Multi target tracking from drones by learning from generalized graph differences
(2020) 17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 p.46-54- Abstract
Formulating the multi object tracking problem as a network flow optimization problem is a popular choice. The weights of such network flow problem can be learnt efficiently from training data using a recently introduced concept called Generalized Graph Differences (GGD). This allows a general tracker implementation to be specialized to drone videos by training it on the VisDrone dataset. Two modifications to the original GGD is introduced in this paper and a result with an average precision of 23.09 on the test set of VisDrone 2019 was achieved.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/255202ed-4669-40ff-9748-32ea5fdedd69
- author
- Ardo, Hakan LU and Nilsson, Mikael LU
- organization
- publishing date
- 2020-03-05
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Multi target tracking
- host publication
- Proceedings - 2019 International Conference on Computer Vision : Workshops, ICCVW 2019 - Workshops, ICCVW 2019
- pages
- 9 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
- conference location
- Seoul, Korea, Republic of
- conference dates
- 2019-10-27 - 2019-10-28
- external identifiers
-
- scopus:85082448559
- ISBN
- 9781728150239
- 978-1-7281-5024-6
- DOI
- 10.1109/ICCVW.2019.00012
- language
- English
- LU publication?
- yes
- id
- 255202ed-4669-40ff-9748-32ea5fdedd69
- date added to LUP
- 2020-05-27 13:40:05
- date last changed
- 2024-08-21 21:58:40
@inproceedings{255202ed-4669-40ff-9748-32ea5fdedd69, abstract = {{<p>Formulating the multi object tracking problem as a network flow optimization problem is a popular choice. The weights of such network flow problem can be learnt efficiently from training data using a recently introduced concept called Generalized Graph Differences (GGD). This allows a general tracker implementation to be specialized to drone videos by training it on the VisDrone dataset. Two modifications to the original GGD is introduced in this paper and a result with an average precision of 23.09 on the test set of VisDrone 2019 was achieved.</p>}}, author = {{Ardo, Hakan and Nilsson, Mikael}}, booktitle = {{Proceedings - 2019 International Conference on Computer Vision : Workshops, ICCVW 2019}}, isbn = {{9781728150239}}, keywords = {{Multi target tracking}}, language = {{eng}}, month = {{03}}, pages = {{46--54}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Multi target tracking from drones by learning from generalized graph differences}}, url = {{http://dx.doi.org/10.1109/ICCVW.2019.00012}}, doi = {{10.1109/ICCVW.2019.00012}}, year = {{2020}}, }