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

Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery

Azimi, Seyedmajid and Vig, Eleonora and Bahmanyar, Reza and Körner, Marco and Reinartz, Peter (2018) Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery. Asian Conference of Computer Vision 2018 (ACCV), 02.-6. Dez. 2018, Perth, Western Australia.

[img] PDF
6MB

Official URL: https://arxiv.org/abs/1807.02700

Abstract

Automatic multi-class object detection in remote sensing images in unconstrained scenarios is of high interest for several applications including traffic monitoring and disaster management. The huge variation in object scale, orientation, category, and complex backgrounds, as well as the different camera sensors pose great challenges for current algorithms. In this work, we propose a new method consisting of a novel joint image cascade and feature pyramid network with multi-size convolution kernels to extract multi-scale strong and weak semantic features. These features are fed into rotation-based region proposal and region of interest networks to produce object detections. Finally, rotational non-maximum suppression is applied to remove redundant detections. During training, we minimize joint horizontal and oriented bounding box loss functions, as well as a novel loss that enforces oriented boxes to be rectangular. Our method achieves 68.16% mAP on horizontal and 72.45% mAP on oriented bounding box detection tasks on the challenging DOTA dataset, outperforming all published methods by a large margin (+6% and +12% absolute improvement, respectively). Furthermore, it generalizes to two other datasets, NWPU VHR-10 and UCAS-AOD, and achieves competitive results with the baselines even when trained on DOTA. Our method can be deployed in multi-class object detection applications, regardless of the image and object scales and orientations, making it a great choice for unconstrained aerial and satellite imagery.

Item URL in elib:https://elib.dlr.de/123599/
Document Type:Conference or Workshop Item (Speech)
Title:Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Azimi, SeyedmajidSeyedmajid.Azimi (at) dlr.dehttps://orcid.org/0000-0002-6084-2272
Vig, EleonoraEleonora.Vig (at) dlr.deUNSPECIFIED
Bahmanyar, Rezareza.bahmanyar (at) dlr.deUNSPECIFIED
Körner, Marcomarco.koerner (at) tum.deUNSPECIFIED
Reinartz, Peterpeter.reinartz (at) dlr.dehttps://orcid.org/0000-0002-8122-1475
Date:2018
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Page Range:pp. 1-16
Status:Published
Keywords:Multi-class Object Detection, Remote Sensing Imagery, traffic monitoring
Event Title:Asian Conference of Computer Vision 2018 (ACCV)
Event Location:Perth, Western Australia
Event Type:international Conference
Event Dates:02.-6. Dez. 2018
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Traffic Management (old)
DLR - Research area:Transport
DLR - Program:V VM - Verkehrsmanagement
DLR - Research theme (Project):V - Vabene++ (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By: Zielske, Mandy
Deposited On:22 Nov 2018 17:10
Last Modified:31 Jul 2019 20:21

Repository Staff Only: item control page

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