GMMCP Tracker: Globally Optimal Generalized Maximum Multi Clique Problem for Multiple Object Tracking

Afshin Dehghan, Shayan Modiri Assari, Mubarak Shah; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 4091-4099

Abstract


Data association is the backbone to many multiple object tracking (MOT) methods. In this paper we formulate data association as a Generalized Maximum Multi Clique problem (GMMCP). We show that this is the ideal case of modeling tracking in real world scenario where all the pairwise relationships between targets in a batch of frames are taken into account. Previous works assume simplified version of our tracker either in problem formulation or problem optimization. However, we propose a solution using GMMCP where no simplification is assumed in either steps. We show that the NP hard problem of GMMCP can be formulated through Binary-Integer Program where for small and medium size MOT problems the solution can be found efficiently. We further propose a speed-up method, employing Aggregated Dummy Nodes for modeling occlusion and miss-detection, which reduces the size of the input graph without using any heuristics. We show that, using the speedup method, our tracker lends itself to real-time implementation which is plausible in many applications. We evaluated our tracker on six challenging sequences of Town Center, TUD-Crossing, TUD-Stadtmitte, Parking-lot 1, Parking-lot 2 and Parking-lot pizza and show favorable improvement against state of art.

Related Material


[pdf]
[bibtex]
@InProceedings{Dehghan_2015_CVPR,
author = {Dehghan, Afshin and Modiri Assari, Shayan and Shah, Mubarak},
title = {GMMCP Tracker: Globally Optimal Generalized Maximum Multi Clique Problem for Multiple Object Tracking},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}