CM-UNet: ConvMixer UNet for Segmentation of Unknown Objects in Cluttered Scenes

CM-UNet: ConvMixer UNet for Segmentation of Unknown Objects in Cluttered Scenes

Object segmentation in cluttered environments is a fundamental pre-processing step for many perception-related tasks such as vision-based robotic grasping. Most of the existing object segmentation methods are incapable of precisely segmenting unknown objects, particularly in scenarios exhibiting sig...

Description complète

Détails bibliographiques
Auteurs principaux: Xiaoqian Huang, Rana Azzam, Sajid Javed, Dongming Gan, Lakmal Seneviratne, Abdelqader Abusafieh, Yahya Zweiri
Format: Article
Langue:English
Publié: IEEE 2022-01-01
Collection:IEEE Access
Sujets:
ConvMixer-based network
UNet
object segmentation
cluttered scene
unknown objects
robotic grasping
Accès en ligne:https://ieeexplore.ieee.org/document/9963530/

Internet

https://ieeexplore.ieee.org/document/9963530/

Documents similaires