The Community for Technology Leaders
Green Image
Issue No. 09 - September (2011 vol. 33)
ISSN: 0162-8828
pp: 1806-1819
Jérôme Berclaz , École Polytechnique Fédérale de Lausanne, Lausanne
François Fleuret , Idiap Research Institute, Martigny
Engin Türetken , École Polytechnique Fédérale de Lausanne, Lausanne
Pascal Fua , École Polytechnique Fédérale de Lausanne, Lausanne
Multi-object tracking can be achieved by detecting objects in individual frames and then linking detections across frames. Such an approach can be made very robust to the occasional detection failure: If an object is not detected in a frame but is in previous and following ones, a correct trajectory will nevertheless be produced. By contrast, a false-positive detection in a few frames will be ignored. However, when dealing with a multiple target problem, the linking step results in a difficult optimization problem in the space of all possible families of trajectories. This is usually dealt with by sampling or greedy search based on variants of Dynamic Programming which can easily miss the global optimum. In this paper, we show that reformulating that step as a constrained flow optimization results in a convex problem. We take advantage of its particular structure to solve it using the k-shortest paths algorithm, which is very fast. This new approach is far simpler formally and algorithmically than existing techniques and lets us demonstrate excellent performance in two very different contexts.
Data association, multiobject tracking, K-shortest paths, linear programming.

J. Berclaz, P. Fua, F. Fleuret and E. Türetken, "Multiple Object Tracking Using K-Shortest Paths Optimization," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 33, no. , pp. 1806-1819, 2011.
88 ms
(Ver 3.3 (11022016))