CRF learning with CNN features for hyperspectral image segmentation
File version
Accepted Manuscript (AM)
Author(s)
Zhou, Jun
Liew, Alan Wee-Chung
Jia, Xiuping
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)
Changlin Wang, Qihao Weng
Date
Size
File type(s)
Location
Beijing, PEOPLES R CHINA
License
Abstract
This paper proposes a method that uses both spectral and spatial information to segment remote sensing hyperspectral images. After a hyperspectral image is over-segmented into superpixels, a deep Convolutional Neural Network (CNN) is used to perform superpixel-level labelling. To further delineate objects from a hyperspectral scene, this paper attempts to combine the properties of CNN and Conditional Random Field (CRF). A mean-field approximation algorithm for CRF inference is used and formulated with Gaussian pairwise potentials as Recurrent Neural Network. This combined network is then plugged into the CNN which leads to a deep network that has robust characteristics of both CNN and CRF. Preliminary results suggest the usefulness of this framework to a promising extent.
Journal Title
Conference Title
2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS)
Book Title
Edition
Volume
2016-November
Issue
Thesis Type
Degree Program
School
Publisher link
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement
© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Item Access Status
Note
Access the data
Related item(s)
Subject
Artificial intelligence not elsewhere classified