IIIT Hyderabad Publications |
|||||||||
|
ParsingWorld’s Skylines using Shape-Constrained MRFsAuthors: Rashmi Vilas Tonge,Subhranshu Maji, C V Jawahar Conference: CVPR 2014 (Conference on Computer Vision and Pattern Recognition 2014) Date: 2014-06-23 Report no: IIIT/TR/2014/51 AbstractWe propose an approach for segmenting the individual buildings in typical skyline images. Our approach is based on a Markov Random Field (MRF) formulation that exploits the fact that such images contain overlapping objects of similar shapes exhibiting a “tiered” structure. Our contributions are the following: (1) A dataset of 120 highresolution skyline images from twelve different cities with over 4,000 individually labeled buildings that allows us to quantitatively evaluate the performance of various segmentation methods, (2) An analysis of low-level features that are useful for segmentation of buildings, and (3) A shapeconstrained MRF formulation that enforces shape priors over the regions. For simple shapes such as rectangles, our formulation is significantly faster to optimize than a standard MRF approach, while also being more accurate. We experimentally evaluate various MRF formulations and demonstrate the effectiveness of our approach in segmenting skyline images. Full paper: pdf Centre for Visual Information Technology |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |