Real-Time Resource Allocation for Tracking Systems

Yash Satsangi, Shimon Whiteson, Frans A. Oliehoek, Henri Bouma
Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence, PMLR R15:641-650, 2017.

Abstract

Automated tracking is key to many computer vision applications. However, many tracking systems struggle to perform in real-time due to the high computational cost of detecting peo- ple, especially in ultra high resolution images. We propose a new algorithm called PartiMax that greatly reduces this cost by applying the person detector only to the relevant parts of the image. PartiMax exploits information in the particle filter to select k of the n candidate pixel boxes in the image. We prove that Parti- Max is guaranteed to make a near-optimal se- lection with error bounds that are independent of the problem size. Furthermore, empirical re- sults on a real-life dataset show that our system runs in real-time by processing only 10% of the pixel boxes in the image while still retain- ing 80% of the original tracking performance achieved when processing all pixel boxes.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR15-satsangi17a, title = {Real-Time Resource Allocation for Tracking Systems}, author = {Satsangi, Yash and Whiteson, Shimon and Oliehoek, Frans A. and Bouma, Henri}, booktitle = {Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence}, pages = {641--650}, year = {2017}, editor = {Elidan, Gal and Kersting, Kristian}, volume = {R15}, series = {Proceedings of Machine Learning Research}, month = {11--15 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r15/main/assets/satsangi17a/satsangi17a.pdf}, url = {https://proceedings.mlr.press/r15/satsangi17a.html}, abstract = {Automated tracking is key to many computer vision applications. However, many tracking systems struggle to perform in real-time due to the high computational cost of detecting peo- ple, especially in ultra high resolution images. We propose a new algorithm called PartiMax that greatly reduces this cost by applying the person detector only to the relevant parts of the image. PartiMax exploits information in the particle filter to select k of the n candidate pixel boxes in the image. We prove that Parti- Max is guaranteed to make a near-optimal se- lection with error bounds that are independent of the problem size. Furthermore, empirical re- sults on a real-life dataset show that our system runs in real-time by processing only 10% of the pixel boxes in the image while still retain- ing 80% of the original tracking performance achieved when processing all pixel boxes.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Real-Time Resource Allocation for Tracking Systems %A Yash Satsangi %A Shimon Whiteson %A Frans A. Oliehoek %A Henri Bouma %B Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2017 %E Gal Elidan %E Kristian Kersting %F pmlr-vR15-satsangi17a %I PMLR %P 641--650 %U https://proceedings.mlr.press/r15/satsangi17a.html %V R15 %X Automated tracking is key to many computer vision applications. However, many tracking systems struggle to perform in real-time due to the high computational cost of detecting peo- ple, especially in ultra high resolution images. We propose a new algorithm called PartiMax that greatly reduces this cost by applying the person detector only to the relevant parts of the image. PartiMax exploits information in the particle filter to select k of the n candidate pixel boxes in the image. We prove that Parti- Max is guaranteed to make a near-optimal se- lection with error bounds that are independent of the problem size. Furthermore, empirical re- sults on a real-life dataset show that our system runs in real-time by processing only 10% of the pixel boxes in the image while still retain- ing 80% of the original tracking performance achieved when processing all pixel boxes. %Z Reissued by PMLR on 04 October 2026.
APA
Satsangi, Y., Whiteson, S., Oliehoek, F.A. & Bouma, H.. (2017). Real-Time Resource Allocation for Tracking Systems. Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R15:641-650 Available from https://proceedings.mlr.press/r15/satsangi17a.html. Reissued by PMLR on 04 October 2026.

Related Material