Scene Parsing Using Region-Based Generative Models
| Autor: | Jiebo Luo, Chris Brown, Matthew Boutell |
|---|---|
| Rok vydání: | 2007 |
| Předmět: |
Parsing
Contextual image classification Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Scene statistics Pattern recognition Belief propagation computer.software_genre Semantics Object detection Computer Science Applications Generative model Discriminative model Signal Processing Media Technology Computer vision Artificial intelligence Electrical and Electronic Engineering business computer ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | IEEE Transactions on Multimedia. 9:136-146 |
| ISSN: | 1520-9210 |
| DOI: | 10.1109/tmm.2006.886372 |
| Popis: | Semantic scene classification is a challenging problem in computer vision. In contrast to the common approach of using low-level features computed from the whole scene, we propose "scene parsing" utilizing semantic object detectors (e.g., sky, foliage, and pavement) and region-based scene-configuration models. Because semantic detectors are faulty in practice, it is critical to develop a region-based generative model of outdoor scenes based on characteristic objects in the scene and spatial relationships between them. Since a fully connected scene configuration model is intractable, we chose to model pairwise relationships between regions and estimate scene probabilities using loopy belief propagation on a factor graph. We demonstrate the promise of this approach on a set of over 2000 outdoor photographs, comparing it with existing discriminative approaches and those using low-level features |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|