realisation of this approach using a Kalman filter with a constant velocity assumption as motion prior. Our method was evaluated on the Multi-Object Tracking dataset MOT17, initial results are reported in the paper. Compared to a baseline model without motion prior, we achieve a reduction in the number of ID switches with the new method. |
eng |
dc.language.iso |
eng |
|
dc.publisher |
Katlenburg-Lindau : Copernicus Publications |
|
dc.relation.ispartof |
ISPRS Geospatial Week 2023 |
|
dc.relation.ispartofseries |
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (ISPRS Archives) ; XLVIII-1/W2-2023 |
|
dc.rights |
CC BY 4.0 Unported |
|
dc.rights.uri |
https://creativecommons.org/licenses/by/4.0 |
|
dc.subject |
Attention |
eng |
dc.subject |
Image Sequence Analysis |
eng |
dc.subject |
Motion Modelling |
eng |
dc.subject |
Pedestrian Tracking |
eng |
dc.subject |
Transformer |
eng |
dc.subject.classification |
Konferenzschrift |
ger |
dc.subject.ddc |
550 | Geowissenschaften
|
|
dc.title |
Integrating Motion Priors For End-To-End Attention-Based Multi-Object Tracking |
eng |
dc.type |
BookPart |
|
dc.type |
Text |
|
dc.relation.essn |
2194-9034 |
|
dc.relation.doi |
https://doi.org/10.5194/isprs-archives-xlviii-1-w2-2023-1619-2023 |
|
dc.bibliographicCitation.volume |
XLVIII-1/W2-2023 |
|
dc.bibliographicCitation.firstPage |
1619 |
|
dc.bibliographicCitation.lastPage |
1626 |
|
dc.description.version |
publishedVersion |
|
tib.accessRights |
frei zug�nglich |
|