Globally optimal solution to multi-object tracking with merged measurements

@article{Henriques2011GloballyOS,
  title={Globally optimal solution to multi-object tracking with merged measurements},
  author={Jo{\~a}o F. Henriques and Rui Caseiro and Jorge P. Batista},
  journal={2011 International Conference on Computer Vision},
  year={2011},
  pages={2470-2477}
}
Multiple object tracking has been formulated recently as a global optimization problem, and solved efficiently with optimal methods such as the Hungarian Algorithm. A severe limitation is the inability to model multiple objects that are merged into a single measurement, and track them as a group, while retaining optimality. This work presents a new graph structure that encodes these multiple-match events as standard one-to-one matches, allowing computation of the solution in polynomial time… CONTINUE READING
Highly Cited
This paper has 119 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 79 extracted citations

Minimum Cost Multi-Way Data Association for Optimizing Multitarget Tracking of Interacting Objects

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2015
View 14 Excerpts
Highly Influenced

A modified KLT multiple objects tracking framework based on global segmentation and adaptive template

Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012) • 2012
View 6 Excerpts
Highly Influenced

Data association for multi-object Tracking-by-Detection in multi-camera networks

2012 Sixth International Conference on Distributed Smart Cameras (ICDSC) • 2012
View 5 Excerpts
Highly Influenced

Raw Trajectory Rectification via Scene-Free Splitting and Stitching

Journal of Computer Science and Technology • 2015
View 5 Excerpts
Highly Influenced

Pattern Recognition

Lecture Notes in Computer Science • 2014
View 10 Excerpts
Highly Influenced

Tracking Indistinguishable Translucent Objects over Time Using Weakly Supervised Structured Learning

2014 IEEE Conference on Computer Vision and Pattern Recognition • 2014
View 9 Excerpts
Highly Influenced

A Stochastic Attribute Grammar for Robust Cross-View Human Tracking

IEEE Transactions on Circuits and Systems for Video Technology • 2018

119 Citations

02040'13'15'17'19
Citations per Year
Semantic Scholar estimates that this publication has 119 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 26 references

PETS2010 and PETS2009 Evaluation of Results Using Individual Ground Truthed Single Views

2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance • 2010
View 4 Excerpts
Highly Influenced

Multi-Object Tracking Through Simultaneous Long Occlusions and Split-Merge Conditions

2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06) • 2006
View 7 Excerpts
Highly Influenced

Multi-Target Tracking - Linking Identities using Bayesian Network Inference

2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06) • 2006
View 3 Excerpts
Highly Influenced

Beyond semi-supervised tracking: Tracking should be as simple as detection, but not simpler than recognition

2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops • 2009
View 1 Excerpt

Detection driven adaptive multi-cue integration for multiple human tracking

2009 IEEE 12th International Conference on Computer Vision • 2009
View 1 Excerpt

Similar Papers

Loading similar papers…