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

Segment-and-count: Vehicle Counting in Aerial Imagery using Atrous Convolutional Neural Networks

Azimi, Seyedmajid and Vig, Eleonora and Kurz, Franz and Reinartz, Peter (2018) Segment-and-count: Vehicle Counting in Aerial Imagery using Atrous Convolutional Neural Networks. In: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, XLII-1, pp. 1-5. ISPRS Midterm Symposia 2018, 09.-12.Okt. 2018, Karlsruhe, Deutschland. DOI: 10.5194/isprs-archives-XLII-1-19-2018

[img] PDF
2MB

Official URL: https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-1/19/2018/isprs-archives-XLII-1-19-2018.pdf

Abstract

High-resolution aerial imagery can provide detailed and in some cases even real-time information about traffic related objects. Vehicle localization and counting using aerial imagery play an important role in a broad range of applications. Recently, convolutional neural networks (CNNs) with atrous convolution layers have shown better performance for semantic segmentation compared to conventional convolutional aproaches. In this work, we propose a joint vehicle segmentation and counting method based on atrous convolutional layers. This method uses a multi-task loss function to simultaneously reduce pixel-wise segmentation and vehicle counting errors. In addition, the rectangular shapes of vehicle segmentations are refined using morphological operations. In order to evaluate the proposed methodology, we apply it to the public "DLR 3K" benchmark dataset which contains aerial images with a ground sampling distance of 13 cm. Results show that our proposed method reaches 81.58% mean intersection over union in vehicle segmentation and shows an accuracy of 91.12% in vehicle counting, outperforming the baselines.

Item URL in elib:https://elib.dlr.de/123595/
Document Type:Conference or Workshop Item (Speech)
Title:Segment-and-count: Vehicle Counting in Aerial Imagery using Atrous Convolutional Neural Networks
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
Kurz, Franzfranz.kurz (at) dlr.dehttps://orcid.org/0000-0003-1718-0004
Reinartz, Peterpeter.reinartz (at) dlr.dehttps://orcid.org/0000-0002-8122-1475
Date:October 2018
Journal or Publication Title:International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
Refereed publication:No
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:No
Volume:XLII-1
DOI :10.5194/isprs-archives-XLII-1-19-2018
Page Range:pp. 1-5
Status:Published
Keywords:Vehicle Segmentation, Vehicle Counting, Aerial Imagery, Convolutional Neural Networks, Atrous Convolution
Event Title:ISPRS Midterm Symposia 2018
Event Location:Karlsruhe, Deutschland
Event Type:international Conference
Event Dates:09.-12.Okt. 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 17:07
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.