Please use this identifier to cite or link to this item: https://doi.org/10.1109/TCSVT.2006.885715
DC FieldValue
dc.titleCooperative multitarget tracking with efficient split and merge handling
dc.contributor.authorKumar, P.
dc.contributor.authorRanganath, S.
dc.contributor.authorSengupta, K.
dc.contributor.authorWeimin, H.
dc.date.accessioned2014-06-17T02:43:10Z
dc.date.available2014-06-17T02:43:10Z
dc.date.issued2006-12
dc.identifier.citationKumar, P., Ranganath, S., Sengupta, K., Weimin, H. (2006-12). Cooperative multitarget tracking with efficient split and merge handling. IEEE Transactions on Circuits and Systems for Video Technology 16 (12) : 1477-1489. ScholarBank@NUS Repository. https://doi.org/10.1109/TCSVT.2006.885715
dc.identifier.issn10518215
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/55444
dc.description.abstractFor applications such as behavior recognition it is important to maintain the identity of multiple targets, while tracking them in the presence of splits and merges, or occlusion of the targets by background obstacles. Here we propose an algorithm to handle multiple splits and merges of objects based on dynamic programming and a new geometric shape matching measure. We then cooperatively combine Kalman filter-based motion and shape tracking with the efficient and novel geometric shape matching algorithm. The system is fully automatic and requires no manual input of any kind for initialization of tracking. The target track initialization problem is formulated as computation of shortest paths in a directed and attributed graph using Dijkstra's shortest path algorithm. This scheme correctly initializes multiple target tracks for tracking even in the presence of clutter and segmentation errors which may occur in detecting a target. We present results on a large number of real world image sequences, where upto 17 objects have been tracked simultaneously in real-time, despite clutter, splits, and merges in measurements of objects. The complete tracking system including segmentation of moving objects works at 25 Hz on 352 × 288 pixel color image sequences on a 2.8-GHz Pentium-4 workstation. © 2006 IEEE.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/TCSVT.2006.885715
dc.sourceScopus
dc.subjectData association
dc.subjectDynamic programming (DP)
dc.subjectKalman filtering
dc.subjectMultitarget tracking (MTT)
dc.subjectShape matching
dc.subjectSplit and merge
dc.typeArticle
dc.contributor.departmentELECTRICAL & COMPUTER ENGINEERING
dc.description.doi10.1109/TCSVT.2006.885715
dc.description.sourcetitleIEEE Transactions on Circuits and Systems for Video Technology
dc.description.volume16
dc.description.issue12
dc.description.page1477-1489
dc.description.codenITCTE
dc.identifier.isiut000242614100003
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.