DocumentCode :
75773
Title :
Parsing Facades with Shape Grammars and Reinforcement Learning
Author :
Teboul, O. ; Kokkinos, Iasonas ; Simon, Laurent ; Koutsourakis, P. ; Paragios, Nikos
Author_Institution :
MAS Lab., Ecole Centrale Paris, Chatenay-Malabry, France
Volume :
35
Issue :
7
fYear :
2013
fDate :
Jul-13
Firstpage :
1744
Lastpage :
1756
Abstract :
In this paper, we use shape grammars (SGs) for facade parsing, which amounts to segmenting 2D building facades into balconies, walls, windows, and doors in an architecturally meaningful manner. The main thrust of our work is the introduction of reinforcement learning (RL) techniques to deal with the computational complexity of the problem. RL provides us with techniques such as Q-learning and state aggregation which we exploit to efficiently solve facade parsing. We initially phrase the 1D parsing problem in terms of a Markov Decision Process, paving the way for the application of RL-based tools. We then develop novel techniques for the 2D shape parsing problem that take into account the specificities of the facade parsing problem. Specifically, we use state aggregation to enforce the symmetry of facade floors and demonstrate how to use RL to exploit bottom-up, image-based guidance during optimization. We provide systematic results on the Paris building dataset and obtain state-of-the-art results in a fraction of the time required by previous methods. We validate our method under diverse imaging conditions and make our software and results available online.
Keywords :
Markov processes; grammars; image segmentation; learning (artificial intelligence); 1D parsing problem; 2D shape parsing problem; Markov decision process; Q-learning; SG; computational complexity; facade parsing problem; image-based guidance; reinforcement learning techniques; semantic segmentation; shape grammars; state aggregation; Equations; Grammar; Image segmentation; Learning; Markov processes; Optimization; Shape; Image arsing; Markov decision processes; data-driven exploration; reinforcement learning; semantic segmentation; shape grammar;
fLanguage :
English
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/TPAMI.2012.252
Filename :
6361407
Link To Document :
بازگشت