A Low-Power Graph Convolutional Network Processor With Sparse Grouping for 3D Point Cloud Semantic Segmentation in Mobile Devices

A low-power graph convolutional network (GCN) processor is proposed for accelerating 3D point cloud semantic segmentation (PCSS) in real-time on mobile devices. Three key features enable the low-power GCN-based 3D PCSS. First, the new hardware-friendly GCN algorithm, sparse grouping-based dilated gr...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on circuits and systems. I, Regular papers Regular papers, 2022-04, Vol.69 (4), p.1507-1518
Hauptverfasser:	Kim, Sangjin, Kim, Sangyeob, Lee, Juhyoung, Yoo, Hoi-Jun
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial neural networks Cloud computing Convolution deep neural network Electronic devices Feature extraction Graph convolutional network Image segmentation low-power accelerators Microprocessors Mobile handsets mobile mixed reality device Pipeline processing point cloud Point cloud compression Power consumption Power management Real time Semantic segmentation Semantics Three dimensional models Three-dimensional displays Workload Workloads
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!