Improving Semantic Segmentation With Generalized Models Of Local Context
| Autor: | Hasan Fehmi Ateş, Sercan Sünetci |
|---|---|
| Přispěvatelé: | Işık Üniversitesi, Mühendislik Fakültesi, Elektrik-Elektronik Mühendisliği Bölümü, Işık University, Faculty of Engineering, Department of Electrical-Electronics Engineering, Ateş, Hasan Fehmi, Sünetci, Sercan |
| Rok vydání: | 2017 |
| Předmět: |
Computer science
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Scale-space segmentation Context (language use) 02 engineering and technology 010501 environmental sciences computer.software_genre 01 natural sciences Image (mathematics) Consistency (database systems) Segmentation 0202 electrical engineering electronic engineering information engineering Computer vision Superpixel 0105 earth and related environmental sciences Parsing Pixel business.industry Pattern recognition Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) Class (biology) Computer Science::Computer Vision and Pattern Recognition Image parsing 020201 artificial intelligence & image processing Artificial intelligence business MRF computer |
| Zdroj: | Computer Analysis of Images and Patterns ISBN: 9783319646978 CAIP (2) |
| Popis: | Semantic segmentation (i.e. image parsing) aims to annotate each image pixel with its corresponding semantic class label. Spatially consistent labeling of the image requires an accurate description and modeling of the local contextual information. Superpixel image parsing methods provide this consistency by carrying out labeling at the superpixel-level based on superpixel features and neighborhood information. In this paper, we develop generalized and flexible contextual models for superpixel neighborhoods in order to improve parsing accuracy. Instead of using a fixed segmentation and neighborhood definition, we explore various contextual models to combine complementary information available in alternative superpixel segmentations of the same image. Simulation results on two datasets demonstrate significant improvement in parsing accuracy over the baseline approach. This work is supported in part by TUBITAK project no: 115E307 and by Isik University BAP project no: 14A205 Publisher's Version |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|