Multiresolution and local search methods for optimizing visual tracking processes on GPU

  • Authors:
  • Raúl Cabido;Antonio S. Montemayor;Juan José Pantrigo;Bryson R. Payne

  • Affiliations:
  • Universidad Rey Juan Carlos (Madrid, SPAIN);Universidad Rey Juan Carlos (Madrid, SPAIN);Universidad Rey Juan Carlos (Madrid, SPAIN);North Georgia College & State University

  • Venue:
  • ACM SIGGRAPH 2007 posters
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Some visual applications, such as virtual blackboards or gesture recognition for HCI applications, rely on precise visual tracking algorithms. In order to provide this accuracy, some refinement methods are needed as a complement to a coarser approach. In this case, Local Search (LS) methods are typically used, as their purpose is the exploration of a search space to improve a previous estimation. In this category fall many search algorithms such as Tabu Search, Simulated Annealing, Scatter Search, etc.