Model-Free, Statistical Detection and Tracking of Moving Objects

A novel statistical approch for detection and tracking of objects is presented here, which uses both edge and color information in a particle filter. The approach does not need any prior models of the objects of interest or of the scene. It starts with homogenous regions as tracking primitives and creates complex objects by merging similar moving regions. Even partially occluded objects in a sequence captured by a moving camera can be tracked efficently and robust.

• Type: Conference
• Year: 2006
• Where: ICIP
• Authors: Mark Ross
• Keywords: Complex Objects, Homogenous Regions, ICIP 2006, Image Processing, Similar Moving Regions