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

LW-ODF: A Light-Weight Object Detection Framework for Optical Remote Sensing Imagery

Wu, Xin and Hong, Danfeng and Ghamisi, Pedram and Li, Wei and Tao, Ran (2019) LW-ODF: A Light-Weight Object Detection Framework for Optical Remote Sensing Imagery. IGARSS 2019, 28.7.-2.8.19, Yokohama, Japan. DOI: 10.1109/IGARSS.2019.8898673

[img] PDF

Official URL: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8898673


In this paper, we propose to extract the multi-scaled and rotation-insensitive deep features to address the issues of object multi-solutions and rotations in geospatial object detection. To this end, we develop a novel object detection framework where a rotation-insensitive convolution neural network is applied for extracting multi-scaled and directioninsensitive feature representation and then the learned features can be fed into the ensemble classifier learning with fast feature pyramid. Such a non-end-to-end learning strategy intuitively reduces the computational cost without the additional performance loss, yielding an effective and efficient light-weight object detection framework. Experimental results conducted on the NWPU VHR-10 dataset demonstrate that the proposed framework outperforms several state-ofthe-art baselines.

Item URL in elib:https://elib.dlr.de/132297/
Document Type:Conference or Workshop Item (Poster)
Title:LW-ODF: A Light-Weight Object Detection Framework for Optical Remote Sensing Imagery
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Wu, XinBeijing Institute of TechnologyUNSPECIFIED
Hong, Danfengdanfeng.hong (at) dlr.deUNSPECIFIED
Ghamisi, Pedramp.ghamisi (at) gmail.comUNSPECIFIED
Li, WeiBeijing Institute of TechnologyUNSPECIFIED
Tao, RanBeijing Institute of TechnologyUNSPECIFIED
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:No
DOI :10.1109/IGARSS.2019.8898673
Page Range:pp. 1462-1465
Keywords:Deep learning, direction-insensitive, geospatial object detection, light-weight, multi-scaled, optical remote sensing imagery.
Event Title:IGARSS 2019
Event Location:Yokohama, Japan
Event Type:international Conference
Event Dates:28.7.-2.8.19
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 > EO Data Science
Deposited By: Hong, Danfeng
Deposited On:05 Dec 2019 16:05
Last Modified:05 Dec 2019 16:05

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.