Show simple item record

dc.contributor.authorWu, Zhengen_US
dc.contributor.authorHristov, Nickolay I.en_US
dc.contributor.authorHedrick, Tyson L.en_US
dc.contributor.authorKunz, Thomas H.en_US
dc.contributor.authorBetke, Margriten_US
dc.date.accessioned2011-10-20T04:51:51Z
dc.date.available2011-10-20T04:51:51Z
dc.date.issued2009-09en_US
dc.identifier.citationWu, Zheng; Hristov, Nickolay; Hedrick, Tyson; Kunz, Thomas; Betke, Margrit. "Tracking a Large Number of Objects from Multiple Views", Technical Report BUCS-TR-2009-005, Computer Science Department, Boston University, March 10, 2009. [Available from: http://hdl.handle.net/2144/1728]en_US
dc.identifier.urihttps://hdl.handle.net/2144/1728
dc.description.abstractWe propose a multi-object multi-camera framework for tracking large numbers of tightly-spaced objects that rapidly move in three dimensions. We formulate the problem of finding correspondences across multiple views as a multidimensional assignment problem and use a greedy randomized adaptive search procedure to solve this NP-hard problem efficiently. To account for occlusions, we relax the one-to-one constraint that one measurement corresponds to one object and iteratively solve the relaxed assignment problem. After correspondences are established, object trajectories are estimated by stereoscopic reconstruction using an epipolar-neighborhood search. We embedded our method into a tracker-to-tracker multi-view fusion system that not only obtains the three-dimensional trajectories of closely-moving objects but also accurately settles track uncertainties that could not be resolved from single views due to occlusion. We conducted experiments to validate our greedy assignment procedure and our technique to recover from occlusions. We successfully track hundreds of flying bats and provide an analysis of their group behavior based on 150 reconstructed 3D trajectories.en_US
dc.description.sponsorshipNational Science Foundation (0326483, 0910908)en_US
dc.language.isoen_USen_US
dc.publisherBoston University Computer Science Departmenten_US
dc.relation.ispartofseriesBUCS Technical Reports;BUCS-TR-2009-005en_US
dc.titleTracking a Large Number of Objects from Multiple Viewsen_US
dc.typeTechnical Reporten_US


This item appears in the following Collection(s)

Show simple item record