DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Cascade Active Learning for Evolution Pattern Extraction from SAR Image Time Series

Cui, Shiyong and Datcu, Mihai (2013) Cascade Active Learning for Evolution Pattern Extraction from SAR Image Time Series. In: MultiTemp 2013 Conference Proceedings, pp. 1-4. IEEE Xplore. MultiTemp 2013, 25.-27. June 2013, Banff, Alberta, Canada.

[img] PDF

Official URL: http://geog.ucalgary.ca/multitemp2013/sites/geog.ucalgary.ca.multitemp2013/files/multitemp_2013_final_program_-_june_27.pdf


In this paper, a cascade active learning approach relying on a coarse-to-fine strategy for evolution pattern indexing is developed, which allows fast indexing and hidden spatial and temporal pattern discovery in multi-temporal SAR images. In this approach, a hierarchical multi-level image representation is adopted and each level is associated with a specific patch size. SVM active learning is applied at each level to obtain reliable samples and reduce the manual effort in labeling the images. When moving to a new level, all the negative patches are neglected and the learning at the new level focuses only on the positive patches. In this way, the computation burden in annotating large data set could be remarkably reduced while keeping the accuracy. Through temporal pattern retrieval, the cascade active learning has been compared with a baseline SVM active learning operating only at the last level in terms of both accuracy and time complexity. We have demonstrated that cascade active learning can not only achieves better accuracy but also reduce remarkably the computation time.

Item URL in elib:https://elib.dlr.de/88812/
Document Type:Conference or Workshop Item (Speech)
Title:Cascade Active Learning for Evolution Pattern Extraction from SAR Image Time Series
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Cui, ShiyongShiyong.Cui (at) dlr.deUNSPECIFIED
Datcu, MihaiMihai.Datcu (at) dlr.deUNSPECIFIED
Journal or Publication Title:MultiTemp 2013 Conference Proceedings
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:No
Page Range:pp. 1-4
Publisher:IEEE Xplore
Keywords:Synthetic aperture radar (SAR), SAR Image Time Series, Multi-temporal SAR, Cascade Active Learning, Evolution Pattern.
Event Title:MultiTemp 2013
Event Location:Banff, Alberta, Canada
Event Type:international Conference
Event Dates:25.-27. June 2013
Organizer:University of Calgary
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Vorhaben hochauflösende Fernerkundungsverfahren
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited On:11 Apr 2014 14:59
Last Modified:31 Jul 2019 19:46

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.