DocumentCode :
2912850
Title :
Shape grammar parsing via Reinforcement Learning
Author :
Teboul, Olivier ; Kokkinos, Iasonas ; Simon, Loïc ; Koutsourakis, Panagiotis ; Paragios, Nikos
Author_Institution :
Lab. MAS, Ecole Centrale Paris, Paris, France
fYear :
2011
fDate :
20-25 June 2011
Firstpage :
2273
Lastpage :
2280
Abstract :
We address shape grammar parsing for facade segmentation using Reinforcement Learning (RL). Shape parsing entails simultaneously optimizing the geometry and the topology (e.g. number of floors) of the facade, so as to optimize the fit of the predicted shape with the responses of pixel-level ´terminal detectors´. We formulate this problem in terms of a Hierarchical Markov Decision Process, by employing a recursive binary split grammar. This allows us to use RL to efficiently find the optimal parse of a given facade in terms of our shape grammar. Building on the RL paradigm, we exploit state aggregation to speedup computation, and introduce image-driven exploration in RL to accelerate convergence. We achieve state-of-the-art results on facade parsing, with a significant speed-up compared to existing methods, and substantial robustness to initial conditions. We demonstrate that the method can also be applied to interactive segmentation, and to a broad variety of architectural styles.
Keywords :
Markov processes; grammars; hierarchical systems; image segmentation; learning (artificial intelligence); facade parsing; facade segmentation; hierarchical Markov decision process; interactive segmentation; reinforcement learning; robustness; shape grammar parsing; Buildings; Grammar; Image color analysis; Labeling; Learning; Markov processes; Shape;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Conference_Location :
Providence, RI
ISSN :
1063-6919
Print_ISBN :
978-1-4577-0394-2
Type :
conf
DOI :
10.1109/CVPR.2011.5995319
Filename :
5995319
Link To Document :
بازگشت