Abstract
In this paper, we view multiple object tracking as a graph partitioning problem. Given any object detector, we build the graph of all detections and aim to partition it into trajectories. To quantify the similarity of any two detections, we consider local cues such as point tracks and speed, global cues such as appearance, as well as intermediate ones such as trajectory straightness. These different clues are dealt jointly to make the approach robust to detection mistakes (missing or extra detections). We thus define a Conditional Random Field and optimize it using an efficient combination of message passing and move-making algorithms. Our approach is fast on video batch sizes of hundreds of frames. Competitive and stable results on varied videos demonstrate the robustness and efficiency of our approach.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
We use the code provided by [2] to compute these metrics.
- 2.
Detections from http://iris.usc.edu/people/yangbo/downloads.html.
- 3.
MOTA code from https://github.com/glisanti/CLEAR-MOT.
- 4.
References
Breitenstein, M., Reichlin, F.: Robust tracking-by-detection using a detector confidence particle filter. In: ICCV (2009)
Andriyenko, A., Schindler, K., Roth, S.: Discrete-continuous optimization for multi-target tracking. In: CVPR (2012)
Milan, A., Schindler, K., Roth, S.: Detection-and trajectory-level exclusion in multiple object tracking. In: CVPR, June 2013
Roshan Zamir, A., Dehghan, A., Shah, M.: GMCP-tracker: global multi-object tracking using generalized minimum clique graphs. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 343–356. Springer, Heidelberg (2012)
Brendel, W., Amer, M., Todorovic, S.: Multiobject tracking as maximum weight independent set. In: CVPR (2011)
Zhang, L., Li, Y., Nevatia, R.: Global data association for multi-object tracking using network flows. In: CVPR (2008)
Shitrit, H.B., Berclaz, J., et al.: Tracking multiple people under global appearance constraints. In: ICCV (2011)
Berclaz, J., Fleuret, F., Turetken, E., Fua, P.: Multiple object tracking using K-shortest paths optimization. TPAMI 33, 1806–1819 (2011)
Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: Globally-optimal greedy algorithms for tracking a variable number of objects. In: CVPR (2011)
Russell, C., Agapito, L., Setti, F.: Efficient second order multi-target tracking with exclusion constraints. In: BMVC (2011)
Benfold, B., Reid, I.: Stable multi-target tracking in real-time surveillance video. In: CVPR (2011)
Collins, R.T.: Multitarget data association with higher-order motion models. In: CVPR (2012)
Butt, A., Collins, R.: Multi-target tracking by Lagrangian relaxation to min-cost network flow. In: CVPR (2013)
Ellis, A., Shahrokni, A., Ferryman, J.: PETS2009 and Winter-PETS 2009 results: A combined evaluation. In: PETS Workshop. IEEE (2009)
Kappes, J.H., Speth, M., Reinelt, G., Schnorr, C.: Towards efficient and exact MAP-inference for large scale discrete computer vision problems via combinatorial optimization. In: CVPR (2013)
Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. TPAMI 28(10), 1568–1583 (2006)
Besag, J.: On the statistical analysis of dirty pictures. Stat. Mehodological Soc. 48(3), 259–302 (1986)
Andres, B., Kappes, J.H., Beier, T., Köthe, U., Hamprecht, F.A.: The lazy flipper: efficient depth-limited exhaustive search in discrete graphical models. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VII. LNCS, vol. 7578, pp. 154–166. Springer, Heidelberg (2012)
Martins, A.F.T., Figueiredo, M.A.T., Aguiar, P.M.Q., Smith, N.A., Xing, E.P.: An augmented Lagrangian approach to constrained MAP inference. In: ICML (2011)
Sontag, D., Choe, D., Li, Y.: Efficiently searching for frustrated cycles in MAP inference. In: Uncertainty in Artificial Intelligence (2012)
Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VI. LNCS, vol. 7577, pp. 611–625. Springer, Heidelberg (2012)
Milan, A., Schindler, K., Roth, S.: Challenges of Ground Truth Evaluation of Multi-Target Tracking. In: CVPR Workshops (2013)
Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the CLEAR MOT metrics. EURASIP JIVP 2008, 1:1–1:10 (2008). doi:10.1155/2008/246309
Zhang, J., Presti, L., Sclaroff, S.: Online multi-person tracking by tracker hierarchy. In: AVSS (2012)
Senst, T., Eiselein, V., Sikora, T.: Robust local optical flow for feature tracking. IEEE Trans. Circuits Syst. Video Technol. 22(9), 1377–1387 (2012)
Zach, C., Gallup, D., Frahm, J.: Fast gain-adaptive KLT tracking on the GPU. In: CVPR Workshops (2008)
Acknowledgements
This work has received funding from the European Community’s FP7/2007-2013 - under grant agreement no 248907-VANAHEIM.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Kumar, R., Charpiat, G., Thonnat, M. (2015). Multiple Object Tracking by Efficient Graph Partitioning. In: Cremers, D., Reid, I., Saito, H., Yang, MH. (eds) Computer Vision -- ACCV 2014. ACCV 2014. Lecture Notes in Computer Science(), vol 9006. Springer, Cham. https://doi.org/10.1007/978-3-319-16817-3_29
Download citation
DOI: https://doi.org/10.1007/978-3-319-16817-3_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16816-6
Online ISBN: 978-3-319-16817-3
eBook Packages: Computer ScienceComputer Science (R0)