Moving Object Extraction with a Localized Pyramid

In this paper, we present a tracking initialization method that combines a rough extraction of moving objects and a refined segmentation of their contours. The extraction of moving objects is obtained with a classical global motion compensation. To obtain accurate contours of the objects, a spatial segmentation is performed with an original localized graph pyramid that focuses the segmentation process either on the object areas or on their borders.

• Type: Conference
• Year: 2004
• Where: ICPR
• Authors: Jérémy Huart, Guillaume Foret, Pascal Bertolino
• Keywords: Computer Vision, ICPR 2004, Localized Graph Pyramid, Segmentation Process, Spatial Segmentation