Quasi-Regular Facade Structure Extraction

MPhil Thesis Defence

Title: "Quasi-Regular Facade Structure Extraction"

By

Mr. Tian HAN


Abstract

In this thesis, we present a two-stage framework for extracting what we 
define as a quasi-regular structure in facade images. A quasi-regular 
structure is an rectangular grid representing the placements of repetitive 
structural architecture objects, e.g., windows, in a facade. Such a 
structure generalizes a perfect single lattice structure with a manageable 
complexity. In our two-stage framework, first, we propose to formulate the 
window detection using an object-oriented Marked Point Process model with 
an efficient MCMC sampler. This lead to an initial structure map which 
indicates potential window locations. Then in the second stage, we propose 
a regularization scheme based on the initial structure map to recover the 
complete structure. This stage takes advantage of previously obtained 
objects information and the intrinsic low rank constraint of the 
quasi-regular structure, thus can reliably extract underlying structures 
from arbitrary shaped windows. We have extensively evaluated our method 
over a large variety of facade images, and demonstrated both the 
efficiency and robustness of our two-stage framework. In addition, both 
qualitative and quantitative comparison with other state-of-art methods 
are presented to show the superiority of our framework.


Date:			Tuesday, 18 June 2013

Time:			4:00pm – 6:00pm

Venue:			Room 5486
 			Lifts 25/26

Committee Members:	Dr. Chiew-Lan Tai (Supervisor)
 			Dr. Huamin Qu (Chairperson)
 			Dr. Pedro Sander


**** ALL are Welcome ****