A joint 3D image semantic segmentation and scalable coding scheme with ROI approach

Along with the digital evolution, image post-production and indexing have become one of the most advanced and desired services in the lossless 3D image domain. The 3D context provides a significant gain in terms of semantics for scene representation. However, it also induces many drawbacks including...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2014 IEEE Visual Communications and Image Processing Conference s. 270 - 273
Hlavní autoři: Samrouth, Khouloud, Deforges, Olivier, Yi Liu, Falou, Wassim, Khalil, Mohamad
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.12.2014
Témata:
3D scalable compression
Context
Image coding
Image color analysis
Image resolution
Image segmentation
RoI extraction and refinement
segmentation
Semantics
Three-dimensional displays
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Along with the digital evolution, image post-production and indexing have become one of the most advanced and desired services in the lossless 3D image domain. The 3D context provides a significant gain in terms of semantics for scene representation. However, it also induces many drawbacks including monitoring visual degradation of compressed 3D image (especially upon edges), and increased complexity for scene representation. In this paper, we propose a semantic region representation and a scalable coding scheme. First, the semantic region representation scheme is based on a low resolution version of the 3D image. It provides the possibility to segment the image according to a desirable balance between 2D and depth. Second, the scalable coding scheme consists in selecting a number of regions as a Region of Interest (RoI), based on the region representation, in order to be refined at a higher bitrate. Experiments show that the proposed scheme provides a high coherence between texture, depth and regions and ensures an efficient solution to the problems of compression and scene representation in the 3D image domain.
DOI:10.1109/VCIP.2014.7051556