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

Crash Rate Estimation by Aerial Image Analysis

Kornfeld, Nils and Lücken, Leonhard and Leich, Andreas and Wagner, Peter and Saul, Hagen and Hoffmann, Ragna (2018) Crash Rate Estimation by Aerial Image Analysis. In: Proceedings of Expert Symposium on Accident Research (ESAR) 2018. Expert Symposium on Accident Research (ESAR) 2018, 19.-20. April 2018, Hannover.

[img] PDF (Abstract)
203kB

Abstract

Estimating road safety is a major concern of a large body of theoretical research as well as for practitioners all over the world. Most related studies rely heavily on structured data as tables concerning the road geometry, infrastructural items, traffic volumes, etc., which are not always available. A more and more universally available source of data, which has rarely been used in conjunction with road safety research are aerial or satellite images. These images potentially contain a wealth of information relevant to the prediction of road safety if they could be thoroughly analyzed in great numbers. Coincident with the widespread availability of satellite and aerial images, machine learning algorithms for image processing and automatic object detection and classification are maturing. This allows the automated processing of huge amounts of image data by artificial neural networks (ANNs) or related machine learning systems, an area in which convolutional neural networks have shown a significant improvement over conventional methods. In the submitted work initial results on the application of machine learning on aerial images are presented. The goal is to determine an estimation of road safety levels. ANNs were trained to predict crash frequencies for road intersections relying merely on aerial images of the intersections. The used data consists of police recorded crashes in the city of Berlin and aerial images provided by the Berlin Senate Department for Urban Development. The performance of the ANN suggests that the line of research is worth further pursuit. For instance, the trained ANN was able to predict the presence of crashes on intersections in a Berlin district excluded from the training process with an accuracy of approximately 74%.

Item URL in elib:https://elib.dlr.de/120283/
Document Type:Conference or Workshop Item (Speech)
Title:Crash Rate Estimation by Aerial Image Analysis
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Kornfeld, Nilsnils.kornfeld (at) dlr.deUNSPECIFIED
Lücken, Leonhardleonhard.lücken (at) dlr.dehttps://orcid.org/0000-0001-6103-6531
Leich, Andreasandreas.leich (at) dlr.dehttps://orcid.org/0000-0001-5242-2051
Wagner, PeterPeter.Wagner (at) dlr.dehttps://orcid.org/0000-0001-9097-8026
Saul, HagenHagen.Saul (at) dlr.dehttps://orcid.org/0000-0001-6961-7883
Hoffmann, RagnaRagna.Hoffmann (at) dlr.deUNSPECIFIED
Date:2018
Journal or Publication Title:Proceedings of Expert Symposium on Accident Research (ESAR) 2018
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Status:Published
Keywords:Machine Learning, Deep Learning, Image Classification, Regression
Event Title:Expert Symposium on Accident Research (ESAR) 2018
Event Location:Hannover
Event Type:international Conference
Event Dates:19.-20. April 2018
Organizer:Medizinische Hochschule Hannover, Accident Research Unit; Medizinische Hochschule Hannover Trauma Department; Per L. Reichertz Institut für Medizinische Informatik
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 - D.MoVe
Location: Berlin-Adlershof
Institutes and Institutions:Institute of Transportation Systems
Deposited By: Kornfeld, Nils
Deposited On:08 Jan 2020 14:27
Last Modified:01 Jun 2020 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.