Polar Occupancy Map - A Compact Traffic Representation for Deep Learning Scenario Classification

Halil Beglerovic; Jonas Ruebsam; Steffen Metzner; Martin Horn

doi:10.1109/ITSC.2019.8916947

Polar Occupancy Map - A Compact Traffic Representation for Deep Learning Scenario Classification

Halil Beglerovic, Jonas Ruebsam, Steffen Metzner, Martin Horn

Institute of Automation and Control (4430)

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Abstract

In order to accelerate development, testing and verification of automated vehicles, it is crucial to classify a wide range of driving scenarios. Scenario classification is usually done by rule-based algorithms or even manual video or signal inspection. A promising alternative is to use machine learning and let neural networks extract the relevant classification features. Since inputs to neural networks need to have a fixed size, an abstract representation of the driving scenario is necessary. In this paper, a scenario representation that captures the dynamic traffic behavior, without loss of relevant information, is presented.

Original language	English
Title of host publication	2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019
Publisher	Institute of Electrical and Electronics Engineers
Pages	4197-4203
Number of pages	7
ISBN (Electronic)	9781538670248
DOIs	https://doi.org/10.1109/ITSC.2019.8916947
Publication status	Published - 1 Oct 2019
Event	2019 IEEE Intelligent Transportation Systems Conference: ITSC 2019 - Auckland, New Zealand Duration: 27 Oct 2019 → 30 Oct 2019 https://www.itsc2019.org/

Publication series

Name	2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019

Conference

Conference	2019 IEEE Intelligent Transportation Systems Conference
Abbreviated title	ITSC 2019
Country/Territory	New Zealand
City	Auckland
Period	27/10/19 → 30/10/19
Internet address	https://www.itsc2019.org/

ASJC Scopus subject areas

Artificial Intelligence
Management Science and Operations Research
Instrumentation
Transportation

Access to Document

10.1109/ITSC.2019.8916947

Cite this

Beglerovic, H., Ruebsam, J., Metzner, S., & Horn, M. (2019). Polar Occupancy Map - A Compact Traffic Representation for Deep Learning Scenario Classification. In 2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019 (pp. 4197-4203). Article 8916947 (2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ITSC.2019.8916947

Polar Occupancy Map - A Compact Traffic Representation for Deep Learning Scenario Classification. / Beglerovic, Halil; Ruebsam, Jonas; Metzner, Steffen et al.
2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019. Institute of Electrical and Electronics Engineers, 2019. p. 4197-4203 8916947 (2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Beglerovic, H, Ruebsam, J, Metzner, S & Horn, M 2019, Polar Occupancy Map - A Compact Traffic Representation for Deep Learning Scenario Classification. in 2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019., 8916947, 2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019, Institute of Electrical and Electronics Engineers, pp. 4197-4203, 2019 IEEE Intelligent Transportation Systems Conference, Auckland, New Zealand, 27/10/19. https://doi.org/10.1109/ITSC.2019.8916947

Beglerovic H, Ruebsam J, Metzner S, Horn M. Polar Occupancy Map - A Compact Traffic Representation for Deep Learning Scenario Classification. In 2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019. Institute of Electrical and Electronics Engineers. 2019. p. 4197-4203. 8916947. (2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019). doi: 10.1109/ITSC.2019.8916947

@inproceedings{3e0a4c6960564a0c847f699274caa084,

title = "Polar Occupancy Map - A Compact Traffic Representation for Deep Learning Scenario Classification",

abstract = "In order to accelerate development, testing and verification of automated vehicles, it is crucial to classify a wide range of driving scenarios. Scenario classification is usually done by rule-based algorithms or even manual video or signal inspection. A promising alternative is to use machine learning and let neural networks extract the relevant classification features. Since inputs to neural networks need to have a fixed size, an abstract representation of the driving scenario is necessary. In this paper, a scenario representation that captures the dynamic traffic behavior, without loss of relevant information, is presented.",

author = "Halil Beglerovic and Jonas Ruebsam and Steffen Metzner and Martin Horn",

year = "2019",

month = oct,

day = "1",

doi = "10.1109/ITSC.2019.8916947",

language = "English",

series = "2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "4197--4203",

booktitle = "2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019",

address = "United States",

note = "2019 IEEE Intelligent Transportation Systems Conference : ITSC 2019, ITSC 2019 ; Conference date: 27-10-2019 Through 30-10-2019",

url = "https://www.itsc2019.org/",

}

TY - GEN

T1 - Polar Occupancy Map - A Compact Traffic Representation for Deep Learning Scenario Classification

AU - Beglerovic, Halil

AU - Ruebsam, Jonas

AU - Metzner, Steffen

AU - Horn, Martin

PY - 2019/10/1

Y1 - 2019/10/1

N2 - In order to accelerate development, testing and verification of automated vehicles, it is crucial to classify a wide range of driving scenarios. Scenario classification is usually done by rule-based algorithms or even manual video or signal inspection. A promising alternative is to use machine learning and let neural networks extract the relevant classification features. Since inputs to neural networks need to have a fixed size, an abstract representation of the driving scenario is necessary. In this paper, a scenario representation that captures the dynamic traffic behavior, without loss of relevant information, is presented.

AB - In order to accelerate development, testing and verification of automated vehicles, it is crucial to classify a wide range of driving scenarios. Scenario classification is usually done by rule-based algorithms or even manual video or signal inspection. A promising alternative is to use machine learning and let neural networks extract the relevant classification features. Since inputs to neural networks need to have a fixed size, an abstract representation of the driving scenario is necessary. In this paper, a scenario representation that captures the dynamic traffic behavior, without loss of relevant information, is presented.

UR - http://www.scopus.com/inward/record.url?scp=85076808015&partnerID=8YFLogxK

U2 - 10.1109/ITSC.2019.8916947

DO - 10.1109/ITSC.2019.8916947

M3 - Conference paper

T3 - 2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019

SP - 4197

EP - 4203

BT - 2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019

PB - Institute of Electrical and Electronics Engineers

T2 - 2019 IEEE Intelligent Transportation Systems Conference

Y2 - 27 October 2019 through 30 October 2019

ER -

Polar Occupancy Map - A Compact Traffic Representation for Deep Learning Scenario Classification

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this