English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking

MPS-Authors
/persons/resource/persons263333

Nguyen,  Duy H. M.
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

/persons/resource/persons221924

Swoboda,  Paul
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)

arXiv:2111.11892.pdf
(Preprint), 21MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Nguyen, D. H. M., Henschel, R., Rosenhahn, B., Sonntag, D., & Swoboda, P. (2021). LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking. Retrieved from https://arxiv.org/abs/2111.11892.


Cite as: https://hdl.handle.net/21.11116/0000-0009-B3ED-2
Abstract
Multi-Camera Multi-Object Tracking is currently drawing attention in the
computer vision field due to its superior performance in real-world
applications such as video surveillance with crowded scenes or in vast space.
In this work, we propose a mathematically elegant multi-camera multiple object
tracking approach based on a spatial-temporal lifted multicut formulation. Our
model utilizes state-of-the-art tracklets produced by single-camera trackers as
proposals. As these tracklets may contain ID-Switch errors, we refine them
through a novel pre-clustering obtained from 3D geometry projections. As a
result, we derive a better tracking graph without ID switches and more precise
affinity costs for the data association phase. Tracklets are then matched to
multi-camera trajectories by solving a global lifted multicut formulation that
incorporates short and long-range temporal interactions on tracklets located in
the same camera as well as inter-camera ones. Experimental results on the
WildTrack dataset yield near-perfect result, outperforming state-of-the-art
trackers on Campus while being on par on the PETS-09 dataset. We will make our
implementations available upon acceptance of the paper.