Multi-hypothesis contextual modeling for semantic segmentation
| Autor: | Hasan Fehmi Ateş, Sercan Sünetci |
|---|---|
| Přispěvatelé: | Ates, Hasan F. Istanbul Medipol Univ, Dept Comp Engn, TR-34810 Istanbul, Turkey, Sunetci, Sercan Isik Univ, Dept Elect & Elect Engn, TR-34980 Istanbul, Turkey, Ates, Hasan -- 0000-0002-6842-1528, Işık Üniversitesi, Mühendislik Fakültesi, Elektrik-Elektronik Mühendisliği Bölümü, Işık University, Faculty of Engineering, Department of Electrical-Electronics Engineering, Sünetci, Sercan |
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
FOS: Computer and information sciences
Computer science Computer Vision and Pattern Recognition (cs.CV) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology computer.software_genre 01 natural sciences Image (mathematics) Segmentation Artificial Intelligence 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Superpixel 010306 general physics Parsing Markov random field Pixel business.industry Pattern recognition Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) Scene Class (biology) Computer Science::Computer Vision and Pattern Recognition Image parsing Signal Processing 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Artificial intelligence MRF business computer Software |
| 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. Segmentation result is typically improved by Markov Random Field (MRF) optimization on the initial labels. However this improvement is limited by the accuracy of initial result and how the contextual neighborhood is defined. In this paper, we develop generalized and flexible contextual models for segmentation neighborhoods in order to improve parsing accuracy. Instead of using a fixed segmentation and neighborhood definition, we explore various contextual models for fusion of complementary information available in alternative segmentations of the same image. In other words, we propose a novel MRF framework that describes and optimizes the contextual dependencies between multiple segmentations. Simulation results on two common datasets demonstrate significant improvement in parsing accuracy over the baseline approaches. 8 pages and 3 figure, accepted to Pattern Recognition Letters, Elsevier |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|