Copyright © 2014 by Intelligent Systems Laboratory, Computer Science Department, Technion - Israel Institute of Technology, Haifa 3200003, Israel. All rights reserved


TheGrue.org

Non-Local Characterization Of Scenery Images: Statistics, 3d Reasoning, And A Generative Model

Non-Local Characterization Of Scenery Images: Statistics, 3d Reasoning, And A Generative ModelBy: Tamar Avraham, Michael Lindenbaum

This work focuses on characterizing scenery images. We semantically divide the objects in natural landscape scenes into background and foreground and show that the shapes of the regions associated with these two types are statistically different. We then focus on the background regions. We study statistical properties such as size and shape, location and relative location, the characteristics of the boundary curves and the correlation of the properties to the region's semantic identity. Then we discuss the imaging process of a simplified 3D scene model and show how it explains the empirical observations. We further show that the observed properties suffice to characterize the gist of scenery images, propose a generative parametric graphical model, and use it to learn and generate semantic sketches of new images, which indeed look like those associated with natural scenery.

 

Publications:

Non-Local Characteristics of Scenery Images: Statistics, 3D Reasoning, and a Generative Model. Tamar Avraham and Michael Lindenbaum, ECCV10 - The 11th European Conference on Computer Vision, 2010. Volume V, LNCS6315, pages 99-112.

[PDF]

 

Multiple Region Categorization for Scenery Images. Tamar Avraham, Ilya Gurvich, and Michael Lindenbaum, 16th International Conference on Image Analysis and Processing, Ravenna, Italy, September 2011.

[PDF]