Towards Detection and Tracking of On-Road Objects

Roland Goecke, Niklas Pettersson, Lars Petersson

Research output: A Conference proceeding or a Chapter in BookConference contribution

3 Citations (Scopus)

Abstract

In this paper, we present a system capable of detecting and tracking on-road objects in the scene, in particular vehicles. Such a system is a useful part of a driver assistance system. This system employs two different techniques in the detection phase to increase the robustness. A large part of this paper is devoted to reducing the computational amount required of the overall algorithm by quickly excluding pixels above the horizon and on the road surface. The number of pixels that require further, computationally expensive processing is reduced by up to 65% in the sequences used in the experimental evaluation. Objects are detected in the remaining image areas by an improved boosting approach of weak classifiers based on the well-known AdaBoost and RealBoost approaches. The tracking is then done by a combination of periodically running the detection algorithm, while using adaptable templates at other times which allow for changes in shape and appearance as the car and the other vehicles travel along the road
Original languageEnglish
Title of host publicationProceedings of the 2007 IEEE Intelligent Vehicles Symposium IV
EditorsUrbano Nunes
Place of PublicationAustralia
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages416-421
Number of pages6
ISBN (Print)9781424410675, 1424410673
DOIs
Publication statusPublished - 2007
Event2007 IEEE Intelligent Vehicles Symposium IV - Istanbul, Istanbul, Turkey
Duration: 13 Jun 200715 Jun 2007

Conference

Conference2007 IEEE Intelligent Vehicles Symposium IV
CountryTurkey
CityIstanbul
Period13/06/0715/06/07

Fingerprint

Pixels
Adaptive boosting
Classifiers
Railroad cars
Processing

Cite this

Goecke, R., Pettersson, N., & Petersson, L. (2007). Towards Detection and Tracking of On-Road Objects. In U. Nunes (Ed.), Proceedings of the 2007 IEEE Intelligent Vehicles Symposium IV (pp. 416-421). Australia: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IVS.2007.4290150
Goecke, Roland ; Pettersson, Niklas ; Petersson, Lars. / Towards Detection and Tracking of On-Road Objects. Proceedings of the 2007 IEEE Intelligent Vehicles Symposium IV. editor / Urbano Nunes. Australia : IEEE, Institute of Electrical and Electronics Engineers, 2007. pp. 416-421
@inproceedings{53947a1ca79442059ca2ada35af05aec,
title = "Towards Detection and Tracking of On-Road Objects",
abstract = "In this paper, we present a system capable of detecting and tracking on-road objects in the scene, in particular vehicles. Such a system is a useful part of a driver assistance system. This system employs two different techniques in the detection phase to increase the robustness. A large part of this paper is devoted to reducing the computational amount required of the overall algorithm by quickly excluding pixels above the horizon and on the road surface. The number of pixels that require further, computationally expensive processing is reduced by up to 65{\%} in the sequences used in the experimental evaluation. Objects are detected in the remaining image areas by an improved boosting approach of weak classifiers based on the well-known AdaBoost and RealBoost approaches. The tracking is then done by a combination of periodically running the detection algorithm, while using adaptable templates at other times which allow for changes in shape and appearance as the car and the other vehicles travel along the road",
author = "Roland Goecke and Niklas Pettersson and Lars Petersson",
year = "2007",
doi = "10.1109/IVS.2007.4290150",
language = "English",
isbn = "9781424410675",
pages = "416--421",
editor = "Urbano Nunes",
booktitle = "Proceedings of the 2007 IEEE Intelligent Vehicles Symposium IV",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Goecke, R, Pettersson, N & Petersson, L 2007, Towards Detection and Tracking of On-Road Objects. in U Nunes (ed.), Proceedings of the 2007 IEEE Intelligent Vehicles Symposium IV. IEEE, Institute of Electrical and Electronics Engineers, Australia, pp. 416-421, 2007 IEEE Intelligent Vehicles Symposium IV, Istanbul, Turkey, 13/06/07. https://doi.org/10.1109/IVS.2007.4290150

Towards Detection and Tracking of On-Road Objects. / Goecke, Roland; Pettersson, Niklas; Petersson, Lars.

Proceedings of the 2007 IEEE Intelligent Vehicles Symposium IV. ed. / Urbano Nunes. Australia : IEEE, Institute of Electrical and Electronics Engineers, 2007. p. 416-421.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Towards Detection and Tracking of On-Road Objects

AU - Goecke, Roland

AU - Pettersson, Niklas

AU - Petersson, Lars

PY - 2007

Y1 - 2007

N2 - In this paper, we present a system capable of detecting and tracking on-road objects in the scene, in particular vehicles. Such a system is a useful part of a driver assistance system. This system employs two different techniques in the detection phase to increase the robustness. A large part of this paper is devoted to reducing the computational amount required of the overall algorithm by quickly excluding pixels above the horizon and on the road surface. The number of pixels that require further, computationally expensive processing is reduced by up to 65% in the sequences used in the experimental evaluation. Objects are detected in the remaining image areas by an improved boosting approach of weak classifiers based on the well-known AdaBoost and RealBoost approaches. The tracking is then done by a combination of periodically running the detection algorithm, while using adaptable templates at other times which allow for changes in shape and appearance as the car and the other vehicles travel along the road

AB - In this paper, we present a system capable of detecting and tracking on-road objects in the scene, in particular vehicles. Such a system is a useful part of a driver assistance system. This system employs two different techniques in the detection phase to increase the robustness. A large part of this paper is devoted to reducing the computational amount required of the overall algorithm by quickly excluding pixels above the horizon and on the road surface. The number of pixels that require further, computationally expensive processing is reduced by up to 65% in the sequences used in the experimental evaluation. Objects are detected in the remaining image areas by an improved boosting approach of weak classifiers based on the well-known AdaBoost and RealBoost approaches. The tracking is then done by a combination of periodically running the detection algorithm, while using adaptable templates at other times which allow for changes in shape and appearance as the car and the other vehicles travel along the road

U2 - 10.1109/IVS.2007.4290150

DO - 10.1109/IVS.2007.4290150

M3 - Conference contribution

SN - 9781424410675

SN - 1424410673

SP - 416

EP - 421

BT - Proceedings of the 2007 IEEE Intelligent Vehicles Symposium IV

A2 - Nunes, Urbano

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Australia

ER -

Goecke R, Pettersson N, Petersson L. Towards Detection and Tracking of On-Road Objects. In Nunes U, editor, Proceedings of the 2007 IEEE Intelligent Vehicles Symposium IV. Australia: IEEE, Institute of Electrical and Electronics Engineers. 2007. p. 416-421 https://doi.org/10.1109/IVS.2007.4290150