Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Tracking hand-off in large surveillance networks|
Van Den Hengel, A.
|Citation:||Conference proceedings: 24th International Conference Image and Vision Computing New Zealand (IVCNZ 2009), 23 – 25 November 2009, Wellington, New Zealand / Donald Bailey (ed.): pp.276-281|
|Conference Name:||International Conference Image and Vision Computing New Zealand (24th : 2009 : Wellington, New Zealand)|
|Alex Cichowski, Christopher Madden, Henry Detmold, Anthony Dick, Anton van den Hengel and Rhys Hill|
|Abstract:||This paper investigates the use of pairwise camera overlap estimates for supporting target tracking across large networks of surveillance cameras. We compare the use of camera overlap topology information to a method based on matching target appearance histograms, and also evaluate the effect of combining both methods. Tracking accuracy results are reported in terms of precision and recall for a 24 camera network. Camera overlap information is shown to deliver significant advantages for tracking when compared with simply matching target appearance histograms, due to its robustness to low quality imagery. We show empirically that this is the case even for automatically derived overlap estimates containing errors.|
|Description:||Invalid ISBN 9871424446988 as shown on the publication|
|Rights:||© 2009 IEEE|
|Appears in Collections:||Computer Science publications|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.