Search
Abstract
The article reviews neural network architectures designed for the segmentation task. It focuses mainly on instance segmentation of stacked objects. The main assumption is that segmentation is based on a color image with an additional depth layer. The paper also introduces the Stacked Bricks Dataset based on three cameras: RealSense L515, ZED2, and a synthetic one. Selected architectures: DeepLab, Mask RCNN, DEtection TRansformer, Geometry-Aware Instance Segmentation, Shapemask, Synthetic Depth Mask RCNN, Synthetic Fusion Mask RCNN (SF-Mask), Unseen Object Instance Segmentation (UOIS), Unseen Object Clustering (UOC), and You Look Only At Coefficients, have been tested on various datasets. The results show that the best architectures for stacked elements segmentation are UOIS, SF-Mask, and UOC.
Citations
-
0
CrossRef
-
0
Web of Science
-
0
Scopus
Authors (3)
-
-
Rafał Okuński
Cite as
Full text
- Publication version
- Accepted or Published Version
- DOI:
- Digital Object Identifier (open in new tab) 10.1016/j.engappai.2023.106942
- License
-
open in new tab
Keywords
Details
- Category:
- Articles
- Type:
- artykuły w czasopismach
- Published in:
-
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
no. 126,
ISSN: 0952-1976 - Language:
- English
- Publication year:
- 2023
- Bibliographic description:
- Czubenko M., Chrzanowski A., Okuński R.: Instance segmentation of stack composed of unknown objects// ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE -,iss. 126 (2023), s.106942-
- DOI:
- Digital Object Identifier (open in new tab) 10.1016/j.engappai.2023.106942
- Sources of funding:
-
- Free publication
- Verified by:
- Gdańsk University of Technology
seen 92 times