Name
Abstract | ||
|---|---|---|
This paper proposes an approach for the semantic segmentation and structural parsing of modular furniture items, such as cabinets, wardrobes, and bookshelves, into so called interaction elements. Such a segmentation into functional units is challenging not only due to the visual similarity of the different elements but also because of their often uniformly colored and low-texture appearance. Our method addresses these challenges by merging structural and appearance likelihoods of each element and jointly optimizing over shape, relative location, and class labels using Markov Chain Monte Carlo (MCMC) sampling. We propose a novel concept called rectangle coverings which provides a tight bound on the number of structural elements and hence narrows down the search space. We evaluate our approach's performance on a novel dataset of furniture items and demonstrate its applicability in practice. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1109/WACV.2016.7477638 | 2016 IEEE Winter Conference on Applications of Computer Vision (WACV) |
Keywords | Field | DocType |
semantic segmentation,structural parsing,modular furniture item,appearance color,appearance texture,Markov chain Monte Carlo sampling,MCMC sampling,rectangle covering | Computer vision,Scale-space segmentation,Pattern recognition,Markov chain Monte Carlo,Computer science,Segmentation,Image texture,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Parsing,Modular design | Conference |
ISSN | Citations | PageRank |
2472-6737 | 2 | 0.36 |
References | Authors | |
24 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tobias Pohlen | 1 | 2 | 0.36 |
| Ishrat Badami | 2 | 9 | 0.87 |
| Markus Mathias | 3 | 443 | 16.78 |
| Bastian Leibe | 4 | 5191 | 312.07 |