A fast multi-object tracking system using an object detector ensemble
Richard Cobos, Jefferson Hernandez, Andres G. Abad
TL;DR
This paper introduces a multi-object tracking system that uses an ensemble of object detectors running periodically to improve real-time performance without significantly sacrificing accuracy.
Contribution
It proposes a novel ensemble-based detection approach that enhances speed in multi-object tracking systems for real-time applications.
Findings
Outperforms other online methods in speed on MOT16 benchmark.
Maintains acceptable accuracy despite increased speed.
Demonstrates effectiveness of detector ensembles in real-time MOT.
Abstract
Multiple-Object Tracking (MOT) is of crucial importance for applications such as retail video analytics and video surveillance. Object detectors are often the computational bottleneck of modern MOT systems, limiting their use for real-time applications. In this paper, we address this issue by leveraging on an ensemble of detectors, each running every f frames. We measured the performance of our system in the MOT16 benchmark. The proposed model surpassed other online entries of the MOT16 challenge in speed, while maintaining an acceptable accuracy.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
A fast multi-object tracking system using an object detector ensemble
Richard Cobos1, Jefferson Hernandez1, and Andres G. Abad
Industrial Artificial Intelligence (INARI) Research Lab
Escuela Superior Politecnica del Litoral
Guayaquil 09-01-5863, Ecuador
Email: {ricgecob, jefehern, agabad}@espol.edu.ec
Abstract
Multiple-Object Tracking (MOT) is of crucial importance for applications such as retail video analytics and video surveillance. Object detectors are often the computational bottleneck of modern MOT systems, limiting their use for real-time applications. In this paper, we address this issue by leveraging on an ensemble of detectors, each running every frames. We measured the performance of our system in the MOT16 benchmark. The proposed model surpassed other online entries of the MOT16 challenge in speed, while maintaining an acceptable accuracy.
Index Terms:
multi-object tracking, ensemble, object detection, Kalman filters
††publicationid: pubid:
1Note: Authors contributed equally
978-1-7281-1614-3/19/$31.00 ©2019 IEEE
I Introduction
\ExecuteMetaData
[sections/introduction.tex]tag
II Methodology
\ExecuteMetaData
[sections/methodology.tex]tag
III Numerical Results and Analysis
\ExecuteMetaData
[sections/results.tex]tag
IV Conclusion and Future Work
\ExecuteMetaData
[sections/conclusions.tex]tag
Acknowledgment
The authors would like to acknowledge the stimulating discussions and help from Victor Merchan, Jose Manuel Vera, and Joo Wang Kim, as well as Tiendas Industriales Asociadas Sociedad Anonima (TIA S.A.), a leading grocery retailer in Ecuador, for providing the necessary funding for this research effort.
The reference list from the paper itself. Each links out to its DOI / PubMed record.
- 1[1] A. Bewley, Z. Ge, L. Ott, F. Ramos, and B. Upcroft, “Simple online and realtime tracking,” in Image Processing (ICIP), 2016 IEEE International Conference on . IEEE, 2016, pp. 3464–3468.
- 2[2] J. Berclaz, F. Fleuret, E. Turetken, and P. Fua, “Multiple object tracking using k-shortest paths optimization,” IEEE transactions on pattern analysis and machine intelligence , vol. 33, no. 9, pp. 1806–1819, 2011.
- 3[3] N. L. Baisa and A. Wallace, “Development of a n-type gm-phd filter for multiple target, multiple type visual tracking,” Journal of Visual Communication and Image Representation , 2019.
- 4[4] F. Yu, W. Li, Q. Li, Y. Liu, X. Shi, and J. Yan, “Poi: Multiple object tracking with high performance detection and appearance feature,” in European Conference on Computer Vision . Springer, 2016, pp. 36–42.
- 5[5] P. Kilambi, E. Ribnick, A. J. Joshi, O. Masoud, and N. Papanikolopoulos, “Estimating pedestrian counts in groups,” Computer Vision and Image Understanding , vol. 110, no. 1, pp. 43–59, 2008.
- 6[6] M. Li, Z. Zhang, K. Huang, and T. Tan, “Estimating the number of people in crowded scenes by mid based foreground segmentation and head-shoulder detection,” in Pattern Recognition, 2008. ICPR 2008. 19th International Conference on . IEEE, 2008, pp. 1–4.
- 7[7] J. Segen, “A camera-based system for tracking people in real time,” in Proceedings of 13th International Conference on Pattern Recognition , vol. 3. IEEE, 1996, pp. 63–67.
- 8[8] C. Zeng and H. Ma, “Robust head-shoulder detection by pca-based multilevel hog-lbp detector for people counting,” in Pattern Recognition (ICPR), 2010 20th International Conference on . IEEE, 2010, pp. 2069–2072.