Trajectory Analysis and Prediction for Improved Pedestrian Safety: Integrated Framework and Evaluations

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

18 Citationer (Scopus)
886 Downloads (Pure)

Resumé

This paper presents a monocular and purely vision based pedestrian trajectory tracking and prediction framework with integrated map-based hazard inference. In Advanced Driver Assistance systems research, a lot of effort has been put into pedestrian detection over the last decade, and several pedestrian detection systems are indeed showing impressive results. Considerably less effort has been put into processing the detections further. We present a tracking system for pedestrians, which based on detection bounding boxes tracks pedestrians and is able to predict their positions in the near future.

The tracking system is combined with a module which, based on the car's GPS position acquires a map and uses the road information in the map to know where the car can drive. Then the system warns the driver about pedestrians at risk, by combining the information about hazardous areas for pedestrians with a probabilistic position prediction for all observed pedestrians.
OriginalsprogEngelsk
TitelIEEE Intelligent Vehicles Symposium (IV), 2015
Antal sider6
ForlagIEEE
Publikationsdato2015
Sider330-335
ISBN (Trykt)978-1-4673-7266-4
DOI
StatusUdgivet - 2015
Begivenhed2015 IEEE Intelligent Vehicles Symposium - COEX, Seoul, Sydkorea
Varighed: 28 jun. 20151 jul. 2015

Konference

Konference2015 IEEE Intelligent Vehicles Symposium
LokationCOEX
LandSydkorea
BySeoul
Periode28/06/201501/07/2015

Fingerprint

Pedestrian safety
Trajectories
Railroad cars
Advanced driver assistance systems
Global positioning system
Hazards
Processing

Citer dette

@inproceedings{d5954cf89e534571a69c1b741a8c0a8c,
title = "Trajectory Analysis and Prediction for Improved Pedestrian Safety: Integrated Framework and Evaluations",
abstract = "This paper presents a monocular and purely vision based pedestrian trajectory tracking and prediction framework with integrated map-based hazard inference. In Advanced Driver Assistance systems research, a lot of effort has been put into pedestrian detection over the last decade, and several pedestrian detection systems are indeed showing impressive results. Considerably less effort has been put into processing the detections further. We present a tracking system for pedestrians, which based on detection bounding boxes tracks pedestrians and is able to predict their positions in the near future.The tracking system is combined with a module which, based on the car's GPS position acquires a map and uses the road information in the map to know where the car can drive. Then the system warns the driver about pedestrians at risk, by combining the information about hazardous areas for pedestrians with a probabilistic position prediction for all observed pedestrians.",
author = "Andreas M{\o}gelmose and Trivedi, {Mohan M.} and Moeslund, {Thomas B.}",
year = "2015",
doi = "10.1109/IVS.2015.7225707",
language = "English",
isbn = "978-1-4673-7266-4",
pages = "330--335",
booktitle = "IEEE Intelligent Vehicles Symposium (IV), 2015",
publisher = "IEEE",
address = "United States",

}

Møgelmose, A, Trivedi, MM & Moeslund, TB 2015, Trajectory Analysis and Prediction for Improved Pedestrian Safety: Integrated Framework and Evaluations. i IEEE Intelligent Vehicles Symposium (IV), 2015. IEEE, s. 330-335, 2015 IEEE Intelligent Vehicles Symposium, Seoul, Sydkorea, 28/06/2015. https://doi.org/10.1109/IVS.2015.7225707

Trajectory Analysis and Prediction for Improved Pedestrian Safety : Integrated Framework and Evaluations. / Møgelmose, Andreas; Trivedi, Mohan M.; Moeslund, Thomas B.

IEEE Intelligent Vehicles Symposium (IV), 2015. IEEE, 2015. s. 330-335.

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

TY - GEN

T1 - Trajectory Analysis and Prediction for Improved Pedestrian Safety

T2 - Integrated Framework and Evaluations

AU - Møgelmose, Andreas

AU - Trivedi, Mohan M.

AU - Moeslund, Thomas B.

PY - 2015

Y1 - 2015

N2 - This paper presents a monocular and purely vision based pedestrian trajectory tracking and prediction framework with integrated map-based hazard inference. In Advanced Driver Assistance systems research, a lot of effort has been put into pedestrian detection over the last decade, and several pedestrian detection systems are indeed showing impressive results. Considerably less effort has been put into processing the detections further. We present a tracking system for pedestrians, which based on detection bounding boxes tracks pedestrians and is able to predict their positions in the near future.The tracking system is combined with a module which, based on the car's GPS position acquires a map and uses the road information in the map to know where the car can drive. Then the system warns the driver about pedestrians at risk, by combining the information about hazardous areas for pedestrians with a probabilistic position prediction for all observed pedestrians.

AB - This paper presents a monocular and purely vision based pedestrian trajectory tracking and prediction framework with integrated map-based hazard inference. In Advanced Driver Assistance systems research, a lot of effort has been put into pedestrian detection over the last decade, and several pedestrian detection systems are indeed showing impressive results. Considerably less effort has been put into processing the detections further. We present a tracking system for pedestrians, which based on detection bounding boxes tracks pedestrians and is able to predict their positions in the near future.The tracking system is combined with a module which, based on the car's GPS position acquires a map and uses the road information in the map to know where the car can drive. Then the system warns the driver about pedestrians at risk, by combining the information about hazardous areas for pedestrians with a probabilistic position prediction for all observed pedestrians.

U2 - 10.1109/IVS.2015.7225707

DO - 10.1109/IVS.2015.7225707

M3 - Article in proceeding

SN - 978-1-4673-7266-4

SP - 330

EP - 335

BT - IEEE Intelligent Vehicles Symposium (IV), 2015

PB - IEEE

ER -