000142801 001__ 142801
000142801 005__ 20190812205350.0
000142801 037__ $$aCONF
000142801 245__ $$aMultiple Object Tracking using Flow Linear Programming
000142801 269__ $$a2009
000142801 260__ $$c2009
000142801 336__ $$aConference Papers
000142801 520__ $$aMulti-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 problem results in a convex problem that can be solved using standard Linear Programming techniques. In addition, this new approach is far simpler formally and algorithmically than existing techniques and yields excellent results on the PETS 2009 data set.
000142801 6531_ $$aLinear Programming
000142801 6531_ $$aMultiple Object Tracking
000142801 6531_ $$aPedestrian Tracking
000142801 700__ $$aBerclaz, Jérôme
000142801 700__ $$0240254$$g146262$$aFleuret, François
000142801 700__ $$0240252$$g112366$$aFua, Pascal
000142801 7112_ $$cSnowbird, Utah$$a12th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (Winter-PETS 2009)
000142801 8564_ $$zn/a$$uhttps://infoscience.epfl.ch/record/142801/files/top.pdf$$s3460762
000142801 909C0 $$xU10659$$pCVLAB$$0252087
000142801 909CO $$ooai:infoscience.tind.io:142801$$qGLOBAL_SET$$pconf$$pIC
000142801 937__ $$aCVLAB-CONF-2009-005
000142801 973__ $$rNON-REVIEWED$$sPUBLISHED$$aEPFL
000142801 980__ $$aCONF