dc.contributor.author | Alam, Fahim Irfan | |
dc.contributor.author | Zhou, Jun | |
dc.contributor.author | Liew, Alan Wee-Chung | |
dc.contributor.author | Jia, Xiuping | |
dc.contributor.editor | Changlin Wang, Qihao Weng | |
dc.date.accessioned | 2017-06-08T05:48:48Z | |
dc.date.available | 2017-06-08T05:48:48Z | |
dc.date.issued | 2016 | |
dc.identifier.isbn | 9781509033324 | |
dc.identifier.issn | 2153-6996 | |
dc.identifier.doi | 10.1109/IGARSS.2016.7730798 | |
dc.identifier.uri | http://hdl.handle.net/10072/339311 | |
dc.description.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. | |
dc.description.peerreviewed | Yes | |
dc.language | English | |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | |
dc.publisher.place | United States | |
dc.relation.ispartofconferencename | 36th IEEE International Geoscience and Remote Sensing Symposium (IGARSS) | |
dc.relation.ispartofconferencetitle | 2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS) | |
dc.relation.ispartofdatefrom | 2016-07-10 | |
dc.relation.ispartofdateto | 2016-07-15 | |
dc.relation.ispartoflocation | Beijing, PEOPLES R CHINA | |
dc.relation.ispartofpagefrom | 6890 | |
dc.relation.ispartofpagefrom | 4 pages | |
dc.relation.ispartofpageto | 6893 | |
dc.relation.ispartofpageto | 4 pages | |
dc.relation.ispartofvolume | 2016-November | |
dc.subject.fieldofresearch | Artificial intelligence not elsewhere classified | |
dc.subject.fieldofresearchcode | 460299 | |
dc.title | CRF learning with CNN features for hyperspectral image segmentation | |
dc.type | Conference output | |
dc.type.description | E1 - Conferences | |
dc.type.code | E - Conference Publications | |
dc.description.version | Accepted Manuscript (AM) | |
gro.faculty | Griffith Sciences, School of Information and Communication Technology | |
gro.rights.copyright | © 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. | |
gro.hasfulltext | Full Text | |
gro.griffith.author | Liew, Alan Wee-Chung | |
gro.griffith.author | Zhou, Jun | |