Abstract | ||
---|---|---|
With strong inference of hierarchical and repetitive structures, semantic information has been widely used in dealing with urban scenes. In this paper, we present a super-pixel-based facade parsing framework which combines the top-down shape grammar splitting with bottom-up information aggregation: machine learning forecasts prior classes, super-pixels improve compactness, and boundary estimation divides the splitting into two procedures - raw and fine, providing a reasonable initial guess for the latter to achieve better random walk optimization results. We also put forward the correlation judging between floors for the purpose of compromising freedom degree reduction with style variety and flexibility, which is also introduced as alignment constraint term to extend the probability energy. Experiments show that our method converges fast and achieves the state-of-the-art results for different styles. Further study on understanding and reconstruction is in progress of exploiting these results. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ACPR.2013.81 | ACPR |
Keywords | Field | DocType |
alignment constraint term,optimisation,shape grammar,top-down shape grammar splitting,correlation-based facade parsing,forecasts prior class,correlation-based facade parsing framework,freedom degree reduction,boundary estimation,learning (artificial intelligence),random walk optimization result,super-pixel-based facade parsing framework,bottom-up information aggregation,probability energy,random walk optimization results,correlation judging,grammars,façade parsing,different style,machine learning,semantic information,probability,learning artificial intelligence | Rule-based machine translation,L-attributed grammar,Grammar-based code,Random walk,Shape grammar,Computer science,Algorithm,Artificial intelligence,Parsing,Parser combinator,Stochastic grammar,Machine learning | Conference |
Citations | PageRank | References |
1 | 0.41 | 7 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Runze Zhang | 1 | 4 | 2.83 |
Ruiling Deng | 2 | 1 | 0.75 |
Xin He | 3 | 2 | 0.78 |
Gang Zeng | 4 | 949 | 70.21 |
Rui Gan | 5 | 183 | 13.62 |
Hongbin Zha | 6 | 2206 | 183.36 |