Where is It? Object Reacquisition in Surveillance Video
Fabian Campbell-West, Hongbin Wang, Paul Miller · 2008
We investigate the novel use of online PCA as a means of learning an object representation for track reacquisition following relatively long periods of track loss. A new Bayesian formulation for object verification is presented and correct track reacquisition is demonstrated for vehicles in ground- and air-based video. Video based object verification in airborne video is a new area, which uniquely positions this work.