Point cloud classification by dynamic graph CNN with adaptive feature fusion

Point cloud classification by dynamic graph CNN with adaptive feature fusion

Abstract The deep neural network has made the most advanced breakthrough in almost all 2D image tasks, so we consider the application of deep learning in 3D images. Point cloud data, as the most basic and important form of representation of 3D images, can accurately and intuitively show the real wor...

Full description

Bibliographic Details
Main Authors: Rui Guo, Yong Zhou, Jiaqi Zhao, Yiyun Man, Minjie Liu, Rui Yao, Bing Liu
Format: Article
Language:English
Published: Wiley 2021-04-01
Series:IET Computer Vision
Subjects:
belief networks
computer vision
convolution
feature extraction
image classification
image recognition
Online Access:https://doi.org/10.1049/cvi2.12039

Internet

https://doi.org/10.1049/cvi2.12039

Similar Items