Robust KLT Tracking with Gaussian and Laplacian of Gaussian Weighting Functions

Object tracking algorithms extensively found in literature are either constrained with assumptions or are overly sensitive to noise. We propose and successfully test two new weighting functions for a feature-based object tracker to achieve superior tracking performance and noise immunity. Also presented is a mechanism for image based optimal weighting function determination.

• Type: Conference
• Year: 2004
• Where: ICPR
• Authors: Anup Basu, Meghna Singh, Mrinal K. Mandal
• Keywords: Computer Vision, Feature-based Object Tracker, ICPR 2004, Object Tracking Algorithms, Optimal Weighting Function