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

R3-Net: A Deep Network for Multioriented Vehicle Detection in Aerial Images and Videos

Li, Qingpeng and Mou, LiChao and Xu, Qizhi and Zhang, Yun and Zhu, Xiao Xiang (2019) R3-Net: A Deep Network for Multioriented Vehicle Detection in Aerial Images and Videos. IEEE Transactions on Geoscience and Remote Sensing, 57 (7), pp. 5028-5042. IEEE - Institute of Electrical and Electronics Engineers. DOI: 10.1109/TGRS.2019.2895362 ISSN 0196-2892

[img] PDF - Registered users only until March 2021 - Published version
39MB

Official URL: https://ieeexplore.ieee.org/document/8651485

Abstract

Vehicle detection is a significant and challenging task in aerial remote sensing applications. Most existing methods detect vehicles with regular rectangle boxes and fail to offer the orientation of vehicles. However, the orientation information is crucial for several practical applications, such as the trajectory and motion estimation of vehicles. In this paper, we propose a novel deep network, called a rotatable region-based residual network (R 3 -Net), to detect multioriented vehicles in aerial images and videos. More specially, R 3 -Net is utilized to generate rotatable rectangular target boxes in a half coordinate system. First, we use a rotatable region proposal network (R-RPN) to generate rotatable region of interests (R-RoIs) from feature maps produced by a deep convolutional neural network. Here, a proposed batch averaging rotatable anchor strategy is applied to initialize the shape of vehicle candidates. Next, we propose a rotatable detection network (R-DN) for the final classification and regression of the R-RoIs. In R-DN, a novel rotatable position-sensitive pooling is designed to keep the position and orientation information simultaneously while downsampling the feature maps of R-RoIs. In our model, R-RPN and R-DN can be trained jointly. We test our network on two open vehicle detection image data sets, namely, DLR 3K Munich Data set and VEDAI Data set, demonstrating the high precision and robustness of our method. In addition, further experiments on aerial videos show the good generalization capability of the proposed method and its potential for vehicle tracking in aerial videos. The demo video is available at https://youtu.be/xCYD-tYudN0.

Item URL in elib:https://elib.dlr.de/134126/
Document Type:Article
Title:R3-Net: A Deep Network for Multioriented Vehicle Detection in Aerial Images and Videos
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Li, QingpengBeihang University, BeijingUNSPECIFIED
Mou, LiChaoLiChao.Mou (at) dlr.deUNSPECIFIED
Xu, QizhiBeihang University, BeijingUNSPECIFIED
Zhang, YunUniversity of New BrunswickUNSPECIFIED
Zhu, Xiao XiangDLR-IMF/TUM-SiPEOUNSPECIFIED
Date:2019
Journal or Publication Title:IEEE Transactions on Geoscience and Remote Sensing
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:57
DOI :10.1109/TGRS.2019.2895362
Page Range:pp. 5028-5042
Publisher:IEEE - Institute of Electrical and Electronics Engineers
ISSN:0196-2892
Status:Published
Keywords:Aerial images and videos, deep learning, multioriented detection, remote sensing, vehicle detection.
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: Mou, LiChao
Deposited On:17 Feb 2020 13:44
Last Modified:17 Feb 2020 13:44

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.