Modeling Object Classes in Aerial Images Using Texture Motifs

We propose a canonical model for object classes in aerial images. This model is motivated by the observation that geographic regions of interest are characterized by collections of texture motifs corresponding to the geographic processes that generate them. We show that this model is effective in learning the common texture themes, or motifs, of the object classes.

• Type: Conference
• Year: 2002
• Where: ICPR
• Authors: Sitaram Bhagavathy, Shawn Newsam, B. S. Manjunath
• Keywords: Common Texture Themes, Computer Vision, ICPR 2002, Object Classes, Texture Motifs