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

MRCNet: Crowd counting and density map estimation in aerial and ground imagery

Bahmanyar, Reza and Vig, Eleonora and Reinartz, Peter (2019) MRCNet: Crowd counting and density map estimation in aerial and ground imagery. BMVC’s Workshop on Object Detection and Recognition for Security Screenin (BMVC-ODRSS), 09.-12. Sep. 2019, Cardiff, United Kingdom.

[img] PDF
2MB

Official URL: https://bmvc2019.org/workshops/

Abstract

In spite of the many advantages of aerial imagery for crowd monitoring and management at mass events, datasets of aerial images of crowds are still lacking in the field. As a remedy, in this work we introduce a novel crowd dataset, the DLR Aerial Crowd Dataset (DLR-ACD), which is composed of 33 large aerial images acquired from 16 flight campaigns over mass events with 226,291 persons annotated. To the best of our knowledge, DLR-ACD is the first aerial crowd dataset and will be released publicly. To tackle the problem of accurate crowd counting and density map estimation in aerial images of crowds, this work also proposes a new encoder-decoder convolutional neural network, the so-called Multi-Resolution Crowd Network (MRCNet). The encoder is based on the VGG-16 network and the decoder is composed of a set of bilinear upsampling and convolutional layers. Using two losses, one at an earlier level and another at the last level of the decoder, MRCNet estimates crowd counts and high-resolution crowd density maps as two different but interrelated tasks. In addition, MRCNet utilizes contextual and detailed local information by combining high- and low-level features through a number of lateral connections inspired by the Feature Pyramid Network (FPN) technique. We evaluated MRCNet on the proposed DLR-ACD dataset as well as on the ShanghaiTech dataset, a CCTV-based crowd counting benchmark. The results demonstrate that MRCNet outperforms the state-of-the-art crowd counting methods in estimating the crowd counts and density maps for both aerial and CCTV-based Images.

Item URL in elib:https://elib.dlr.de/128895/
Document Type:Conference or Workshop Item (Speech)
Title:MRCNet: Crowd counting and density map estimation in aerial and ground imagery
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Bahmanyar, Rezareza.bahmanyar (at) dlr.dehttps://orcid.org/0000-0002-6999-714X
Vig, EleonoraEleonora.Vig (at) dlr.deUNSPECIFIED
Reinartz, Peterpeter.reinartz (at) dlr.dehttps://orcid.org/0000-0002-8122-1475
Date:2019
Refereed publication:No
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Status:Accepted
Keywords:Aerial Imagery, Crowd Counting, Crowd Density Map Estimation, Convolutional Neural Networks, Disaster Management, Security Systems
Event Title:BMVC’s Workshop on Object Detection and Recognition for Security Screenin (BMVC-ODRSS)
Event Location:Cardiff, United Kingdom
Event Type:international Conference
Event Dates:09.-12. Sep. 2019
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Road Transport
DLR - Research area:Transport
DLR - Program:V ST Straßenverkehr
DLR - Research theme (Project):V - NGC KoFiF
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By: Bahmanyar, Gholamreza
Deposited On:29 Aug 2019 10:58
Last Modified:01 Nov 2019 03:00

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.