Improving semantic segmentation with generalized models of local context

Yükleniyor...
Küçük Resim

Tarih

2017

Dergi Başlığı

Dergi ISSN

Cilt Başlığı

Yayıncı

Springer International Publishing AG

Erişim Hakkı

info:eu-repo/semantics/closedAccess

Araştırma projeleri

Organizasyon Birimleri

Dergi sayısı

Özet

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.

Açıklama

Anahtar Kelimeler

Image parsing, Segmentation, Superpixel, MRF

Kaynak

17th International Conference on Computer Analysis of Images and Patterns (CAIP)

WoS Q Değeri

Q4

Scopus Q Değeri

Q3

Cilt

10425

Sayı

Künye

Ateş, H. F. & Sünetci, S. (2017). Improving semantic segmentation with generalized models of local context. Paper presented at the 17th International Conference on Computer Analysis of Images and Patterns (CAIP), 10425 320-330. doi:10.1007/978-3-319-64698-5_27