Towards Semantic Understanding of Surrounding Vehicular Maneuvers

A Panoramic Vision-Based Framework for Real-World Highway Studies

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

6 Citationer (Scopus)
352 Downloads (Pure)

Resumé

This paper proposes the use of multiple low-cost visual sensors to obtain a surround view of the ego-vehicle for semantic understanding. A multi-perspective view will assist the analysis of naturalistic driving studies (NDS), by automating the task of data reduction of the observed sequences into events. A user-centric vision-based framework is presented using a vehicle detector and tracker in each separate perspective. Multi-perspective trajectories are estimated and analyzed to extract 14 different events, including potential dangerous behaviors such as overtakes and cut-ins. The system is tested on ten sequences of real-world data collected on U. S. highways. The results show the potential use of multiple low-cost visual sensors for semantic understanding around the ego-vehicle.
OriginalsprogEngelsk
Titel2016 IEEE Computer Vision and Pattern Recognition Workshops : Automatic Traffic Surveillance
ForlagIEEE
Publikationsdato19 dec. 2016
Sider1584-1591
ISBN (Trykt)978-1-5090-1438-5
ISBN (Elektronisk)978-1-5090-1437-8
DOI
StatusUdgivet - 19 dec. 2016
Begivenhed2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops: Automated Traffic Surveillance - Las Vegas, USA
Varighed: 1 jul. 2016 → …

Workshop

Workshop2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops: Automated Traffic Surveillance
LandUSA
ByLas Vegas
Periode01/07/2016 → …

Fingerprint

Semantics
Sensors
Costs
Data reduction
Trajectories
Detectors

Citer dette

Kristoffersen, Miklas Strøm ; Dueholm, Jacob Velling ; Satzoda, Ravi K. ; Trivedi, Mohan M. ; Møgelmose, Andreas ; Moeslund, Thomas B. / Towards Semantic Understanding of Surrounding Vehicular Maneuvers : A Panoramic Vision-Based Framework for Real-World Highway Studies. 2016 IEEE Computer Vision and Pattern Recognition Workshops: Automatic Traffic Surveillance. IEEE, 2016. s. 1584-1591
@inproceedings{4a8c0cca54d84dccb581f426a984c713,
title = "Towards Semantic Understanding of Surrounding Vehicular Maneuvers: A Panoramic Vision-Based Framework for Real-World Highway Studies",
abstract = "This paper proposes the use of multiple low-cost visual sensors to obtain a surround view of the ego-vehicle for semantic understanding. A multi-perspective view will assist the analysis of naturalistic driving studies (NDS), by automating the task of data reduction of the observed sequences into events. A user-centric vision-based framework is presented using a vehicle detector and tracker in each separate perspective. Multi-perspective trajectories are estimated and analyzed to extract 14 different events, including potential dangerous behaviors such as overtakes and cut-ins. The system is tested on ten sequences of real-world data collected on U. S. highways. The results show the potential use of multiple low-cost visual sensors for semantic understanding around the ego-vehicle.",
author = "Kristoffersen, {Miklas Str{\o}m} and Dueholm, {Jacob Velling} and Satzoda, {Ravi K.} and Trivedi, {Mohan M.} and Andreas M{\o}gelmose and Moeslund, {Thomas B.}",
year = "2016",
month = "12",
day = "19",
doi = "10.1109/CVPRW.2016.197",
language = "English",
isbn = "978-1-5090-1438-5",
pages = "1584--1591",
booktitle = "2016 IEEE Computer Vision and Pattern Recognition Workshops",
publisher = "IEEE",
address = "United States",

}

Kristoffersen, MS, Dueholm, JV, Satzoda, RK, Trivedi, MM, Møgelmose, A & Moeslund, TB 2016, Towards Semantic Understanding of Surrounding Vehicular Maneuvers: A Panoramic Vision-Based Framework for Real-World Highway Studies. i 2016 IEEE Computer Vision and Pattern Recognition Workshops: Automatic Traffic Surveillance. IEEE, s. 1584-1591, 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops: Automated Traffic Surveillance, Las Vegas, USA, 01/07/2016. https://doi.org/10.1109/CVPRW.2016.197

Towards Semantic Understanding of Surrounding Vehicular Maneuvers : A Panoramic Vision-Based Framework for Real-World Highway Studies. / Kristoffersen, Miklas Strøm; Dueholm, Jacob Velling; Satzoda, Ravi K.; Trivedi, Mohan M.; Møgelmose, Andreas; Moeslund, Thomas B.

2016 IEEE Computer Vision and Pattern Recognition Workshops: Automatic Traffic Surveillance. IEEE, 2016. s. 1584-1591.

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - Towards Semantic Understanding of Surrounding Vehicular Maneuvers

T2 - A Panoramic Vision-Based Framework for Real-World Highway Studies

AU - Kristoffersen, Miklas Strøm

AU - Dueholm, Jacob Velling

AU - Satzoda, Ravi K.

AU - Trivedi, Mohan M.

AU - Møgelmose, Andreas

AU - Moeslund, Thomas B.

PY - 2016/12/19

Y1 - 2016/12/19

N2 - This paper proposes the use of multiple low-cost visual sensors to obtain a surround view of the ego-vehicle for semantic understanding. A multi-perspective view will assist the analysis of naturalistic driving studies (NDS), by automating the task of data reduction of the observed sequences into events. A user-centric vision-based framework is presented using a vehicle detector and tracker in each separate perspective. Multi-perspective trajectories are estimated and analyzed to extract 14 different events, including potential dangerous behaviors such as overtakes and cut-ins. The system is tested on ten sequences of real-world data collected on U. S. highways. The results show the potential use of multiple low-cost visual sensors for semantic understanding around the ego-vehicle.

AB - This paper proposes the use of multiple low-cost visual sensors to obtain a surround view of the ego-vehicle for semantic understanding. A multi-perspective view will assist the analysis of naturalistic driving studies (NDS), by automating the task of data reduction of the observed sequences into events. A user-centric vision-based framework is presented using a vehicle detector and tracker in each separate perspective. Multi-perspective trajectories are estimated and analyzed to extract 14 different events, including potential dangerous behaviors such as overtakes and cut-ins. The system is tested on ten sequences of real-world data collected on U. S. highways. The results show the potential use of multiple low-cost visual sensors for semantic understanding around the ego-vehicle.

U2 - 10.1109/CVPRW.2016.197

DO - 10.1109/CVPRW.2016.197

M3 - Article in proceeding

SN - 978-1-5090-1438-5

SP - 1584

EP - 1591

BT - 2016 IEEE Computer Vision and Pattern Recognition Workshops

PB - IEEE

ER -