Region Merging Driven by Deep Learning for RGB-D Segmentation and Labeling
| Autor: | Maria Camporese, Giampaolo Pagnutti, Umberto Michieli, Pietro Zanuttigh, Andrea Agiollo |
|---|---|
| Přispěvatelé: | Nicola Conci, Caifeng Shan, Lucio Marcenaro, Jungong Han, Umberto Michieli, Maria Camporese, Andrea Agiollo, Giampaolo Pagnutti, Pietro Zanuttigh |
| Rok vydání: | 2019 |
| Předmět: |
Scheme (programming language)
Speedup Region Merging Convolutional Neural Networks Semantic Seg- mentation Deep Learning business.industry Computer science Deep learning 020206 networking & telecommunications Pattern recognition 02 engineering and technology Convolutional neural network 0202 electrical engineering electronic engineering information engineering RGB color model Join (sigma algebra) 020201 artificial intelligence & image processing Segmentation Artificial intelligence business computer computer.programming_language Free parameter |
| Zdroj: | ICDSC |
| Popis: | Among the various segmentation techniques, a widely used family of approaches are the ones based on region merging, where an initial oversegmentation is progressively refined by joining segments with similar characteristics. Instead of using deterministic approaches to decide which segments are going to be merged we propose to exploit a convolutional neural network which takes a couple of segments as input and decides whether to join or not the segments. We fitted this idea into an existent iterative semantic segmentation scheme for RGB-D data. We were able to lower the number of free parameters and to greatly speedup the procedure while achieving comparable or even higher results, thus allowing for its usage in free navigation systems. Furthermore, our method could be extended straightforwardly to other fields where region merging strategies are exploited. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|