Track validation using gradient-based normalised cross-correlation
Citation:
Darren Caulfield and Kenneth Dawson-Howe, Track validation using gradient-based normalised cross-correlation, British Machine Vision Conference, Dundee, Scotland., 29/8/2011 - 2/9/2011, Jesse Hoey, Stephen McKenna and Emanuele Trucco, BMVA Press, 2011, 70.1 - 70.11Download Item:
Abstract:
We develop a gradient-based normalised cross-correlation tracker that is as robust as brute-force template matching while being signi?cantly more computationally ef?cient. The technique serves as the basis of our track validation algorithm: by tracking an object forwards in time, reinitialising at the end of the sequence and then tracking backwards in time, we can determine whether or not the object has been followed correctly ? the forwards and backwards trajectories will be very different for tracking failures. If such a failure occurs, we iteratively attempt to validate shorter portions of the video sequence
until validation is achieved. The algorithm provides a means of determining whether or not an object was tracked successfully without the need for ground truth data.
Author's Homepage:
http://people.tcd.ie/kdawsonDescription:
PUBLISHED
Author: DAWSON-HOWE, KENNETH MARK
Other Titles:
British Machine Vision ConferencePublisher:
BMVA PressType of material:
Conference PaperCollections
Availability:
Full text availableMetadata
Show full item recordLicences: